Table of Contentsheim.ifi.uio.no/griff/SIGMM-records-1401.pdfCommittee Draft for Green Metadata...

.

Volume 6, Number 1March 2014

Published by the Association for Computing MachinerySpecial Interest Group on Multimedia

ISSN 1947-4598http://sigmm.org/records

Table of Contents

1 Volume 6, Issue 1, March 2014 (ISSN 1947-4598)

1 ACM TOMM (TOMCCAP) Call for Special Issue Proposals

1 MPEG Column: 107th MPEG Meeting

3 ACM Multimedia 2013 Summary

17 Most cited papers before the era of ICMR

18 ESSENTIA: an open source library for audio analysis

21 SIGMM Award for Outstanding PhD Thesis in Multimedia Computing,

Communications and Applications

23 Call for Nominations for the SIGMM Technical Achievement Award 2014

24 MediaEval 2014: Benchmarking Initiative for Multimedia Evaluation

24 Call for Nominations: ACM TOMCCAP Nicolas D. Georganas Best Paper

Award

25 PhD Thesis Summaries

25 Håvard Espeland

25 Jia Hao

26 Johannes Konert

27 Recently published

27 IEEE MultiMedia Volume 21, Issue 2

28 MMSJ Volume 20, Issue 1

28 MMSJ Volume 20, Issue 2

28 MMTC R-Letter Volume 5, Issue 2

29 MTAP Volume 69, Issue 2

29 MTAP Volume 69, Issue 3

30 TOMCCAP, Volume 10, Issue 1s

30 TOMCCAP, Volume 10, Issue 2

31 TOMCCAP, Volume 10, Issue 3

31 Job Opportunities

31 PhD in IP-based media content delivery

32 PhD position in Computer Science

32 PhD position in computer science: Model-checking for malware detection

32 PhD position in computer science: Multimedia Networking

32 PhD position in computer science: Software verification

33 PostDoc position: Multimedia Communication

.

33 Researcher, Multimedia Search and Mining

33 Calls for Contribution

33 CFPs: Sponsored by ACM SIGMM

35 CFPs: Sponsored by ACM (any SIG)

36 CFPs: Sponsored by IEEE (any TC)

38 CFPs: Not ACM-/IEEE-sponsored

41 Back Matter

41 Notice to Contributing Authors to SIG Newsletters

41 Impressum

.

ACM SIGMM RecordsVol. 6, No. 1, March 2014 1


Volume 6, Issue 1, March 2014 (ISSN 1947-4598)

SIGMM RecordsVolume 6, Issue 1, March 2014 (ISSN 1947-4598)

ACM TOMM (TOMCCAP)Call for Special IssueProposals

ACM – TOMM is one of the world’s leading journalson multimedia. As in previous years, we are planningto publish a special issue in 2015. Proposals areaccepted until May, 1st 2014. Each special issue isin the responsibility of the guest editors. If you wishto guest edit a special issue, you should preparea proposal as outlined below, then send this via e-mail to the Senior Associate Editor (SAE) for SpecialIssue Management of TOMM, Shervin Shirmohammadi([email protected])

Call for Proposals – Special IssueDeadline for Proposal Submission: May, 1st 2014Notification: June, 1st 2014http://tomccap.acm.org/

Proposals should:

• Cover a current or emerging topic in the areaof multimedia computing, communications andapplications;

• Set out the importance of the special issue’s topic inthat area;

• Give a strategy for the recruitment of high qualitypapers;

• Indicate a draft timeline in which the special issuecould be produced (paper writing, reviewing, andsubmission of final copies to TOMM), assuming theproposal is accepted.

• Include the list of the proposed guest editors, theirshort bios, and their experience as related to theSpecial Issue’s topic

As in the previous years, the special issue will bepublished as online-only issue in the ACM DigitalLibrary. This gives the guest editors higher flexibility inthe review process and the number of papers to beaccepted, while yet ensuring a timely publication.

The proposals will be reviewed by the SAE together withthe EiC. The final decision will be made by the EiC. Anotification of acceptance for the proposals will be given

until June, 1st 2014. Once a proposal is accepted wewill contact you to discuss the further process.

For questions please contact:

• Shervin Shirmohammadi – Senior AssociateEditor for Special Issue Management( [email protected] )

• Ralf Steinmetz – Editor in Chief (EiC)( [email protected] )

• Sebastian Schmidt – Information Director( [email protected] )

MPEG Column: 107thMPEG Meeting– original posts here and here by Multimedia

Communication blog and bitmovin techblog, Christian

Timmerer, AAU/bitmovin

The MPEG-2 Transport Stream (M2TS; formally knownas Rec. ITU-T H.222.0 | ISO/IEC 13818-1) has beenawarded with the Technology & EngineeringEmmy® Award by the National Academy of TelevisionArts & Sciences. It is the fourth time MPEGreceived an Emmy award. The M2TS is widely deployedacross a broad range of application domain such asbroadcast, cable TV, Internet TV (IPTV and OTT), andBlu-ray Disks. The Emmy was received during thisyear’s CES2014 in Las Vegas.

Plenary during the 107th MPEG Meeting.

Other topics of the 107th MPEG meeting in San Joseinclude the following highlights:

• Requirements: Call for Proposals on Screen Contentjointly with ITU-T’s Video Coding Experts Group(VCEG)

http://records.sigmm.ndlab.net/2014/02/acm-tomm-tomccap-call-for-special-issue-proposals/



http://tomccap.acm.org/

http://records.sigmm.ndlab.net/2014/02/mpeg-column-107th-mpeg-meeting/

http://records.sigmm.ndlab.net/2014/02/mpeg-column-107th-mpeg-meeting/

http://multimediacommunication.blogspot.com/2014/01/mpeg-news-report-from-107th-meeting-san.html

http://www.bitmovin.net/blog-details/mpeg-news-a-report-from-the-107th-meeting-san-jose-ca-usa.html

http://multimediacommunication.blogspot.co.at/

http://multimediacommunication.blogspot.co.at/

http://www.bitmovin.net/blog.html

http://research.timmerer.com

http://research.timmerer.com

http://www.aau.at

http://www.bitmovin.net/

http://www.cesweb.org/Awards/Tech-Engineering-Emmy-Awards.aspx

.

MPEG Column: 107th MPEG Meeting

ISSN 1947-4598http://sigmm.org/records 2

ACM SIGMM RecordsVol. 6, No. 1, March 2014

• Systems: Committee Draft for Green Metadata

• Video: Study Text Committee Draft for CompactDescriptors for Visual Search (CDVS)

• JCT-VC: Draft Amendment for HEVC ScalableExtensions (SHVC)

• JCT-3D: Proposed Draft Amendment for HEVC 3DExtensions (3D-HEVC)

• Audio: 3D audio plans to progress to CD at 108thmeeting

• 3D Graphics: Working Draft 4.0 of AugmentedReality Application Format (ARAF) 2nd Edition

The official MPEG press release can be downloadedfrom the MPEG Web site. Some of the above highlightedtopics will be detailed in the following and, of course,there’s an update on DASH-related matters at the end.

Call for Proposals on Screen Content

Screen content refers to content coming not fromcameras but from screen/desktop sharing andcollaboration, cloud computing and gaming, wirelesslyconnected displays, control rooms with high resolutiondisplay walls, virtual desktop infrastructures, tabletsas secondary displays, PC over IP, ultra-thin clienttechnology, etc. Also mixed-content is within the scopeof this work item and may contain a mixture of camera-captured video and images with rendered computer-generated graphics, text, animation, etc.

Although this type of content was considered during thecourse of the HEVC standardization, recent studies inMPEG have led to the conclusion that significant furtherimprovements in coding efficiency can be obtained byexploiting the characteristics of screen content and,thus, a Call for Proposals (CfP) is being issued fordeveloping possible future extensions of the HEVCstandard.

Companies and organizations are invited to submitproposals in response to this call –issued jointly byMPEG with ITU-T VCEG. Responses are expected to besubmitted by early March, and will be evaluated duringthe 108th MPEG meeting. The timeline is as follows:

• 2014/01/17: Final Call for Proposals

• 2014/01/22: Availability of anchors and end of editingperiod for Final CfP

• 2014/02/10: Mandatory registration deadlineOne of the contact persons (see Section 10) mustbe notified, and an invoice for the testing fee will besent after registration. Additional logistic informationwill also be sent to proponents by this date.

• 2014/03/05: Coded test material shall be available atthe test site. By this date, the payment of the testingfee is expected to be finalized.

• 2014/03/17: Submission of all documents andrequested data associated with the proposal.

• 2014/03/27-04/04: Evaluation of proposals atstandardization meeting.

• 2015: Final draft standard expected.

It will be interesting to see the coding efficiency of thesubmitted proposals compared to a pure HEVC or evenAVC approach.

DEC PDP-8 at Computer History Museum during MPEGSocial Event.

Committee Draft for Green Metadata

Green Metadata, formerly known as Green MPEG,shall enable energy-efficient media consumption andreached Committee Draft (CD) status at the 107thMPEG meeting. The representation formats definedwithin Green Metadata help reducing decoder powerconsumption and display power consumption. Clientsmay utilize such information for the adaptive selectionof operating voltage or clock frequencies within theirchipsets. Additional, it may be used to set the brightnessof the backlights for the display to save powerconsumption.

Green Metadata also provides metadata for thesignaling and selection of DASH representations toenable the reduction of power consumption for theirencoding.

The main challenge in terms of adoption of this kindof technology is how to exploit these representationformats to actually achieve energy-efficient mediaconsumption and how much!

What’s new on the DASH frontier?

The text of ISO/IEC 23009-1 2nd edition PDAM1has been approved which may be referred toas MPEG-DASH v3 (once finalized and integratedinto the second edition, possibly with furtheramendments and corrigenda, if applicable). This first

http://mpeg.chiariglione.org/meetings/107

.

ACM Multimedia 2013 Summary



amendment to MPEG-DASH v2 comprises accuratetime synchronization between server and client for liveservices as well as a new profile, i.e., ISOBMFF HighProfile which basically combines the ISOBMFF Liveand ISOBMFF On-demand profiles and adds the Xlinkfeature.

Additionally, a second amendment to MPEG-DASHv2 has been started featuring Spatial RelationshipDescription (SRD) and DASH Client Authentication andContent Access Authorization (DAA).

Other DASH-related aspects include the following:

• The common encryption for ISOBMFF has beenextended with a simple pattern-based encryptionmode, i.e., a new method which should simply contentencryption.

• The CD has been approved for the carriage of timedmetadata metrics of media in ISOBMFF. This allowsfor the signaling of quality metrics within the segmentsenabling QoE-aware DASH clients.

What else? That is, some publicly available MPEGoutput documents… (Dates indicate availability and endof editing period, if applicable, using the following formatYY/MM/DD):

• Report of 3D-AVC Subjective Quality Assessment(14/02/28)

• Working Draft 3 of Video Coding for Browsers(14/01/31)

• Common Test Conditions for Proposals on VCBEnhancements (14/01/17)

• Study Text of ISO/IEC CD 15938-13 CompactDescriptors for Visual Search (14/02/14)

• WD 4.0 of ARAF 2nd Edition (14/02/07)

• Text of ISO/IEC 23001-7 PDAM 1 Simple pattern-based encryption mode (14/01/31)

• Text of ISO/IEC CD 23001-10 Carriage of TimedMetadata Metrics of Media in the ISO Base Media FileFormat (14/01/31)

• Text of ISO/IEC CD 23001-11 Green Metadata(14/01/24)

• Preliminary Draft of ISO/IEC 23008-2:2013/FDAM1HEVC Range Extensions (14/02/28)

• Text of ISO/IEC 23008-2:2013/DAM3 HEVC ScalableExtensions (14/01/31)

• Preliminary Draft of ISO/IEC 23008-2:2013/FDAM2HEVC Multiview Extensions (14/02/28)

• Text of ISO/IEC 23008-2:2013/PDAM4 3DExtensions (14/03/14)

• Text of ISO/IEC CD 23008-12 Image File Format(14/01/17)

• Text of ISO/IEC 23009-1:201x DCOR 1 (14/01/24)

• Text of ISO/IEC 23009-1:201x PDAM 1 High Profileand Availability Time Synchronization (14/01/24)

• WD of ISO/IEC 23009-1 AMD 2 (14/01/31)

• Requirements for an extension of HEVC for coding ofscreen content (14/01/17)

• Joint Call for Proposals for coding of screen content(14/01/22)

• Draft requirements for Higher Dynamic Range (HDR)and Wide Color Gamut (WCG) video coding forBroadcasting, OTT, and Storage Media (14/01/17)

• Working Draft 1 of Internet Video Coding (IVC)(14/01/31)

ACM Multimedia 2013Summary

Conference/WorkshopProgram Highlights

ACM Multimedia 2013 was held at the CCIB (Centre deConventions Internacional de Barcelona) from October21st to October 25th, 2012 in Barcelona. The ArtExhibition has been held for the entire duration ofthe conference at the FAD (Forment de les Arts i delDisseny) in the center of the city while the workshopswere held in the Universitat Pompeu Fabra – Balmesbuilding during the first two days of the conference (Oct.21-Oct 22). It was the first time the conference was heldin Spain and it offered a high-quality program and a fewnotable innovations.

Dr. Nozha Boujemaa from INRIA, France, Dr. AlejandroJaimes from Yahoo! Labs, Spain and Prof. Nicu Sebefrom the University of Trento, Italy were the generalco-chairs of the conference. Dr. Daniel Gatica-Perezfrom IDIAP & EPFL, Switzerland, Dr. David A. Shammafrom Yahoo! Labs, USA, Prof. Marcel Worring from theUniversity of Amsterdam, The Netherlands, and Prof.Roger Zimmermann from the National University ofSingapore, Singapore were the program co-chairs. Theentire organization committee is listed in Appendix A.

The number of participants was 544. The mainconference was attended by 476 participants out ofwhich 425 paid and 51 participants were special cases(sponsors, student volunteers, etc.), and 68 participantsattended workshops only. The tutorials which werefree of charge were registered by 312 in advance.Multimedia art exhibition was open to public from Oct.21 to Oct.28, and visited by more than 2,000 visitors.The total revenue of the conference was $318,151, andthe surplus was $25,430.



http://records.sigmm.ndlab.net/2014/02/acm-multimedia-2013-summary/

http://records.sigmm.ndlab.net/2014/02/acm-multimedia-2013-summary/

.




The venue (CCIB)

Below is the list of the program components ofMultimedia 2013.

• ž Technical Papers: Full and Short papers

• ž Keynote Talks

• ž SIGMM Achievement Award Talk, Ph.D ThesisAward Talk

• ž Panel

• ž Brave New Ideas

• ž Multimedia Grand Challenge Solutions

• ž Technical Demos

• ž Open Source Software Competition

• ž Doctoral Symposium

• ž Art Exhibition and Reception

• ž Tutorials

• ž Workshops

• ž Awards and Banquet

Innovations made forMultimedia 2013:

In attempt to continuously improve ACM Multimedia andensure its vibrant role for the multimedia community, wehave made a number of enhancements for this year’sconference:

• The Technical Program Committee defined twelveTechnical Areas for major focus for this year’sconference, including introducing new TechnicalAreas for Music & Audio and Crowdsourcing toreflect their growing interest and promise. Wehave also changed the names of some traditionalTechnical Areas and provided extensive descriptionof each area to help the authors choosing the mostappropriate Technical Area for their manuscripts.

• We have introduced a new role in the organizationof the conference: the author’s advocate. His explicitrole was to listen to the authors, and to help themif reviews are clearly below average quality. Theauthors could request the mediation of the author’sadvocate after the reviews have been sent to themand they had to clearly justify the reasons whysuch mediation is needed (the reviews or the meta-review were below average quality). The task of theadvocate was to investigate carefully the matter and

to request additional review or reexamination of thedecision of the particular manuscript. This year, theauthor’s advocate was Pablo Cesar from CWI, TheNetherlands.

• We have decided to keep a couple of plenary sessionswhich will bring singular focus to conference activities:keynotes, Multimedia Grand Challenge competition,Best Paper session, Technical Achievement Awardand Best PhD Award sessions. The other technicalsessions are held in parallel to allow pursuit of morespecialized interests at the conference. We havelimited the number of parallel session to no more than3 to minimize the risk of having overlapping interests.

• The use of video spotlights for advertising the works tobe presented. These were meant to offer all attendeesan opportunity to become aware of the content ofeach paper, and thus to be attracted to attend thecorresponding poster or talk.

• Workshops and Tutorials are held on separate daysfrom the main conference in order to reduce conflictwith the regular Technical Program.

• The Multimedia Art Exhibition featured both invitedand selected artists. It was open for the duration of theconference in the satellite venue located in the centerof the city.

• Following the last two years’ precedent, Tutorials aremade free for all participants.

• Recognizing that students are the lifeblood of our nextgeneration of multimedia thinkers, this year’s StudentTravel Grant was greatly expanded. We had a totalamount of $26,000 received from SIGMM ($16,000)and NSF ($10,000) that supported 35 students.

• Finally, we have decided to provide open access forthe community to the proceedings available in theACM Digital Libraries. As such, no USB proceedingswere handed over to the participants encouragingeveryone to get online access.

Technical Program

Following the guidelines of the ACM Multimedia ReviewCommittee, the conference was structured into 12Areas, with a two-tier TPC, a double-blind reviewprocess, and a target acceptance rate of 20% for longpapers and 27.7% for short papers.

Based on the experience from ACM Multimedia 2012and the responses to our “Call for Areas” that we issuedto the community, we selected the following Areas.

1. Art, Entertainment, and Culture

2. Authoring and Collaboration

3. Crowdsourcing

4. Media Transport and Delivery

.




5. Mobile & Multi-device

6. Multimedia Analysis

7. Multimedia HCI

8. Music & Audio

9. Search, Browsing, and Discovery

10.Security and Forensics

11.Social Media & Presence

12.Systems and Middleware

The Technical Program Committee was first created byappointing Area Chairs (ACs). A total of 29 colleaguesagreed to serve in this role. Each Area was representedby two ACs, with exception of two Areas (MultimediaAnalysis and Search, Browsing, and Discovery) whosescope has traditionally attracted the largest proportion ofpapers and so required further coordination. The addedtopic diversity brought an increase in gender diversityto the ACs, which increased from approximately 12%in previous years to 22% for 2013. We also made aconscious effort to bring new talent and excellence intothe community and to better represent emerging trendsin the field. For this we appointed many young andwell recognized ACs who served in this role for thefirst time. For each junior AC, we co-appointed a seniorresearcher as their co-AC to aid in their shepherding.In a second step, the Area Chairs were responsiblefor appointing the TPC members (reviewers) for theircoordinated areas. This was a large effort to growthe TPC base for the conference as well as ensureproper expertise was represented in each area. Wecoupled this with a hard goal of limiting the number ofsubmissions assigned to each TPC member for review.For example, two years ago, the average number ofpapers assigned to a reviewer was 9 with over 38% ofthe approximately 225 TPC members receiving 10 ormore papers to review. With our design, we had a total of398 reviewers receiving an average of 4.13 papers perreviewer. While we were unable to keep a hard ceilinglimitation, only 2.51% of the TPC received 10 or morepapers to review—all TPC members who had agreedto serve in more than one area. The Area Chairs werein charge of assigning all papers for review, and eachsubmission was reviewed double-blind by three TPCmembers.

Reviews and reviewer assignments of papers co-authored by Area Chairs, Program Chairs, and GeneralChairs were handled by Program Chairs who had noconflicts of interest for each specific case.

Another novelty introduced in the reviewing process wasto set the paper submission deadline to a significantlyearlier date than previous years, in order to allocate

more time for reviews, rebuttals, discussions, and finaldecisions. Despite the reduced time given to authors,the response to the Call for Papers was enthusiastic witha total of 235 long papers and 278 short papers goingthrough review.

The authors of long papers were asked to write arebuttal after receiving the reviews. A new elementin the reviewing process was the introduction of theAuthor’s Advocate figure, created to provide authorswith an independent channel to express concernsabout the quality of the reviews for their papers, andto raise a flag about these reviews. All cases werebrought to the attention to the corresponding AreaChair. After evaluating each case reported to him (16reviews out of 761 long paper reviews), the Author’sAdvocate recommended in 5 cases that new reviewswere generated and added to the discussion. Thereviewers had a period for on-line discussion of reviewsand rebuttals, after which the Area Chairs drafted ameta-review for each paper.

Decisions on long and short papers were made at theTPC meeting held at the University of Amsterdam onJune 11, 2013. The meeting was physically attended byone of the General Chairs, three of the Program Chairs,the Author’s Advocate, and 86% of the ACs. Many of theACs who were unable to attend were tele-present onlinefor discussions. On the first half day of the TPC meeting,the Area Chairs worked in breakout sessions to discussthe papers that were weak accepts and weak rejects,with the exception of conflict of interest papers whichwere handled out of band as previously mentioned. Inthe second half of the first day, the ACs met in a plenarysession where they reviewed the clear accepts anddefended the decisions on the borderline papers basedon the papers themselves, reviews, meta-reviews, on-line discussions, and authors’ rebuttal comments.

In many cases, an emergency reviewer was added ifthere was clear intersection with a related submissionarea. If a paper had any conflict of interest during theplenary session with an Area, Program, or GeneralChair, they were excused from the room. On June

.




12, 2013, the Program Chairs finalized the processand conference program in a separate meeting—arranging the sessions by thematic narratives and not bysubmission area to promote cross-area conversationsduring the conference itself.

The review process resulted in an overall acceptancerate of 20.0% for long papers and 27.7% for short papers(the distribution of submissions and the acceptance ratefor each one of the 12 areas is shown in the graphbelow). All accepted long papers were shepherdedby the Area Chairs themselves or by qualified TPCmembers who were in charge of verifying that therevised papers adequately addressed concerns raisedby the reviewers and changes promised by authors intheir rebuttals. This step ensured that all of the acceptedpapers are of the highest quality possible. In addition,four papers with high review scores were nominatedat the TPC meeting as candidates for the Best PaperAward. Each nominated paper had to be successfullychampioned and defended by the ACs from that area.The winner was announced at the Conference Banquet.

ACM Multimedia 2013Program at a Glance

The entire program of ACM Multimedia 2013 is shownbelow.

.




Workshop session

Conference venue

Opening ceremony

Keynote presentation

Poster/Demo session

SIGMM Achievement Award Talk

Keynote Talks

Multimedia FramedDr. Elizabeth F. Churchill (Ebay Research Labs)Wednesday, Oct. 23, 2013

Abstract:

Multimedia is the combination of several mediaforms. Information designers, educationalists andartists are concerned with questions such as: Istext, or audio or video, or a combination of allthree, the best format for the message? Shouldanother modality (e.g., haptics/touch, olfaction) beinvoked instead to make the message more effectiveand/or the experience more engaging? How doesthe setting affect perception/reception? How doesframing affect people’s experience of multimedia?How is the artifact changed through interaction withaudience members? In this presentation, I will talkabout people’s experience of multimedia artifacts likevideos. I will discuss the ways in which framingaffects how we experience multimedia. Framing canbe intentional–scripted creations produced with clearintent by technologists, designers, media producers,media artists, film-makers, archivists, documentariansand architects. Framing can also be unintentional.Everyday acts of interest and consumption turn us,the viewers, into co-producers of the experiencesof the multimedia artifacts we have viewed. Wedownload, annotate, comment and share multimediaartifacts online. Our actions are reflected in view

.




counts, displayed comments and content ranking. Ouractions therefore change how multimedia artifacts areinterpreted and understood by others.

Drawing on examples from the history of film and ofperformance art, from current social media research andfrom research conducted with collaborators over thepast 16 years, I will illustrate how content understandingis modulated by context, by the “framing” of the content. Iwill consider three areas of research that are addressingthe issue of framing, and that have implications for ourunderstanding of ‘multimedia’ consumption, now and inthe future: (1) The psychology and psychophysiologyof multimedia as multimodal experience; (2) Emergingpractices with contemporary social media capture andsharing from personal devices; and (3) Innovations insocial media and audience analytics focused on moredeeply understanding media consumption.

I will conclude with some technical excitements, design/development challenges and experiential possibilitiesthat lie ahead.

Dr. Elizabeth Churchill is Director of Human ComputerInteraction at eBay Research Labs (ERL) in San Jose,California. Formerly a Principal Research Scientist atYahoo! Research, she founded, staffed and managedthe Internet Experiences Group. Until September of2006, she worked at the Palo Alto Research Center(PARC), California, in the Computing Science Lab(CSL). Prior to that she formed and led the SocialComputing Group at FX Palo Laboratory, Fuji Xerox’sresearch lab in Palo Alto. Originally a psychologist bytraining, throughout her career Elizabeth has focusedon understanding people’s social and collaborativeinteractions in their everyday digital and physicalcontexts. With over 100 peer-reviewed publications and5 edited books, topics she has written about includeimplicit learning, human-agent systems, mixed initiativedialogue systems, social aspects of information seeking,digital archive and memory, and the development ofemplaced media spaces. She has been a regularcolumnist for ACM interactions since 2008. Elizabethhas a BSc in Experimental Psychology, an MSc inKnowledge Based Systems, both from the Universityof Sussex, and a PhD in Cognitive Science from theUniversity of Cambridge. In 2010, she was recognisedas a Distinguished Scientist by the Association forComputing Machinery (ACM). Elizabeth is the currentExecutive Vice President of ACM SigCHI (HumanComputer Interaction Special Interest Group). She is aDistinguished Visiting Scholar at Stanford University’sMedia X, the industry affiliate program to Stanford’s H-STAR Institute.

The Space between the ImagesLeonidas J. Guibas (Stanford University)Thursday, Oct. 24, 2013

Abstract:

Multimedia content has become a ubiquitous presenceon all our computing devices, spanning the gamutfrom live content captured by device sensors such assmartphone cameras to immense databases of images,audio and video stored in the cloud. As we try tomaximize the utility and value of all these petabytesof content, we often do so by analyzing each piece ofdata individually and foregoing a deeper analysis of therelationships between the media. Yet with more andmore data, there will be more and more connectionsand correlations, because the data captured comes fromthe same or similar objects, or because of particularrepetitions, symmetries or other relations and self-relations that the data sources satisfy. This is particularlytrue for media of a geometric character, such as GPStraces, images, videos, 3D scans, 3D models, etc.

In this talk we focus on the “space between theimages”, that is on expressing the relationships betweendifferent multimedia data items. We aim to make suchrelationships explicit, tangible, first class objects thatthemselves can be analyzed, stored, and queried —irrespective of the media they originate from. Wediscuss mathematical and algorithmic issues on howto represent and compute relationships or mappingsbetween media data sets at multiple levels of detail.We also show how to analyze and leverage networksof maps and relationships, small and large, betweeninter-related data. The network can act as a regularizer,allowing us to to benefit from the “wisdom of thecollection” in performing operations on individual datasets or in map inference between them.

We will illustrate these ideas using examples from therealm of 2D images and 3D scans/shapes — but thesenotions are more generally applicable to the analysisof videos, graphs, acoustic data, biological data suchas microarrays, homeworks in MOOCs, etc. This is anoverview of joint work with multiple collaborators, as willbe discussed in the talk.

Prof. Leonidas Guibas obtained his Ph.D. fromStanford under the supervision of Donald Knuth. Hismain subsequent employers were Xerox PARC, DEC/SRC, MIT, and Stanford. He is currently the PaulPigott Professor of Computer Science (and by courtesy,Electrical Engineering) at Stanford University. He headsthe Geometric Computation group and is part ofthe Graphics Laboratory, the AI Laboratory, the Bio-X Program, and the Institute for Computational andMathematical Engineering. Professor Guibas’ interestsspan geometric data analysis, computational geometry,geometric modeling, computer graphics, computervision, robotics, ad hoc communication and sensornetworks, and discrete algorithms. Some well-knownpast accomplishments include the analysis of double

.




hashing, red-black trees, the quad-edge data structure,Voronoi-Delaunay algorithms, the Earth Mover’sdistance, Kinetic Data Structures (KDS), Metropolis lighttransport, and the Heat-Kernel Signature. ProfessorGuibas is an ACM Fellow, an IEEE Fellow and winnerof the ACM Allen Newell award.

SIGMM Talks

SIGMM Achievement Award TalkDick Bulterman, CWI, The NetherlandsFriday, Oct. 25, 2013

The 2013 winner of SIGMM award for OutstandingTechnical Contributions to Multimedia Computing,Communications and Applications is Prof. Dr. DickBulterman. The ACM SIGMM Technical Achievementaward is given in recognition of outstandingcontributions over a researcher’s career. Prof. DickBulterman has been selected for his outstandingtechnical contributions in multimedia authoring, mediaannotation, and social sharing from research throughstandardization to entrepreneurship, and in particular forpromoting international Web standards for multimediaauthoring and presentation (SMIL) in the W3CSynchronized Multimedia Working Group as well ashis dedicated involvement in the SIGMM researchcommunity for many years.

Dr. Dick Bulterman has been a long time intellectualleader in the area of temporal modeling and supportfor complex multimedia system. His research has ledto the development of several widely used multimediaauthoring systems and players. He developed theAmsterdam Hypermedia Model, the CMIF documentstructure, the CMIFed authoring environment, theGRiNS editor and player, and a host of multimediademonstrator applications. In 1999, he started the CWIspinoff company called Oratrix Development BV, andhe worked as CEO to widely deliver this software. Heis currently a Research Group Head of the Distributedand Interactive Systems at Centrum Wiskunde &Informatica (CWI) in Amsterdam, The Netherlands.He is also a Full Professor of Computer Science atVrije Universiteit, Amsterdam. His research interestsare multimedia authoring and document processing.Dick has a strong international reputation for thedevelopment of the domain-specific temporal languagefor multimedia (SMIL). Much of this software hasbeen incorporated into the widely used Ambulant OpenSource SMIL Player, which has served to encouragedevelopment and use of time-based multimedia content.His conference publications and book on SMIL havehelped to promote SMIL and its acceptance as a W3Cstandard. Dick’s recent work on social sharing of videowill likely prove influential in upcoming Interactive TVproducts. This work has already been recognized in the

academic community, earning the ACM SIGMM bestpaper award at ACM MM 2008 and also at the EUROITVconference.

SIGMM Ph.D Thesis Award TalkXirong Li, Remin University, ChinaFriday, Oct. 25, 2013

The SIGMM Ph.D. Thesis Award Committeerecommended this year’s award for the outstandingPh.D. thesis in multimedia computing, communicationsand applications to Dr. Xirong Li.

The committee considered Dr. Li’s dissertation titled“Content-based visual search learned from socialmedia” as worthy of the award as it substantiallyextends the boundaries for developing content-basedmultimedia indexing and retrieval solutions. In particular,it provides fresh new insights into the possibilities forrealizing image retrieval solutions in the presence of vastinformation that can be drawn from the social media.

The committee considered the main innovation of Dr.Li’s work to be in the development of the theoryand algorithms providing answers to the followingchallenging research questions:(a) what determines the relevance of a social tag withrespect to an image,(b) how to fuse tag relevance estimators,(c) which social images are the informative negativeexamples for concept learning,(d) how to exploit socially tagged images for visualsearch and(e) how to personalize automatic image tagging withrespect to a user’s preferences.

The significance of the developed theory and algorithmslies in their power to enable effective and efficientdeployment of the information collected from the socialmedia to enhance the datasets that can be used to learnautomatic image indexing mechanisms (visual conceptdetection) and to make this learning more personalizedfor the user.

Dr. Xirong Li received the B.Sc. and M.Sc. degreesfrom the Tsinghua University, China, in 2005 and2007, respectively, and the Ph.D. degree from theUniversity of Amsterdam, The Netherlands, in 2012, allin computer science. The title of his thesis is “Content-based visual search learned from social media”. Heis currently an Assistant Professor in the Key Labof Data Engineering and Knowledge Engineering,Renmin University of China. His research interest isimage search and multimedia content analysis. Dr. Lireceived the IEEE Transactions on Multimedia PrizePaper Award 2012, Best Paper Nominee of the ACMInternational Conference on Multimedia Retrieval 2012,Chinese Government Award for Outstanding Self-

.




Financed Students Abroad 2011, and the Best PaperAward of the ACM International Conference on Imageand Video Retrieval 2010. He served as publicity co-chair for ICMR 2013.

PanelCross-Media Analysis and MiningWednesday, Oct 23, 2013

Panelists:Mark Zhang, Alberto del Bimbo, SelcukCandan, Alexander Hauptmann, Ramesh Jain, AlexisJoly, Yueting Zhuang

Motivation

Today there are lots of heterogeneous andhomogeneous media data from multiple sources,such as news media websites, microblog, mobilephone, social networking websites, and photo/videosharing websites. Integrated together these media datarepresent different aspects of the real-world and helpdocument the evolution of the world. Consequently, itis impossible to correctly conceive and to appropriatelyunderstand the world without exploiting the dataavailable on these different sources of rich multimediacontent simultaneously and synergistically.

Cross-media analysis and mining is a research area inthe general field of multimedia content analysis whichfocuses on the exploitation of the data with differentmodalities from multiple sources simultaneously andsynergistically to discover knowledge and understandthe world. Specifically, we emphasize two essentialelements in the study of cross-media analysis that helpdifferentiate cross-media analysis from the rest of theresearch in multimedia content analysis or machinelearning.

The first is the simultaneous co-existence of datafrom two or more different data sources. This elementindicates the concept of “cross”, e.g., cross-modality,cross-source, and cross cyberspace to reality. Cross-modality means that heterogeneous features areobtained from the data in different modalities; cross-source means that the data may be obtained acrossmultiple sources (domains or collections); cross-spacemeans that the virtual world (i.e., cyberspace) and thereal world (i.e., reality) complement each other.

The second is the leverage of different types ofdata across multiple sources for strengthening theknowledge discovery, for example, discovering the(latent) correlation or synergy between the data withdifferent modalities across multiple sources, transferringthe knowledge learned from one domain (e.g., amodality or a space) to generate knowledge in anotherrelated domain, and generating a summary with the datafrom multiple sources.

There two essential elements help promote cross-mediaanalysis and mining as a new, emerging, and importantresearch area in today’s multimedia research. Withthe emphasis on knowledge discovery, cross-mediaanalysis is different from the traditional research areassuch as cross-lingual translation. On the other hand,with the general scenarios of the leverage of differenttypes of data across multiple sources for strengtheningthe knowledge discovery, cross-media analysis andmining addresses a broader series of problems thanthe traditional research areas such as transfer learning.Overall, cross-media analysis and mining is beneficialfor many applications in data mining, causal inference,machine learning, multimedia, and public security.

Like other emerging hot topics in multimedia research,cross-media analysis and mining also has a numberof fundamental and controversial issues that mustbe addressed in order to have a full and completeunderstanding of the research in this topic. These issuesinclude but are not limited to whether or not thereexists a unified representation or modeling for the samesemantic concept from different media, and if there iswhat such unified representation or modeling is; whetheror not there exists any “law” that governs the topicevolution and development over the time in differentmedia and if there is what such “law” is and how it isformulated; whether or not there exists a mapping for aconceptual or semantic activity between the cyberspaceand the real-world, and if there is what such a mappingis and how it is developed and formulated.

Brave New Idea Program

Brave New Ideas addressed long term researchchallenges, pointed to new research directions, orprovided new insights or brave perspectives that pavethe way to innovation. The selection process wasdifferent from the regular papers. First, submissionof a 2 page abstract was requested. Then, the firstselection was performed and a full paper was requiredfor the selected abstracts and reviewed and chosen. Wereceived 38 submissions for the first stage and 14 wereinvited to submit the full paper for the second reviewingstage. Finally, there were accepted 6 papers, whichformed two sessions of oral presentations.

Multimedia Grand Challenge Solutions

We had received six challenges as shown below for theMultimedia Grand Challenge Solutions Program.

1. NHK – Where is beauty? Grand Challenge

2. Technicolor – Rich Multimedia Retrieval from InputVideos Grand Challenge

3. Yahoo! – Large-scale Flickr-tag Image ClassificationGrand Challenge

.




4. Huawei/3DLife – 3D human reconstruction and actionrecognition Grand Challenge

5. MediaMixer/VideoLectures.NET – TemporalSegmentation and Annotation Grand Challenge

6. Microsoft: MSR – Bing Image Retrieval GrandChallenge

We received 34 proposals for this program, and 14 ofthem were accepted for the presentation. In order topromote submissions, all presentations in this programwere awarded as Multimedia Grand Challenge Finalists.The best prize and two second best prizes werechosen and awarded. Requested by Technicolor, theGrand Challenge Multimodal Prize was also chosen andawarded.

Technical Demonstrations

We have received 80 excellent technical demonstrationsproposals. The number of submissions was in line tothe demonstrations received in the previous year. Threereviewers were assigned to each demo proposal, andfinally 40 proposals were chosen. The best demo prizewas awarded.

Open Source Software CompetitionThis year was the 6

th edition of the Open software

competition being part of the ACM Multimedia program.The goal of this competition is to praise the invaluablecontribution of researchers and software developerswho advance the field by providing the community withimplementations of codecs, middleware, frameworks,toolkits, libraries, applications, and other multimediasoftware. This year we have received 16 submissionsand after assigning three reviewers to each of them wehave selected 11 for the competition. The best opensource software was awarded.

Doctoral Symposium

Doctoral Symposium was meant as a forum formentoring graduate students. It was held in theafternoon of Oct. 25 both in the oral and poster formats.We have received 19 proposals for doctoral symposium.We accepted 13 presentations (6 oral + poster and 7additional posters). Additionally, there was organized aDoctoral Symposium lunch in which the students had theopportunity to talk to their assigned mentors. Finally, thebest doctoral symposium paper was awarded.

Multimedia Art Exhibition and Reception

ACM Multimedia provided a rich Multimedia ArtExhibition to stimulate artists and researchers aliketo meet and discover the frontiers of multimediaartistic communication. The Art Exhibition has attractedsignificant work from a variety of digital artistscollaborating with research institutions. We have

endeavored to select exhibits that achieved aninteresting balance between technology and artisticintent. The techniques underpinning these artworks arerelevant to several technical tracks of the conference,in particular those dealing with human-centered andinteractive media.

We had a satellite venue, FAD (Forment de les Arts i delDisseny), for the art exhibition located in the center ofthe city. The venue had a very good public access. Theexhibition was open from Oct. 21 to Oct. 28 and visitedby more than 2,000 visitors. The reception event washeld with the artists on Oct. 23. We had selected 10 artworks for the exhibition:

1. Emotion Forecast, Maurice Benayoun (CityUniversity of Hong Kong)

2. Critical, Anabela Costa (France)

3. Smile-Wall, Shen-Chi Chen, He-Lin Luo, Kuan-Wen Chen, Yu-Shan Lin, Hsiao-Lun Wang, Che-Yao Chan, Kai-Chih Huang, Yi-Ping Hung (NationalTaiwan University)

4. SOMA, Guillaume Faure (France)

5. A Feast of Shadow Puppetry, Zhenzhen Hu, Min Lin,Si Liu, Jiangguo Jiang, Meng Wang, Richang Hong,Shuicheng Yan, Hefei University of Technology andNUS

6. Tele Echo Tube, Hill Hiroki Kobayashi, Kaoru Saito,Akio Fujiwara (University of Tokyo)

7. 3D-Stroboscopy, Sujin Lee (Sogang University,South Korea)

8. The Qi of Calligraphy, He-Lin Luo, Yi-Ping Hung(Taiwan National University), I-Chun Chen (TainanNational University of the Arts)

9. Gestural Pen Animation, Sheng-Ying Pao and KentLarson (MIT Media Lab, USA)

10.MixPerceptions, Jose San Pedro (TelefonicaResearch, Spain), Aurelio San Pedro (EscolaMassana, Barcelona), Juan Pablo Carrascal (UPF,Barcelona), Matylda Szmukier (Telefonica Research,Spain)

.




Attending the Art Exhibition

San Pedro’s Mix Perceptions

Tutorials

We received in 14 tutorial proposals and we haveselected 8 tutorials for the main program. All tutorialswere half day and were held on Oct. 21 and 22 in parallelwith the workshops in the in the Universitat PompeuFabra – Balmes building. Tutorials were made free forall participants and we received 312 pre-registrations.

Gerald Friedland(ICSI)

Tutorial 1 Foundations andApplications ofSemantic Technologiesfor Multimedia Content

Ansgar Scherp (Uni Mannheim,Germany)

Tutorial 2 Towards Next-Generation MultimediaRecommendationSystems

Jialie Shen, (SMU Singapore)

Shuicheng Yan (NUS)

Xian-Sheng Hua (Microsoft)

Tutorial 3 Crowdsourcing forMultimedia Research

Mohammad Soleymani (Imperial College London)

Martha Larson (TU Delft)

Tutorial 4 Massive-ScaleMultimedia SemanticModeling

John R. Smith (IBM Research )

Liangliang Cao (IBM Research)

Tutorial 5 Social Interactionsover Geographic-AwareMultimedia Systems

Roger Zimmerman (NUS)

Yi Yu (NUS)

Tutorial 6 Multimedia InformationRetrieval: Music andAudio

Markus Schedl (JKU Linz)

Emilia Gomez (UPF)

Masataka Goto (AIST)

Tutorial 7 Blending the Physicaland the Virtual inMusical Technology:From interface designto multimodal signalprocessing

George Tzanetakis (U Victoria, Canada)

Sidney Fels (UBC)

Michael Lyons (Ritsumeikan U, JP)

Tutorial 8 Privacy Concerns ofSharing Multimedia inSocial Networks

Gerald Friedland (ICSI)

Workshops

Workshops have always been an important part ofthe conference. Below is the list of workshops held inconjunction with ACM Multimedia 2013. We had 9 fullday workshops and 4 half day workshops, which wereheld on Oct. 21-22 in parallel with the tutorials. Wefollowed the rule from last year and two complementaryworkshop only registrations were provided for invitedtalks of each workshop to encourage participation ofnotable speakers.

Full Day Workshops (8)

1. 2nd International Workshop on Socially-AwareMultimedia (SAM 2013)Organizers: Pablo Cesar (CWI, NL)Matthew Cooper (FXPAL)David A. Shamma (Yahoo!)Doug Williams (BT)

1. 4th ACM/IEEE ARTEMIS 2013 InternationalWorkshop on Analysis and Retrieval of TrackedEvents and Motion in Imagery StreamsOrganizers: Marco Bertini (University of Florence,Italy)Anastasios Doulamis (TU Crete, Greece)Nikolaos Doulamis (Cyprus University of Technology,Cyprus)

.




Jordi Gonzàlez (Universitat Autònoma de Barcelona,Spain)Thomas Moeslund (University of Aalborg, Denmark)

1. 5th International Workshop on Multimedia forCooking and Eating Activities (CEA2013)Organizer: Kiyoharu Aizawa(Univ. of Tokyo, JP)

1. 4th International Workshop on Human BehaviorUnderstanding (HBU 2013)Organizers: Albert Ali Salah, Bo#aziçi Univ., TurkeyHayley Hung, Delft Univ. of Technology, TheNetherlandsOya Aran, Idiap Research Intitute, SwitzerlandHatice Gunes, Queen Mary Univ. of London (QMUL),UK

1. International ACM Workshop on Crowdsourcing forMultimedia 2013 (CrowdMM 2013)Organizers: Wei-Ta Chu (National Chung ChengUniversity, TW)Martha Larson (Delft University of Technology, NL)Kuan-Ta Chen (Academia Sinica, TW)

1. First ACM MM Workshop on Multimedia Indexingand Information Retrieval for Healthcare (ACM MMMIIRH)Organizers: Jenny Benois-Pineau, University ofBordeaux 1, FranceAlexia Briasouli, CERTH -ITIAlex Hauptman, Carnegie-Mellon University, USA

1. Workshop on Personal Data Meets DistributedMultimediaOrganizers: Vivek Singh, MIT, USATat-Seng Chua, NUSRamesh Jain, University of California, Irvine, USAAlex (Sandy) Pentland, MIT, USA

1. Workshop on Immersive Media ExperiencesOrganizers: Teresa Chambel, University of Lisbon,PortugalV. Michael Bove, MIT Media Lab, USASharon Strover, University of Texas at Austin, USAAPaula Viana, Polytechnic of Porto and INESC TEC,PortugalGraham Thomas, BBC, UK

1. Workshop on Event-based Media Integration andProcessingOrganizers: Fausto Giunchiglia, University of Trento,ItalySang “Peter” Chin, Johns Hopkins University, USGiulia Boato, University of Trento, ItalyBogdan Ionescu, University Politehnica of Bucharest,RomaniaYiannis Kompatsiaris, Centre for Research andTechnology Hellas, Greece

Half Day Workshops (4)

1. ACM Multimedia Workshop on Geotagging and ItsApplicationsOrganizers: Liangliang Cao, IBM T. J. WatsonResearch Center, USAGerald Friedland, International Computer ScienceInstitute, USA,Pascal Kelm, Technische Universitaet of Berlin,Germany

1. Data-driven challenge-based workshop ACM MM2013(AVEC 2013)Organizers: Björn Schuller, TUM, GermanyMichel Valstar, University of Nottingham, UKRoddy Cowie, Queen’s University Belfast, UKMaja Pantic, Imperial College London, UKJarek Krajewski, University of Wuppertal, Germany

1. 2nd ACM International Workshop on MultimediaAnalysis for Ecological Data (MAED 2013)Organizers: Concetto Spampinato, University ofCatania, ItalyVasileios Mezaris, CERTH, GreeceJacco van Ossenbruggen, CWI, The Netherlands

1. 3rd International Workshop on Interactive Multimediaon Mobile and Portable Devices(IMMPD’13)Organizers: Jiebo Luo, University of Rochester, USACaifeng Shan, Philips Research, The NetherlandsLing Shao, The University of Sheffield, UKMinoru Etoh, NTT DOCOMO, Japan

Awards

Awards were given in almost all the programs except forshort papers during the banquet that was organized atthe conference venue. The following awards have beengiven:

Best Paper Award

Luoqi Liu, Hui Xu, Junliang Xing, Si Liu, Xi Zhou andShuicheng Yan, National University of Singapore (NUS),“Wow! You Are So Beautiful Today!”

Best Student Paper Award

Hanwang Zhang, Zheng-Jun Zha, Yang Yang,Shuicheng Yan, Yue Gao and Tat-Seng Chua, NationalUniversity of Singapore (NUS), “Attributes-augmentedSemantic Hierarchy for Image Retrieval”

Grand Challenge 1st Place Award [Sponsored byTechnicolor]

Brendan Jou, Hongzhi Li, Joseph G. Ellis, DanielMorozoff-Abegauz and Shih-Fu Chang, Digital Video& Multimedia (DVMM) Lab, Columbia University,

.




“Structured Exploration of Who, What, When, andWhere in Heterogenous Multimedia News Sources”

Grand Challenge 2nd Place Award [Sponsored byTechnicolor]

Subhabrata Bhattacharya, Behnaz Nojavanasghari,Tao Chen, Dong Liu, Shih-Fu Chang, Mubarak Shah,University of Central Florida and Columbia University,“Towards a Comprehensive Computational Model forAesthetic Assessment of Videos”

Grand Challenge 3rd Place Award [Sponsored byTechnicolor]

Shannon Chen, Penye Xia, and Klara Nahrstedt, UIUC,“Activity-Aware Adaptive Compression: A Morphing-Based Frame Synthesis Application in 3DTI”

Program chairs during the banquet

Award ceremony

Banquet venue

Social program

Grand Challenge Multimodal Award [Sponsored byTechnicolor]

Chun-Che Wu, Kuan-Yu Chu, Yin-Hsi Kuo, Yan-Ying Chen, Wen-Yu Lee, Winston H. Hsu, NationalTaiwan University, Taiwan, “Search-Based RelevanceAssociation with Auxiliary Contextual Cues”

Best Demo Award

Duong-Trung-Dung Nguyen, Mukesh Saini; Vu-ThanhNguyen, Wei Tsang Ooi, National University ofSingapore (NUS), “Jiku director: An online mobile videomashup system”

Best Doctoral Symposium Paper

Jules Francoise, Institut de Recherche etCoordination Acoustique/Musique (IRCAM), “Gesture-Sound Mapping by demonstration in Interactive MusicSystems”

Best Open Source Software Award

Dmitry Bogdanov, Nicolas Wack, Emilia Gómez,Sankalp Gulati, Perfecto Herrera, Oscar Mayor, GerardRoma, Justin Salamon, Jose Zapata Xavier Serra(UPF), “ESSENTIA: An Audio Analysis Library for MusicInformation Retrieval”

Prize amounts:

Best Paper Award 500 euro

Best Student PaperAward

250 euro

Grand Challenge 1stPrize

750 euro

Grand Challenge 2ndPrize

500 euro

Grand Challenge 3ndPrize

200 euro

Grand ChallengeMultimodal Prize

500 euro

.




Best Technical DemoAward

250 euro

Best Doctoral SymposiumPaper

250 euro

Best Open SourceSoftware Award

250 euro

Student Travel Grant (35students)

$26,000 ($10,000 NSF,$16,000 SIGMM)

Sponsors:We had an incredible support from industriesand funding organizations (38.5k euro). All the sponsorsand the institutional supporters are listed in Appendix B.The sponsoring amount for each individual sponsor isas follows:

Sponsor Amount

FXPAL 5000 euro

Google 5000 euro

Huawei 5000 euro

Yahoo!Labs 5000 euro

Technicolor 4000 euro

Media Mixer 3500 euro

INRIA 3000 euro

Facebook 2000 euro

IBM 2000 euro

Telefonica 2000 euro

Microsoft 2000 euro

Total 38500 euro

The benefits for the sponsors were honoraryregistrations and publicity, that is, the company logowas published on the website of the conference, in theProceedings, and the Booklet.

On top of these amounts we have received 16k$ fromSIGMM and 10K from NSF for student travel grants.

Geographical distribution ofthe participants

We had 544 participants at the main conference andworkshops. The main conference was attended by 476participants out of which 425 paid and 51 participantswere special cases (sponsors, student volunteers, etc.),and 68 participants attended only the workshops. Thetutorials which were free of charge were registered by312 in advance.

Country-wise distribution is shown below. As shown inthe list, the geographical distribution was wide meaning

that we managed to attract participants from a largenumber of countries.

Total # ofparticipants

544

USA 75 Switzerland20

Singapore 48 Germany 20

China 45 Portugal 20

Japan 40 Taiwan 18

UK 35 Korea 15

Italy 29 Australia 15

France 28 Greece 14

Netherlands26 Turkey 14

Spain 26 25 othercountries

56

Survey

In order to gather opinions from the participants at ACMMultimedia 2013 we have performed a post-conferencesurvey and the results are summarized in Appendix C.Here we summarize the 10 most important issues thatwere compiled after analyzing the answers received.The effort to gather all this information is the first ofits kind at ACM Multimedia and we hope this traditionwill be continued in the future. The results of thesurvey represent in our opinion a very good source ofinformation for the future organizers.

1. Poster space too small

2. Many people still want USB proceedings!!

3. Oral topics in the same time slot overlapped toomuch. Need to diversify.

4. Need to attract more multimedia niche topics. Shouldnot become a second rate CV conference

5. First day location hard to find. Workshop/tutorialbetter to be co-located with main conference

6. Senior members of MM community should participatein paper sessions more

7. Need to update web site program content and makeit available earlier

8. Consider offering short spotlight talks for posterpapers

9. Keep 15 mins for oral, but have them presented againin poster session for more discussion

.




10.SIGMM business meeting too long. Not enough timefor QA.

Conclusion

ACM Multimedia 2013 was a great success with a greatnumber of submissions, an excellent technical program,attractive program components, and stimulating events.As a result, we welcomed a large number of participants,in line with our initial expectation. There were a fewproblems see above but this is only natural.

We greatly acknowledge those who have contributedto the success of ACM Multimedia 2013. We thankthe organizers of ACM Multimedia 2012 for their usefulsuggestions and comments which helped us to improvethe organization the 2013 edition. We also thank themfor giving us the template for the conference booklet. Wethank the many paper authors and proposal contributorsfor the various technical and program components.We thank the large number of volunteers, includingthe Organizing Committee members and TechnicalProgram Committee members who worked very hard tocreate this year’s outstanding conference. Every aspectof the conference was also aided by local committeemembers and by the hard work of Grupo Pacifico, towhom we are very grateful. We thank also ACM staff andSheridan Printing Company for their constant support.This success was clearly due to the integration of theirefforts.

Appendix A: ACM MULTIMEDIA2013 CONFERENCEORGANIZATION

General Co-Chairs

Alejandro (Alex) Jaimes (Yahoo Labs, Spain)Nicu Sebe (University of Trento, Italy)Nozha Boujemaa (INRIA, France)

Technical Program Co-Chairs

Daniel Gatica-Perez (IDIAP & EPFL, Switzerland)David A. Shamma (Yahoo Labs, USA)Marcel Worring (University of Amsterdam, TheNetherlands)Roger Zimmermann (National University of Singapore,Singapore)

Author’s Advocate

Pablo Cesar (CWI, The Netherlands)

Multimedia Grand Challenge Co-Chairs

Yiannis Kompatsiaris (CERTH, Greece)Neil O’Hare (Yahoo Labs, Spain)

Interactive Arts Co-Chairs

Antonio Camurri (University of Genova, Italy)Marc Cavazza (Teesside University, UK)

Local Arrangement Chair

Mari-Carmen Marcos (Pompeu Fabra University, Spain)

Sponsorship Chairs

Ricardo Baeza-Yates (Yahoo Labs, Spain)Bernard Merialdo (Eurecom, France)

Panel Co-Chairs

Yong Rui (Microsoft, China)Winston Hsu (National Tawain University, Taiwan)Michael Lew (University of Leiden, The Netherlands)

Video Program Chairs

Alexis Joly (INRIA, France)Giovanni Maria Farinella (University of Catania, Italy)Julien Champ (INRIA/LIRMM, France)

Brave New Ideas Co-Chairs

Jiebo Luo (University of Rochester, USA)Shuicheng Yan (National University of Singapore,Singapore)

Doctorial Symposium Chairs

Hayley Hung (Technical University of Delft, TheNetherlands)Marco Cristani (University of Verona, Italy)

Open Source Competition Chairs

Ioannis (Yiannis) Patras (Queen Mary University, UK)Andrea Vedaldi (Oxford University, UK)

Tutorial Co-Chairs

Kiyoharu Aizawa (University of Tokyo, Japan)Lexing Xie (Australian National University, Australia)

Workshop Co-Chairs

Maja Pantic (Imperial College, UK )Vladimir Pavlovic (Rutgers University, USA)

Student Travel Grants Co-Chairs

Ramanathan Subramanian (ADSC, Singapore)Jasper Uijlings (University of Trento, Italy)

Publicity Co-Chairs

Marco Bertini (University of Florence, Italy)Ichiro Ide (Nagoya University, Japan)

.

Most cited papers before the era of ICMR



Technical Demo Co-Chairs

Yi Yang (Carnegie Mellon University, USA)Xavier Anguera (Telefonica Research, Spain)

Proceedings Co-Chairs

Bogdan Ionescu (University Politehnica of Bucharest,Romania)Qi Tian (University of Texas San Antonio, USA)

Web Chair

Michele Trevisol (Web Research Group UPF & YahooLabs, Spain)

Appendix B. ACM MM 2012 Sponsors &Supporters

Most cited papersbefore the era of ICMRIn the early years of 2000, the field of multimediaretrieval was composed of special sessions atconferences and small workshops. There were nomultimedia retrieval conferences. One of the leadingworkshops (B. Kerherve, V. Oria and S. Satoh) wasthe ACM SIGMM Workshop on Multimedia InformationRetrieval (MIR) which was held with the ACM MMconference.

To have a central meeting for the scientific community,the International Conference on Image and VideoRetrieval (CIVR) was founded in 2002 (J. Eakins,P. Enser, M. Graham, M.S. Lew, P. Lewis and A.Smeaton). Both meetings evolved over the next decade. CIVR and MIR became ACM SIGMM sponsoredconferences and established reputations for high qualitywork.

In 2010, the steering committees of both CIVR and MIRvoted to combine the two conferences toward unifyingthe communities and establishing the ACM flagshipmeeting for multimedia retrieval, the ACM International

Conference on Multimedia Retrieval (ICMR). In2013, ICMR was ranked by the Chinese ComputingFederation as the #1 meeting in multimedia retrieval andthe #4 meeting in the wide domain of Multimedia andGraphics.

For archival reasons, this is a summary of whichpapers had the most citations from ACM CIVR and ACMMIR (2008-2010), based on Google Scholar data in theperiod from February 17-18, 2014.

Google Scholar citations were used because they havewide coverage (ACM, IEEE, Springer, Elsevier,etc.), are publicly accessible and because they arebeing increasingly accepted by researchers for bothpaper citations estimates and computing the h-index.

The information below is given in the format ofRank | Citations | Article-Information

CIVR 2008

1. 173 - World-scale mining of objects and events fromcommunity photo collectionsTill Quack, Bastian Leibe, Luc Van Goolhttp://dl.acm.org/citation.cfm?id=1386363

2. 81 - Analyzing Flickr groupsRadu Andrei Negoescu, Daniel Gatica-Perezhttp://dl.acm.org/citation.cfm?id=1386406

3. 70 - A comparison of color features for visual conceptclassificationKoen E.A. van de Sande, Theo Gevers, Cees G.M.Snoekhttp://dl.acm.org/citation.cfm?id=1386376

4. 68 - Language modeling for bag-of-visual wordsimage categorizationPierre Tirilly, Vincent Claveau, Patrick Groshttp://dl.acm.org/citation.cfm?id=1386388

5. 46 - Multiple feature fusion by subspace learningYun Fu, Liangliang Cao, Guodong Guo, Thomas S.Huanghttp://dl.acm.org/citation.cfm?id=1386373

CIVR 2009

1. 379 - NUS-WIDE: a real-world web image databasefrom National University of SingaporeTat-Seng Chua, Jinhui Tang, Richang Hong, HaojieLi, Zhiping Luo, Yantao Zhenghttp://dl.acm.org/citation.cfm?id=1646452

2. 124 - Evaluation of GIST descriptors for web-scaleimage searchMatthijs Douze, Hervé Jégou, HarsimratSandhawalia, Laurent Amsaleg, Cordelia Schmidhttp://dl.acm.org/citation.cfm?id=1646421

http://records.sigmm.ndlab.net/2014/03/most-cited-papers-before-the-era-of-icmr/

http://records.sigmm.ndlab.net/2014/03/most-cited-papers-before-the-era-of-icmr/

http://dl.acm.org/citation.cfm?id=1386363







.

ESSENTIA: an open source library for audio analysis



3. 81 - Real-time bag of words, approximatelyJ. R. R. Uijlings, A. W. M. Smeulders, R. J. H. Schahttp://dl.acm.org/citation.cfm?id=1646405

4. 57 - Dense sampling and fast encoding for 3D modelretrieval using bag-of-visual featuresHideki Nakayama, Tatsuya Harada, Yasuo Kuniyoshihttp://dl.acm.org/citation.cfm?id=1646419

5. 46 - Multilayer pLSA for multimodal image retrievalRainer Lienhart, Stefan Romberg, Eva Hörsterhttp://dl.acm.org/citation.cfm?id=1646408

CIVR 2010

1. 43 - Signature Quadratic Form DistanceChristian Beecks, Merih Seran Uysal, Thomas Seidlhttp://dl.acm.org/citation.cfm?id=1816105

2. 41 - Feature detector and descriptor evaluation inhuman action recognitionLing Shao, Riccardo Mattivihttp://dl.acm.org/citation.cfm?id=1816111

3. 38 - Unsupervised multi-feature tag relevancelearning for social image retrievalXirong Li, Cees G. M. Snoek, Marcel Worringhttp://dl.acm.org/citation.cfm?id=1816044

4. 29 - Co-reranking by mutual reinforcement for imagesearchTing Yao, Tao Mei, Chong-Wah Ngohttp://dl.acm.org/citation.cfm?id=1816048

5. Two papers were tied for 5th place in citations:

• 20 - On the sampling of web images for learningvisual concept classifiersShiai Zhu, Gang Wang, Chong-Wah Ngo, Yu-GangJianghttp://dl.acm.org/citation.cfm?id=1816051

• 20 - Plant species identification using leaf imageretrievalCarlos Caballero, M. Carmen Arandahttp://dl.acm.org/citation.cfm?id=1816089

MIR 2008

1. 285 - The MIR flickr retrieval evaluationMark J. Huiskes, Michael S. Lewhttp://dl.acm.org/citation.cfm?id=1460104

2. 203 - Outdoors augmented reality on mobile phoneusing loxel-based visual feature organizationGabriel Takacs, Vijay Chandrasekhar, NatashaGelfand, Yingen Xiong, Wei-Chao Chen, ThanosBismpigiannis, Radek Grzeszczuk, Kari Pulli, BerndGirodhttp://dl.acm.org/citation.cfm?id=1460165

3. 119 - Learning tag relevance by neighbor voting forsocial image retrievalXirong Li, Cees G.M. Snoek, Marcel Worringhttp://dl.acm.org/citation.cfm?id=1460126

4. 58 - Spirittagger: a geo-aware tag suggestion toolmined from flickrEmily Moxley, Jim Kleban, B. S. Manjunathhttp://dl.acm.org/citation.cfm?id=1460102

5. 42 - Content-based mood classification for photosand music: a generic multi-modal classificationframework and evaluation approachPeter Dunker, Stefanie Nowak, André Begau,Cornelia Lanzhttp://dl.acm.org/citation.cfm?id=1460114

MIR 2010

1. 82 - New trends and ideas in visual concept detection:the MIR flickr retrieval evaluation initiativeMark J. Huiskes, Bart Thomee, Michael S. Lewhttp://dl.acm.org/citation.cfm?id=1743475

2. 78 - How reliable are annotations via crowdsourcing:a study about inter-annotator agreement for multi-label image annotationStefanie Nowak, Stefan Rügerhttp://dl.acm.org/citation.cfm?id=1743478

3. 45 - Exploring automatic music annotation with“acoustically-objective” tagsDerek Tingle, Youngmoo E. Kim, Douglas Turnbullhttp://dl.acm.org/citation.cfm?id=1743400

4. 39 - Feature selection for content-based, time-varyingmusical emotion regressionErik M. Schmidt, Douglas Turnbull, Youngmoo E. Kimhttp://dl.acm.org/citation.cfm?id=1743431

5. 34 - ACQUINE: aesthetic quality inference engine –real-time automatic rating of photo aestheticsRitendra Datta, James Z. Wanghttp://dl.acm.org/citation.cfm?id=1743457

ESSENTIA: an opensource library for audioanalysisOver the last decade, audio analysis has become afield of active research in academic and engineeringworlds. It refers to the extraction of information andmeaning from audio signals for analysis, classification,storage, retrieval, and synthesis, among other tasks.Related research topics challange understanding and




















http://records.sigmm.ndlab.net/2014/03/essentia-an-open-source-library-for-audio-analysis/



.




modeling of sound and music, and develop methodsand technologies that can be used to process audioin order to extract acoustically and musically relevantdata and make use of this information. Audio analysistechniques are instrumental in the development of newaudio-related products and services, because thesetechniques allow novel ways of interaction with soundand music.

Essentia is an open-source C++ library for audioanalysis and audio-based music informationretrieval released under the Affero GPLv3 license (alsoavailable under proprietary license upon request). Itcontains an extensive collection of reusable algorithmswhich implement audio input/output functionality,standard digital signal processing blocks, statisticalcharacterization of data, and a large set of spectral,temporal, tonal and high-level music descriptors thatcan be computed from audio. In addition, Essentia canbe complemented with Gaia, a C++ library with pythonbindings which allows searching in a descriptor spaceusing different similarity measures and classifying theresults of audio analysis (same license terms apply).Gaia can be used to generate classification models thatEssentia can use to compute high-level description ofmusic.

Essentia is not a framework, but rather a collectionof algorithms wrapped in a library. It doesn’t enforcecommon high-level logic for descriptor computation (soyou aren’t locked into a certain way of doing things).It rather focuses on the robustness, performance andoptimality of the provided algorithms, as well as easeof use. The flow of the analysis is decided andimplemented by the user, while Essentia is taking care ofthe implementation details of the algorithms being used.A number of examples are provided with the library,however they should not be considered as the onlycorrect way of doing things.

The library includes Python bindings as well as anumber of predefined executable extractors for theavailable music descriptors, which facilitates its usefor fast prototyping and allows setting up researchexperiments very rapidly. The extractors cover anumber of common use-cases for researchers, forexample, computing all available music descriptors foran audio track, extracting only spectral, rhythmic, ortonal descriptors, computing predominant melody andbeat positions, and returning the results in yaml/jsondata formats. Furthermore, it includes a Vamp pluginto be used for visualization of music descriptors usinghosts such as Sonic Visualiser.

The library is cross-platform and supports Linux, MacOS X and Windows systems. Essentia is designedwith a focus on the robustness of the providedmusic descriptors and is optimized in terms of thecomputational cost of the algorithms. The providedfunctionality, specifically the music descriptors includedout-of-the-box and signal processing algorithms, iseasily expandable and allows for both researchexperiments and development of large-scale industrialapplications.

Essentia has been in development for more than 7 yearsincorporating the work of more than 20 researchers anddevelopers through its history. The 2.0 version markedthe first release to be publicly available as free softwarereleased under AGPLv3.

Algorithms

Essentia currently features the following algorithms(among others):

• Audio file input/output: ability to read and writenearly all audio file formats (wav, mp3, ogg, flac, etc.)

• Standard signal processing blocks: FFT, DCT,frame cutter, windowing, envelope, smoothing

• Filters (FIR & IIR): low/high/band pass, band reject,DC removal, equal loudness

• Statistical descriptors: median, mean, variance,power means, raw and central moments, spread,kurtosis, skewness, flatness

• Time-domain descriptors: duration, loudness,LARM, Leq, Vickers’ loudness, zero-crossing-rate, logattack time and other signal envelope descriptors

• Spectral descriptors: Bark/Mel/ERB bands, MFCC,GFCC, LPC, spectral peaks, complexity, rolloff,contrast, HFC, inharmonicity and dissonance

• Tonal descriptors: Pitch salience function,predominant melody and pitch, HPCP (chroma)related features, chords, key and scale, tuningfrequency

• Rhythm descriptors: beat detection, BPM, onsetdetection, rhythm transform, beat loudness

• Other high-level descriptors: danceability,dynamic complexity, audio segmentation, semanticannotations based on SVM classifiers

The complete list of algorithms is available online in theofficial documentation.

Architecture

The main purpose of Essentia is to serve as a libraryof signal-processing blocks. As such, it is intended toprovide as many algorithms as possible, while trying tobe as little intrusive as possible. Each processing blockis called an Algorithm, and it has three different types

http://www.gnu.org/licenses/agpl.html

http://github.com/MTG/gaia

http://www.vamp-plugins.org/

http://www.sonicvisualiser.org/

http://essentia.upf.edu/documentation/

.




of attributes: inputs, outputs and parameters. Algorithmscan be combined into more complex ones, which arealso instances of the base Algorithm class and behavein the same way. An example of such a compositealgorithm is presented in the figure below. It shows acomposite tonal key/scale extractor, which combinesthe algorithms for frame cutting, windowing, spectrumcomputation, spectral peaks detection, chroma features(HPCP) computation and finally the algorithm for key/scale estimation from the HPCP (itself a compositealgorithm).

The algorithms can be used in two different modes:standard and streaming. The standard mode isimperative while the streaming mode is declarative. Thestandard mode requires to specifying the inputs andoutputs for each algorithm and calling their processingfunction explicitly. If the user wants to run a networkof connected algorithms, he/she will need to manuallyrun each algorithm. The advantage of this mode isthat it allows very rapid prototyping (especially whenthe python bindings are coupled with a scientificenvironment in python, such as ipython, numpy, andmatplotlib).

The streaming mode, on the other hand, allows todefine a network of connected algorithms, and then aninternal scheduler takes care of passing data betweenthe algorithms inputs and outputs and calling thealgorithms in the appropriate order. The scheduleravailable in Essentia is optimized for analysis tasks, anddoes not take into account the latency of the network.For real-time applications, one could easily replace thisscheduler with another one that favors latency overthroughput. The advantage of this mode is that it resultsin simpler and safer code (as the user only needs tocreate algorithms and connect them, there is no roomfor him to make mistakes in the execution order ofthe algorithms), and in lower memory consumption ingeneral, as the data is streamed through the networkinstead of being loaded entirely in memory (which is theusual case when working with the standard mode). Eventhough most of the algorithms are available for both thestandard and streaming mode, the code that implementsthem is not duplicated as either the streaming versionof an algorithm is deduced/wrapped from its standardimplementation, or vice versa.

Applications

Essentia has served in a large number of researchactivities conducted at Music Technology Group since

2006. It has been used for music classification, semanticautotagging, music similarity and recommendation,visualization and interaction with music, sound indexing,musical instruments detection, cover detection, beatdetection, and acoustic analysis of stimuli forneuroimaging studies. Essentia and Gaia have beenused extensively in a number of research projects andindustrial applications. As an example, both librariesare employed for large-scale indexing and content-based search of sound recordings within Freesound,a popular repository of Creative Commons licensedaudio samples. In particular, Freesound uses audiobased similarity to recommend sounds similar to userqueries. Dunya is a web-based software applicationusing Essentia that lets users interact with an audiomusic collection through the use of musical conceptsthat are derived from a specific musical culture, in thiscase Carnatic music.

Examples

Essentia can be easily used via its python bindings.Below is a quick illustration of Essentia’s possibilities forexample on detecting beat positions of music track andits predominant melody in a few lines of python codeusing the standard mode:

from essentia.standard import *;

audio = MonoLoader(filename =

'audio.mp3')(); beats, bconfidence =

http://en.wikipedia.org/wiki/Harmonic_pitch_class_profiles

http://www.mtg.upf.edu/

http://freesound.org/

http://dunya.compmusic.upf.edu/carnatic/

http://en.wikipedia.org/wiki/Beat_detection

http://www.justinsalamon.com/melody-extraction.html

.

SIGMM Award for Outstanding PhD Thesis in Multimedia Computing, Communications and Applications



BeatTrackerMultiFeature()(audio); print

beats; audio = EqualLoudness()

(audio); melody, mconfidence

= PredominantMelody(guessUnvoiced=True,

frameSize=2048, hopSize=128)(audio);

print melody

Another python example for computation of MFCCfeatures using the streaming mode:from essentia.streaming import * loader

= MonoLoader(filename = 'audio.mp3')

frameCutter = FrameCutter(frameSize =

1024, hopSize = 512) w = Windowing(type

= 'hann') spectrum = Spectrum() mfcc =

MFCC() pool = essentia.Pool() # connect

all algorithms into a network loader.audio

>> frameCutter.signal frameCutter.frame

>> w.frame >> spectrum.frame

spectrum.spectrum >> mfcc.spectrum

mfcc.mfcc >> (pool, 'mfcc') mfcc.bands

>> (pool, 'mfcc_bands') # compute network

essentia.run(loader) print pool['mfcc']

print pool['mfcc_bands']

Vamp plugin provided with Essentia allows to use manyof its algorithms via the graphical interface of SonicVisualiser. In this example, positions of onsets arecomputed for a music piece (marked in red):

An interested reader is referred to the documentiononline for more example applications built on top ofEssentia.

Getting Essentia

The detailed information about Essentia is availableonline on the official web page: http://essentia.upf.edu.It contains the complete documentation for the project,compilation instructions for Debian/Ubuntu, Mac OS Xand Windows, as well as precompiled packages. Thesource code is available at the official Github repository:http://github.com/MTG/essentia. In our current work weare focused on expanding the library and the communityof users, and all active Essentia users are encouragedto contribute to the library.

References

[1] Serra, X., Magas, M., Benetos, E., Chudy, M., Dixon,S., Flexer, A., Gómez, E., Gouyon, F., Herrera, P.,Jordà, S., Paytuvi, O, Peeters, G., Schlüter, J., Vinet,H., and Widmer, G., Roadmap for Music InformationReSearch, G. Peeters, Ed., 2013. [Online].

[2] Bogdanov, D., Wack N., Gómez E., Gulati S., HerreraP., Mayor O., Roma, G., Salamon, J., Zapata, J.,Serra, X. (2013). ESSENTIA: an Audio Analysis Libraryfor Music Information Retrieval. International Societyfor Music Information Retrieval Conference(ISMIR’13).493-498.

[3] Bogdanov, D., Wack N., Gómez E., Gulati S., HerreraP., Mayor O., Roma, G., Salamon, J., Zapata, J.,Serra, X. (2013). ESSENTIA: an Open-Source Libraryfor Sound and Music Analysis. ACM InternationalConference on Multimedia (MM’13).

SIGMM Awardfor OutstandingPhD Thesis inMultimedia Computing,Communications andApplications

Award Description

This award will be presented at most once per year to aresearcher whose PhD thesis has the potential of veryhigh impact in multimedia computing, communicationand applications, or gives direct evidence of suchimpact. A selection committee will evaluate contributionstowards advances in multimedia including multimediaprocessing, multimedia systems, multimedia networkservices, multimedia applications and interfaces. Theaward will recognize members of the SIGMM communityand their research contributions in their PhD theses aswell as the potential of impact of their PhD theses inmultimedia area. The selection committee will focus oncandidates’ contributions as judged by innovative ideasand potential impact resulting from their PhD work.

The award includes a US$500 honorarium, an awardcertificate of recognition, and an invitation for therecipient to receive the award at a current year’sSIGMM-sponsored conference, the ACM InternationalConference on Multimedia (ACM Multimedia). A public

http://en.wikipedia.org/wiki/Mel-frequency_cepstrum

http://en.wikipedia.org/wiki/Onset_%28audio%29

http://essentia.upf.edu

http://github.com/MTG/essentia

http://mires.eecs.qmul.ac.uk/wiki/index.php/Roadmap

http://mires.eecs.qmul.ac.uk/wiki/index.php/Roadmap

http://mtg.upf.edu/node/2793

http://mtg.upf.edu/node/2793



http://records.sigmm.ndlab.net/2014/04/sigmm-award-for-outstanding-phd-thesis-in-multimedia-computing-communications-and-applications/






.

SIGMM Award for Outstanding PhD Thesis in Multimedia Computing, Communications and Applications



citation for the award will be placed on the SIGMMwebsite, in the SIGMM Records e-newsletter as well asin the ACM e-newsletter.

Funding

The award honorarium, the award plaque of recognitionand travel expenses to the ACM InternationalConference on Multimedia will be fully sponsored by theSIGMM budget.

Nomination Applications

Nominations will be solicited by the 31st May 2014with an award decision to be made by August 30. Thistiming will allow a recipient to prepare for an awardpresentation at ACM Multimedia in that Fall (October/November).

The initial nomination for a PhD thesis must relate toa dissertation deposited at the nominee’s AcademicInstitution between January and December of the yearprevious to the nomination. As discussed below, somedissertations may be held for up to three years by theselection committee for reconsideration. If the originalthesis is not in English, a full English translation mustbe provided with the submission. Nominations for theaward must include:

1. PhD thesis (upload at: https://cmt.research.microsoft.com/SIGMMA2014/ )

2. A statement summarizing the candidate’s PhD thesiscontributions and potential impact, and justification ofthe nomination (two pages maximum);

3. Curriculum Vitae of the nominee

4. Three endorsement letters supporting the nominationincluding the significant PhD thesis contributionsof the candidate. Each endorsement should beno longer than 500 words with clear specificationof nominee PhD thesis contributions and potentialimpact on the multimedia field.

5. A concise statement (one sentence) of the PhD thesiscontribution for which the award is being given. Thisstatement will appear on the award certificate and onthe website.

The nomination rules are:

1. The nominee can be any member of the scientificcommunity.

2. The nominator must be a SIGMM member.

3. No self-nomination is allowed.

If a particular thesis is considered to be of exceptionalmerit but not selected for the award in a given year, theselection committee (at its sole discretion) may elect toretain the submission for consideration in at most twofollowing years. The candidate will be invited to resubmithis/her work in these years.

A thesis is considered to be outstanding if:

1. Theoretical contributions are significant andapplication to multimedia is demonstrated.

2. Applications to multimedia is outstanding, techniquesare backed by solid theory with clear demonstrationthat algorithms can be applied in new domains –e.g., algorithms must be demonstrably scalable inapplication in terms of robustness, convergence andcomplexity.

The submission process of nominations will bepreceded by the call for nominations. The call ofnominations will be widely publicized by the SIGMMawards committee and by the SIGMM Executive Boardat the different SIGMM venues, such as during theSIGMM premier ACM Multimedia conference (at theSIGMM Business Meeting) on the SIGMM web site,via SIGMM mailing list, and via SIGMM e-newsletterbetween September and December of the previousyear.

Submission Process

• Register an account at https://cmt.research.microsoft.com/SIGMMA2014/ andupload one copy of the nominated PhD thesis. Thenominee will receive a Paper ID after the submission.

• The nominator must then collate other materialsdetailed in the previous section and upload themas supplementary materials, except the endorsementletters, which must be emailed separately as detailedbelow.

• Contact your referees and ask them to sendall endorsement letters to [email protected] the title: “PhD Thesis Award EndorsementLetter for [YourName]“. The web administrator willacknowledge the receipt and the submission CMTwebsite will reflect the status of uploaded documentsand endorsement letters.

It is the responsibility of the nominator to followthe process and make sure documentation iscomplete. Thesis with incomplete documentation will beconsidered invalid.

Selection Committee

The 2014 award selection committee consists of:

https://cmt.research.microsoft.com/SIGMMA2014/




.

Call for Nominations for the SIGMM Technical Achievement Award 2014



• Prof. Kiyoharu Aizawa ([email protected])from University of Tokyo, Japan

• Prof. Baochun Li ([email protected]) fromUniversity of Toronto, Canada

• Prof. K. Selcuk Candan ([email protected]) fromArizona State University, USA

• Prof. Shin’ichi Satoh ([email protected]) from NationalInstitute of Informatics, Japan

• Dr. Daniel Gatica-Perez ([email protected]) from Idiap-EPFL, Switzerland

Call for Nominations forthe SIGMM TechnicalAchievement Award2014

for Outstanding TechnicalContributions to MultimediaComputing, Communicationsand Applications

AWARD DESCRIPTION

This award is presented every year to aresearcher who has made significant and lastingcontributions to multimedia computing, communicationand applications. Outstanding technical contributionsthrough research and practice are recognized. Towardsthis goal, contributions are considered from academiaand industry that focus on major advances in multimediaincluding multimedia processing, multimedia contentanalysis, multimedia systems, multimedia networkprotocols and services, and multimedia applicationsand interfaces. The award recognizes members of thecommunity for long-term technical accomplishmentsor those who have made a notable impact througha significant technical innovation. The selectioncommittee focuses on candidates’ contributions asjudged by innovative ideas, influence in the community,and/or the technical/social impact resulting from theirwork. The award includes a $2000 honorarium, anaward certificate of recognition, and an invitation for therecipient to present a keynote talk at a current year’sSIGMM-sponsored conference, the ACM InternationalConference on Multimedia (ACM Multimedia). Travelexpenses to the conference will be covered by SIGMM,and a public citation for the award will be placed on theSIGMM website.

FUNDING

The award honorarium, the award certificate ofrecognition and travel expenses to the ACMInternational Conference on Multimedia is fullysponsored by the SIGMM budget.

NOMINATION PROCESS

Nominations are solicited by May 31, 2014 with decisionmade by July 30 2014, in time to allow the aboverecognition and award presentation at ACM Multimedia2014.

Nominations for the award must include:

• A statement summarizing the candidate’saccomplishments, description of the significance ofthe work, and justification of the nomination (twopages maximum);

• Curriculum Vitae of the nominee;

• Three endorsement letters supporting the nominationincluding the significant contributions of the candidate.Each endorsement should be no longer than500 words with clear specification of nomineecontributions and impact on the multimedia field;

• A concise statement (one sentence) of theachievement(s) for which the award is being given.This statement will appear on the award certificateand on the website.

The nomination rules are:

• The nominee can be any member of the scientificcommunity.

• The nominator must be a SIGMM member.

• No self-nomination is allowed.

• Nominations that do not result in an award will bevalid for two further years. After three years a revisednomination can be resubmitted.

• The SIGMM elected officers as well as members ofthe Awards Selection Committee are not eligible.

Please submit your nomination to the award committeeby email.Committee

• Dick Bulterman ([email protected])

• Hong-Jiang Zhang ([email protected])

• Nicu Sebe ([email protected])

• Rainer Lienhart ([email protected])

• Shih-Fu Chang ([email protected])

http://records.sigmm.ndlab.net/2014/04/call-for-nominations-for-the-sigmm-technical-achievement-award-2014/




.

MediaEval 2014: Benchmarking Initiative for Multimedia Evaluation



PREVIOUS RECIPIENTS

• 2013: Dick Bulterman (for outstanding technicalcontributions in multimedia authoring throughresearch, standardization, and entrepreneurship).

• 2012: Hong-Jiang Zhang (pioneering contributionsto and leadership in media computing includingcontent-based media analysis and retrieval, and theirapplications).

• 2011: Shi-Fu Chang (for pioneering research andinspiring contributions in multimedia analysis andretrieval).

• · 2010: Ramesh Jain (for pioneering research andinspiring leadership that transformed multimediainformation processing to enhance the quality oflife and visionary leadership of the multimediacommunity).

• · 2009: Lawrence A. Rowe (for pioneering researchin continuous media software systems and visionaryleadership of the multimedia research community).

• · 2008: Ralf Steinmetz (for pioneering work inmultimedia communications and the fundamentals ofmultimedia synchronization).

MediaEval 2014:BenchmarkingInitiative for MultimediaEvaluation

MediaEval is a multimedia benchmark evaluation thatoffers tasks promoting research and innovation in areasrelated to human and social aspects of multimedia.Registration for MediaEval 2014 is now open.

We encourage participants to register before 1 May,when the first tasks release their first data. TheMediaEval benchmark focuses on aspects of multimediaincluding and going beyond visual content, suchas language, speech, music, and social factors.Participants carry out one or more of the tasks offeredand submit runs to be evaluated. They then write uptheir results and present them at the MediaEval 2014workshop, 16-17 October, Barcelona, Spain.

Dates: May-October

More information: http://www.multimediaeval.org

Call for Nominations:ACM TOMCCAP NicolasD. Georganas BestPaper Award

The Editor-in-Chief of ACM TOMCCAP invites youto nominate candidates for the “ACM Transactionson Multimedia Computing, Communications andApplications Nicolas D. Georganas Best Paper Award”.

The award is given annually to the author(s) of anoutstanding paper published in ACM TOMCCAP withinthe previous legal year from January 1 until December31. The award carries a plaque as well as travel fundsto the ACM MM conference where the awardee(s) willbe honored.

Procedure

Nominations for the award must include the following:

• A statement describing the technical contributionsof the nominated paper and a description of thesignificance of the paper. The statement should notexceed 500 words. No self-nomination is accepted.

• Two additional supporting statements by recognizedexperts in the field regarding the technical contributionof the paper and its significance to the respective field.

Only papers published in regular issues (no SpecialIssues) can be nominated.

Nominations will be reviewed by the SelectionCommittee and the winning paper will finally be voted bythe TOMCCAP Editorial Board.

Deadline

Deadline for nominations of papers published in 2013(Volume 9) is the 15th of June 2014.

Contact

Please send your nominations to theEditor-in-Chief at [email protected](<[email protected]>)If you have questions, please contact theTOMCCAP information director at [email protected] (<[email protected]>)

Further details can be found at http://tomccap.acm.org/

http://records.sigmm.ndlab.net/2014/04/mediaeval-2014-benchmarking-initiative-for-multimedia-evaluation/




http://www.multimediaeval.org/

http://records.sigmm.ndlab.net/2014/04/call-for-nominations-acm-tomccap-nicolas-d-georganas-best-paper-award/




http://tomccap.acm.org/

.

PhD Thesis Summaries




Håvard Espeland

Processing Cyclic MultimediaWorkloads on ModernArchitectures

Supervisor(s) and Committee member(s): Pål Halvorsen,Carsten Griwodz (supervisors), Christian Plessl, MeiWen, Tor Skeie (opponents)URL: http://home.ifi.uio.no/paalh/students/HaavardEspeland-phd.pdf

Working with modern architectures for high performanceapplications is increasingly more diffi- cult forprogrammers as the complexity of both the systemarchitectures and software continue to increase. Thelevel of hand tuning and native adaptations required toachieve high performance comes at the cost of limitingthe portability of the software. For instance, we show thata compute intensive DCT algorithm performs better ongraphic processors than the best algorithm for x86. Inparticular, limited portability is true for cyclic multimediaworkloads, a set of programs that run continuouslywith strict requirements for high performance and lowlatency. An example of a typical multimedia workload isa pipeline of many small image processing algorithmsworking in tandem to complete a particular task. Theinput can be videos from one or more live cameras,and the output is a set of video frames with elementsfrom several of the source videos, for example asstitched panorama frames or 3D warped video. Such asetup runs continuously and potentially needs to adaptto various degrees of changes in the setup withoutinterruptions or downtime.

To reach the performance goal required by multimediapipelines, modern, heterogeneous architectures are

considered instead of the traditional symmetric multi-processing architectures. We also investigate variationsbetween recent microarchitectures of symmetricprocessors to identify differences that a low-levelscheduler must take into account. Further, sincemultimedia workloads often need to adapt to variousexternal conditions, e.g., adding another participantto a video conference, we also investigate elasticand portable processing of multimedia workloads.To do this, we propose a framework design andlanguage, which we call P2G. In the age of Big Data,this idea differs from the typical frameworks usedfor distributed processing, such as MapReduce andDryad, in that it is designed for continuous operationinstead of batch processing of large workloads.We emphasize heterogeneous support and exposeparallel opportunities in workloads in a way that iseasy to target since it is similar to sequential executionwith mul- tidimensional arrays. The framework ideasare implemented as a prototype and released as anopen source platform for further experimentation andevaluation.

Media Performance GroupURL: http://mpg.ndlab.net

The Media Performance Group (MPG) addressesresource utilization and performance challenges tosupport a wide range of interactive multimedia servicesto the large user masses in the Internet. The goalsare to reduce the costs, increase the number of usersand optimize the perceived service quality. MPG’sactivities branch into several areas of multimediasystems to maintain and improve our ability to evaluatethe performance of complete multimedia systems. Thisgoal ties research branches together that are as diverseas multicore programming and user perception.

Jia Hao

The transmission and processingof sensor-rich videos in mobileenvironment

Supervisor(s) and Committee member(s): RogerZimmermann (supervisor), Ye Wang (advisor), Wei TsangOoi (advisor), Mun Choon Chan (rapporteur)URL: http://scholarbank.nus.edu.sg/handle/10635/48668

http://records.sigmm.ndlab.net/?phd-thesis-summary=havard-espeland

http://home.ifi.uio.no/paalh/students/HaavardEspeland-phd.pdf

http://home.ifi.uio.no/paalh/students/HaavardEspeland-phd.pdf

http://mpg.ndlab.net

http://records.sigmm.ndlab.net/?phd-thesis-summary=jia-hao

http://scholarbank.nus.edu.sg/handle/10635/48668

.




The astounding volume of camera sensors producedfor and embedded in cellular phones has led to arapid advancement in their quality, wide availability andpopularity for capturing, uploading and sharing of videos(also referred to user-generated content or UGC).Furthermore, GPS-enabled smartphones have becomean essential contributor to location-based services. Alarge number of geo-tagged photos and videos havebeen accumulating continuously on the web, posinga challenging problem for mining this type of mediadata. Existing solutions attempt to examine the signalcontent of the videos and recognize objects and events.This is typically time-consuming and computationallyexpensive and the results can be uneven in theirquality. Therefore these methods face challenges whenapplied to large video repositories. Furthermore, theacquisition and transmission of large amounts of videodata on mobile devices face fundamental challengessuch as power and wireless bandwidth constraints. Tosupport diverse mobile video applications, it is critical toovercome these challenges.

Recent technological trends have opened anotheravenue that fuses much more accurate, relevantdata with videos: the concurrent collection of sensor-generated geospatial contextual data. The aggregationof multi-sourced geospatial data into a standalone meta-data tag allow video content to be identified by anumber of precise, objective geospatial characteristics.These so-called sensor-rich videos can conveniently becaptured with smartphones. In this thesis we investigatethe transmission and processing of sensor-rich videos inmobile environment. Our work focuses on the followingkey issues for sensor-rich videos:

1) Energy-efficient video acquisition and upload. Wedesign a system to support energy-efficient sensor-rich video delivery. The core of our approach is theseparate transmission of the small amount of text-based

geospatial meta-data from the large binary-based videocontent.

2) Point of Interest (POI) detection and visual distanceestimation. We propose a technique which is ableto detect interesting regions and objects and theirdistances from the camera positions in a fully automatedway.

3) Presentation of user generated videos. We present asystem that provides an integrated solution to presentvideos based on keyframe extraction and interactive,map-based browsing.

4) Geo-predictive video streaming. We present amethod to predict the bandwidth change for HTTPstreaming. The method make use of the geo-locationinformation to build bandwidth maps to facilitatebandwidth prediction, and efficient quality adaptation.We also propose two quality adaptation algorithms foradaptive HTTP streaming.

Our study shows that using location and viewingdirection information, coupled with timestamps, efficientvideo delivery systems can be developed, moreinteresting information can be mined from videorepository, and user-generated video presentation canbe more natural.

Media Management Research LabURL: http://eiger.ddns.comp.nus.edu.sg

Our group's research focuses on Streaming Media andGeo-Referenced Video Management (GeoVid).The GeoVid project explores the concept of sensor-richvideo tagging. Specifically, recorded videos are taggedwith a continuous stream of extended geographicproperties that relate to the camera scenes. Thismeta-data is then utilized for storing, indexing andsearching large collections of community-generatedvideos. By considering video related meta-information,more relevant search results can be returned andadvanced searches, such as directional and surroundqueries, can be executed.

Johannes Konert

Interactive Multimedia Learning:Using Social Media for PeerEducation in Single-PlayerEducational Games

Supervisor(s) and Committee member(s): Evaluator:Prof. Dr.-Ing. habil. Ralf Steinmetz Co-evaluator: Prof. Dr.paed. habil. Regina Bruder

http://eiger.ddns.comp.nus.edu.sg

http://records.sigmm.ndlab.net/?phd-thesis-summary=johannes-konert

.

Recently published



Social Media, as an information and communicationtechnology, enables users to exchange informationabout experiences and insights in easy ways. Suchexchange can be used for peer interaction amongplayers of educational computer games as well.The players profit from social media content aslearning resources are created, edited, and thenshared by peers. Therefore, social media applicationsand concepts can serve as a way to bring peereducation concepts closer to educational games andenhance the way learners share hints, assess eachothers’ solutions, and give feedback in the learningand playing process. However, the intersection ofserious games and social media appears to be aquite novel research field. This thesis contributes anarchitectural approach, addressing the challenge ofintersecting educational games and social media froman interdisciplinary perspective. Major contributionsinclude concepts for user-generated content exchange,game adaptation, and peer group formation. Thefirst contribution, a concept for content exchange,supports peer tutoring and assessment of user-generated content. It’s implementation and evaluation inthe PEDALE scenario addresses primarily the IndividualGroup Assessment Problem. This problem concernsthe diagnosis and assessment of individual learners’abilities, while simultaneously seeking group learningand collaboration. The evaluation study conductedthrough this work in a classroom scenario showsthe benefits of the content and knowledge exchangefor individual learners under certain conditions. Thesecond contribution, a concept for game adaptation, isdesigned to support peer interaction between playersof educational games and acquaintances in a socialmedia environment. The thesis’ solution proposesinteraction patterns to allow the influence to gameplayby peers. In the corresponding Genius scenario, theconducted evaluation study shows significantly strongeracceptance values by players experiencing the gameadaptation, compared to those using a game withoutthem. For the third contribution, a concept for peergroup formation, a new algorithm has been designed

on the basis of a mathematical optimization model.The underlying Group Formation Problem is formallydefined and thoroughly analyzed. This problem refers tothe necessity to simultaneously respect homogeneousas well as heterogeneous matching criteria whenbuilding learning groups. The simulative evaluationreveals that the proposed solution, GroupAL, generatessignificantly better group formation results than allreviewed algorithms from related work. The resultsfrom the three conducted evaluations contribute tothe aim of bringing serious games and social mediacloser together. The created solutions and the unifyingmiddleware architecture SoCom.KOM build a solidfoundation for further research on the creation of socialserious sames.

Recently published

IEEE MultiMedia Volume 21,Issue 2

Editor-In-Chief: Yong RuiURL: http://www.computer.org/multimediaPublished: April–June 2014

Feature Articles

• Fabien Danieau, Julien Fleureau, Philippe Guillotel,Nicolas Mollet, Marc Christie, and Anatole Lecuyer:Toward Haptic Cinematography: Enhancing MovieExperiences with Camera-Based Haptic Effects

• Mei-Chen Yeh and Wen-Po Wu: Clustering Faces inMovies Using an Automatically Constructed SocialNetwork

• Tao Guan, Yunfeng He, Liya Duan, Jianzhong Yang,Juan Gao, and Junqing Yu: Efficient BOF Generationand Compression for On-Device Mobile Visual LocationRecognition

• Kewei Tu, Meng Meng, Mun Wai Lee, Tae Eun Choe,and Song-Chun Zhu: Joint Video and Text Parsing forUnderstanding Events and Answering Queries

Department Articles

• Yong Rui: EIC’s Message: IEEE MultiMedia ForgesAhead

• Thomas Huang, Vuong Le, Thomas Paine, PooyaKhorrami, and Usman Tariq: Vision & Views: VisualMedia: History and Perspectives

• Si Liu, Luoqi Liu, and Shuicheng Yan: Media Impact:Fashion Analysis: Current Techniques and FutureDirections

• John Wus, Jun Tian, Hongbing Li, Dong-Qing Zhang,Wei Jiang, Zhenyu Wu, and Heather Yu: Multimedia atWork: Toward Experiential Mobile Media Processing

http://records.sigmm.ndlab.net/?eventjournal-toc=ieee-multimedia-volume-21-issue-2

http://records.sigmm.ndlab.net/?eventjournal-toc=ieee-multimedia-volume-21-issue-2

http://www.computer.org/multimedia

.

Recently published



• Ying Chen and Anthony Vetro: Industry & Standards:Next-Generation 3D Formats with Depth Map Support

MMSJ Volume 20, Issue 1

Editor-in-Chief: Thomas PlagemannURL: http://link.springer.com/journal/530/20/1/page/1Published: February 2014

The Multimedia Systems Journal details innovativeresearch ideas, emerging technologies, state-of-the-art methods and tools in all aspects of multimediacomputing, communication, storage, and applications. Itfeatures theoretical, experimental, and survey articles.

• Suchendra M. Bhandarkar, Lakshmish Ramaswamy,Hari K. Devulapally: Collaborative caching for efficientdissemination of personalized video streams inresource constrained environments

• Minseok Song, Wanhyung Ryu, Jeong Seop Sim,Yeongju Lee: Balancing disk energy against reliabilityin video playback

• Benyamin Norouzi, Seyed Mohammad Seyedzadeh,Sattar Mirzakuchaki, Mohammad Reza Mosavi: A novelimage encryption based on hash function with only two-round diffusion process

• Daniele Borghesani, Costantino Grana, Rita Cucchiara:Miniature illustrations retrieval and innovativeinteraction for digital illuminated manuscripts

• Tomasz Hachaj, Marek R. Ogiela: Rule-basedapproach to recognizing human body poses andgestures in real time

MMSJ Volume 20, Issue 2

Editor-in-Chief: Thomas PlagemannURL: http://link.springer.com/journal/530/20/2/page/1Published: March 2014

Special Issue on Digital Media Security and RightsManagement

Guest editors: Wojciech Mazurczyk, KrzysztofSzczypiorski

• Wojciech Mazurczyk, Krzysztof Szczypiorski:Editorial: Advances in digital media security and rightmanagement

• David Megías, Josep Domingo-Ferrer: Privacy-awarepeer-to-peer content distribution using automaticallyrecombined fingerprints

• Ta Minh Thanh, Munetoshi Iwakiri: A proposal of digitalrights management based on incomplete cryptographyusing invariant Huffman code length feature

• Hui Tian, Jin Liu, Songbin Li: Improving security ofquantization-index-modulation steganography in lowbit-rate speech streams

• Mehdi Fallahpour, David Megías: Secure logarithmicaudio watermarking scheme based on the humanauditory system

• Robert Huijie Deng, Xuhua Ding, Yongdong Wu, ZhuoWei: Efficient block-based transparent encryption forH.264/SVC bitstreams

• Wei Chen, Zafar Shahid, Thomas Stütz, FlorentAutrusseau, Patrick Le Callet: Robust drift-free bit-ratepreserving H.264 watermarking

• Xingguang Song, Shiguo Lian, Wei Hu, Yang Hu:Digital video watermarking based on intra predictionmodes for audio video coding standard

• Gaurav Bhatnagar, Q. M. Jonathan Wu: Enhancing thetransmission security of biometric images using chaoticencryption

• Mohammad Javad Khosravi, Ahmad Reza Naghsh-Nilchi: A novel joint secret image sharing and robuststeganography method using wavelet

• Guangjie Liu, Weiwei Liu, Yuewei Dai, Shiguo Lian:Adaptive steganography based on block complexityand matrix embedding

• Deepayan Bhowmik, Charith Abhayaratne: Onrobustness against JPEG2000: a performanceevaluation of wavelet-based watermarking techniques

MMTC R-Letter Volume 5,Issue 2

Board Director: Irene ChengBoard Co-Directors: Weiyi Zhang and Christian TimmererURL: http://committees.comsoc.org/mmc/r-letters/MMTC-RLetter-Apr2014.pdfPublished: April 2014

The objectives of the IEEE MMTC R-Letter are:

• Stimulate research on multimedia communication.

• Encourage researchers to submit papers (R-LetterCFP) to IEEE MMTC sponsored publications andconferences.

• Nominate papers published in IEEE MMTCsponsored publications/conferences for best paperawards.

• Message from the Review Board

• Prediction of Video Popularity Based on Cross-DomainKnowledge Transfer

• A short review for “Towards Cross-Domain Learningfor Social Video Popularity Prediction”

• Edited by Karine Pires and Gwendal Simon

• Lighting the design of replication algorithms for P2PVoD system in practice

http://records.sigmm.ndlab.net/?eventjournal-toc=mmsj-volume-20-issue-1

http://link.springer.com/journal/530/20/1/page/1

http://records.sigmm.ndlab.net/?eventjournal-toc=mmsj-volume-20-issue-2


http://records.sigmm.ndlab.net/?eventjournal-toc=mmtc-r-letter-volume-5-issue-2

http://records.sigmm.ndlab.net/?eventjournal-toc=mmtc-r-letter-volume-5-issue-2

http://committees.comsoc.org/mmc/r-letters/MMTC-RLetter-Apr2014.pdf

http://committees.comsoc.org/mmc/r-letters/MMTC-RLetter-Apr2014.pdf

.

Recently published



• A short review for “On Replication Algorithm in P2PVoD”

• Edited by Lifeng Sun

• The Design of Next Generation MultimediaSynchronization Algorithms

• A short review for “Evolution of temporal multimediasynchronization principles:A historical viewpoint”

• Edited by Irene Cheng

• Converting 2D to 3D by Learning from Examples

• A short review for “Learning-based, automatic 2D-to-3D image and video conversion”

• Edited by Jun Zhou

• Sparse Representation Assists Video Tagging

• A short review for “Video-to-Shot Tag Propagation byGraph Sparse Group Lasso”

• Edited by Vladan Velisavljevi#

• Using Near-Infrared Image for Dehazing

• A short review for “Near-Infrared Guided Color ImageDehazing”

• Edited by Gene Cheung

• Exploring frequency-domain oversampling formulticarrier transmissions in Underwater AcousticCommunications

• A short review for “Frequency-Domain Oversamplingfor Zero-Padded OFDM in Underwater AcousticCommunications”

• Edited by Weiyi Zhang

• Paper Nomination Policy

• MMTC R-Letter Editorial Board

• Multimedia Communications Technical Committee(MMTC) Officers

MTAP Volume 69, Issue 2

Editor-in-Chief: Borko FurhtURL: http://link.springer.com/journal/11042/69/2/page/1Published: March 2014

Multimedia Tools and Applications publishes originalresearch articles on multimedia development andsystem support tools as well as case studies ofmultimedia applications. It also features experimentaland survey articles. The journal is intended foracademics, practitioners, scientists and engineers whoare involved in multimedia system research, design andapplications. All papers are peer reviewed.

• Anastasios Doulamis, Nikolaos Doulamis,Luc van Gool, Mark Nixon: Guest editorial: Event-based video analysis/retrieval

• Rachid Benmokhtar: Robust human action recognitionscheme based on high-level feature fusion

• Constantinos Lalos, Athanasios Voulodimos,Anastasios Doulamis, Theodora Varvarigou: Efficienttracking using a robust motion estimation technique

• Athanasios S. Voulodimos, Dimitrios I. Kosmopoulos,Nikolaos D. Doulamis, Theodora A. Varvarigou: A top-down event-driven approach for concurrent activityrecognition

• Steven Verstockt, Sofie Van Hoecke,Pieterjan De Potter, Peter Lambert,Charles Hollemeersch, Bart Sette, Bart Merci, Rik Vande Walle: Multi-modal time-of-flight based fire detection

• Anastasios Doulamis: Event-driven video adaptation: Apowerful tool for industrial video supervision

• Sher Muhammad Doudpota: Mining movie archives forsong sequences

• Chrysoula Gkonela, Konstantinos Chorianopoulos:VideoSkip: event detection in social web videos with animplicit user heuristic

• Klimis Ntalianis, Nicolas Tsapatsoulis,Anastasios Doulamis, Nikolaos Matsatsinis: Automaticannotation of image databases based on implicitcrowdsourcing, visual concept modeling and evolution

• Stéphane Marchand-Maillet, Patrick Lambert,Bernard Mérialdo, Jenny Benois-Pineau: GuestEditorial: Preface to the special issue on Content-Based Multimedia Indexing

• Xiushan Nie, Jiande Sun, Zhihui Xing, Xiaocui Liu:Video fingerprinting based on graph model

• Sabin Tiberius Strat, Alexandre Benoit,Patrick Lambert, Alice Caplier: Retina enhanced SURFdescriptors for spatio-temporal concept detection

• Alexis Lechervy, Philippe-Henri Gosselin,Frédéric Precioso: Boosted kernel for imagecategorization

• Wei Zhang, Ke Gao, Yongdong Zhang, Jintao Li:Efficient binary code indexing with pivot based localitysensitive clustering

• Hisham Mohamed, Stéphane Marchand-Maillet:Distributed media indexing based on MPI andMapReduce

• Antonio Foncubierta-Rodríguez, Henning Müller,Adrien Depeursinge: Retrieval of high-dimensionalvisual data: current state, trends and challenges ahead

MTAP Volume 69, Issue 3

Editor-in-Chief: Borko FurhtURL: http://link.springer.com/journal/11042/69/3/page/1Published: April 2014

• Cheonshik Kim: Data hiding by an improved exploitingmodification direction

• Yajie Yan , Xiaohui Liang , Ke Xie & Qinping Zhao:ASEHM: a new transmission control mechanism forremote rendering system

• Lixing Dong , Shufang Lu & Xiaogang Jin: Real-timeimage-based chinese ink painting rendering

• Haidong Wang & Guizhong Liu: Priority and delayaware packet management framework for real-timevideo transport over 802.11e WLANs

http://records.sigmm.ndlab.net/?eventjournal-toc=mtap-volume-69-issue-2


http://records.sigmm.ndlab.net/?eventjournal-toc=mtap-volume-69-issue-3


.

Recently published



• Dong Hyun Kim & Jong Deok Kim: A collisionavoidance scheme for the synchronized broadcastpackets in a multi-AP Wi-Fi broadcasting system

• Christian X. Ries & Rainer Lienhart: A survey on visualadult image recognition

• Daniel Carlos Guimarães Pedronette , Ricardo da SilvaTorres & Rodrigo Tripodi Calumby: Using contextualspaces for image re-ranking and rank aggregation

• Rehanullah Khan , Allan Hanbury , Robert Sablatnig ,Julian Stöttinger , F. Ali Khan & F. Alam Khan:Systematic skin segmentation: merging spatial andnon-spatial data

• Svebor Karaman , Jenny Benois-Pineau , VladislavsDovgalecs , Rémi Mégret , Julien Pinquier , RégineAndré-Obrecht , Yann Gaëstel & Jean-FrançoisDartigues: Hierarchical Hidden Markov Model indetecting activities of daily living in wearable videos forstudies of dementia

• Jacek Chmielewski: Finding interactive 3D objects bytheir interaction properties

• Kuan-Sheng Zou , Wai-Hung Ip , Chun-Ho Wu , Zeng-Qiang Chen , Kai-Leung Yung & Ching-Yuen Chan:A novel 3D model retrieval approach using combinedshape distribution

• Can Fang , Peng Zhang , Cheng Fu & Zili Zhang:Coverage enhancement by using the mobility of mobilesensor nodes:

• Roya Choupani , Stephan Wong & Mehmet Tolun:Multiple description coding for SNR scalable videotransmission over unreliable networks

• Yuan-Yu Tsai: An adaptive steganographic algorithmfor 3D polygonal models using vertex decimation

• Bing Yang & Duanqing Xu: Color boosted visualsaliency detection and its application to imageclassification

• Xueming Qian , Danping Guo , Xingsong Hou , ZhiLi , Huan Wang , Guizhong Liu & Zhe Wang: HWVP:hierarchical wavelet packet descriptors and theirapplications in scene categorization and semanticconcept retrieval

• Abolfazl Tazaree , Amir-Masud Eftekhari-Moghadam &Saeedeh Sajjadi-Ghaem-Maghami: A semantic imageclassifier based on hierarchical fuzzy association rulemining

• Brett Adams , Dinh Phung & Svetha Venkatesh: Socialreader: towards browsing the social web

• Rodrigo Tripodi Calumby , Ricardo da Silva Torres &Marcos André Gonçalves: Multimodal retrieval withrelevance feedback based on genetic programming

• Huey-Min Sun: Online smoothness with droppingpartial data based on advanced video coding stream

• Yi-Ming Chen & Wei-Chen Wu: An anonymous DRMscheme for sharing multimedia files in P2P networks

• Mohsin Bilal , Ayyaz Hussain , Muhammad ArfanJaffar , Tae-Sun Choi & Anwar M. Mirza: Estimationand optimization based ill-posed inverse restorationusing fuzzy logic

• Bilel Ben Fradj & Azza Ouled Zaid: Scalable videocoding using motion-compensated temporal filteringand intra-band wavelet based compression

• Guanyang Liu , Yuru Zhang , Keke Lu & Lingzhi Liu: Ahybrid haptic guidance model for tank gunners in highprecision and high speed motor skill training

• Marco Roccetti , Gustavo Marfia & Cristian Bertuccioli:Day and night at the museum: intangible computerinterfaces for public exhibitions

TOMCCAP, Volume 10, Issue1s

Editor-in-Chief: Ralf SteinmetzURL: http://dl.acm.org/citation.cfm?id=2576908&picked=prox&CFID=433614180&CFTOKEN=32386073Published: January 2014sponsored by ACM SIGMM

Special issue of best papers of ACM MMSys 2013 andACM NOSSDAV 2013Guest editors: Roger Zimmermann, LaszloBöszörmenyi, Pål Halvorsen

• Roger Zimmermann, Laszlo Böszörmenyi, PålHalvorsen: Introduction to the special issue of bestpapers of ACM MMSys 2013 and ACM NOSSDAV2013

• Chun-Ying Huang, Kuan-Ta Chen, De-Yu Chen, Hwai-Jung Hsu, Cheng-Hsin Hsu: GamingAnywhere: Thefirst open source cloud gaming system

• Niall Murray, Yuansong Qiao, Brian Lee, Gabriel-MiroMuntean: User-profile-based perceived olfactory andvisual media synchronization

• Ahsan Arefin, Raoul Rivas, Klara Nahrstedt: OSM:Prioritized evolutionary QoS optimization for interactive3D teleimmersion

• Shanghong Zhao, Wei Tsang Ooi, Axel Carlier,Geraldine Morin, Vincent Charvillat: Bandwidthadaptation for 3D mesh preview streaming

• Håkon Kvale Stensland, Vamsidhar Reddy Gaddam,Marius Tennøe, Espen Helgedagsrud, Mikkel Næss,Henrik Kjus Alstad, Asgeir Mortensen, RagnarLangseth, Sigurd Ljødal, Østein Landsverk, CarstenGriwodz, Pål Halvorsen, Magnus Stenhaug, DagJohansen: Bagadus: An integrated real-time system forsoccer analytics

• Minseok Song, Yeongju Lee, Euiseok Kim: Savingdisk energy in video servers by combining caching andprefetching

TOMCCAP, Volume 10, Issue2

Editor-in-Chief: Ralf SteinmetzURL: http://dl.acm.org/citation.cfm?id=2579228&picked=prox&CFID=433614180&CFTOKEN=32386073

http://records.sigmm.ndlab.net/?eventjournal-toc=tomccap-volume-10-issue-1s

http://records.sigmm.ndlab.net/?eventjournal-toc=tomccap-volume-10-issue-1s

http://dl.acm.org/citation.cfm?id=2576908&picked=prox&CFID=433614180&CFTOKEN=32386073


http://dx.doi.org/10.1145/2557424

http://dx.doi.org/10.1145/2557424

http://dx.doi.org/10.1145/2557424

http://dx.doi.org/10.1145/2537855

http://dx.doi.org/10.1145/2537855

http://dx.doi.org/10.1145/2540994

http://dx.doi.org/10.1145/2540994

http://dx.doi.org/10.1145/2543899

http://dx.doi.org/10.1145/2543899

http://dx.doi.org/10.1145/2543899

http://dx.doi.org/10.1145/2537854

http://dx.doi.org/10.1145/2537854

http://dx.doi.org/10.1145/2541011

http://dx.doi.org/10.1145/2541011

http://dx.doi.org/10.1145/2537856

http://dx.doi.org/10.1145/2537856

http://dx.doi.org/10.1145/2537856

http://records.sigmm.ndlab.net/?eventjournal-toc=tomccap-volume-10-issue-2




.

Job Opportunities



Published: February 2014sponsored by ACM SIGMM

The Transactions on Multimedia Computing,Communication and Applications are the SIGMM’s ownTransactions. As a service to Records readers, weprovide direct links to ACM Digital Library for the papersof the latest TOMCCAP issue.

• Yunhua Deng, Rynson W. H. Lau: Dynamic loadbalancing in distributed virtual environments using heatdiffusion

• James She, Jon Crowcroft, Hao Fu, Flora Li:Convergence of interactive displays with smart mobiledevices for effective advertising: A survey

• Ekaterina Gonina, Gerald Friedland, Eric Battenberg,Penporn Koanantakool, Michael Driscoll, EvangelosGeorganas, Kurt Keutzer: Scalable multimedia contentanalysis on parallel platforms using python

• Surendar Chandra, John Boreczky, Lawrence A. Rowe:High performance many-to-many intranet screensharing with DisplayCast

• Ya-Lin Lee, Wen-Hsiang Tsai: A new data hidingmethod via revision history records on collaborativewriting platforms

• Jin Yuan, Yi-Liang Zhao, Huanbo Luan, Meng Wang,Tat-Seng Chua: Memory recall based video search:Finding videos you have seen before based on yourmemory

• Xianglong Liu, Yadong Mu, Bo Lang, Shih-Fu Chang:Mixed image-keyword query adaptive hashing overmultilabel images

TOMCCAP, Volume 10, Issue3

Editor-in-Chief: Ralf SteinmetzURL: http://dl.acm.org/citation.cfm?id=2602979&picked=prox&CFID=320571598&CFTOKEN=30265955Published: April 2014sponsored by ACM

• Ning Liu, Huajie Cui, S.-H. Gary Chan, Zhipeng Chen,Yirong Zhuang: Dissecting User Behaviors for aSimultaneous Live and VoD IPTV System

• Rossano Gaeta, Marco Grangetto, Lorenzo Bovio:DIP: Distributed Identification of Polluters in P2P LiveStreaming

• Mohammad Asharful Hoque, Matti Siekkinen, JukkaK. Nurminen, Sasu Tarkoma, Mika Aalto: SavingEnergy in Mobile Devices for On-Demand MultimediaStreaming -- A Cross-Layer Approach

• Feng Wang, Wan-Lei Zhao, Chong-Wah Ngo,Bernard Merialdo: A Hamming Embedding Kernel with

Informative Bag-of-Visual Words for Video SemanticIndexing

• Ying Yang, Ioannis Ivrissimtzis: Mesh DiscriminativeFeatures for 3D Steganalysis

• Abdelwahab Hamam, Abdulmotaleb El Saddik, JihadAlja'am: A Quality of Experience Model for HapticVirtual Environments

• Marco Botta, Davide Cavagnino, Victor Pomponiu:Protecting the Content Integrity of Digital Imagery withFidelity Preservation: An Improved Version

• Da Luo, Weiqi Luo, Rui Yang, Jiwu Huang: IdentifyingCompression History of Wave Audio and ItsApplications

Job Opportunities

PhD in IP-based mediacontent delivery

Swinburne University of Technology and Netflix Inc.are pleased to announce a newly funded full-time PhDposition at Swinburne’s Centre for Advanced InternetArchitectures (CAIA) .

Research program:The research program will be focussed on technologiesand techniques associated with high performance,IP-based content delivery. Topics of interest includeoperating system and network stack design, congestioncontrol, transport protocols, algorithms for buffermanagement, adaptive streaming, and related areas.

Candidate attributes:We are looking for an academically strong applicantwith a track record of hands-on experience andexperimentation with network protocols, networkedservices and open-source operating systems such asFreeBSD and/or Linux. Your academic backgroundwill ideally include a First-class Honours bachelorsdegree (4-year minimum) in Electronic Engineering,Telecommunications Engineering, Computer Science orequivalent.

You may have just recently finished your undergraduatestudies, or you graduated awhile ago. In either caseyou are excited by the possibility of returning to full-timestudy leading to a PhD.

Deadline:Applications received by 5pm April 27th 2014(Melbourne time) will be reviewed and evaluated byrepresentatives of CAIA and Netflix Inc. Applicationsreceived after this time may also be considered ifcircumstances allow.

http://dx.doi.org/10.1145/2499906

http://dx.doi.org/10.1145/2499906

http://dx.doi.org/10.1145/2499906

http://dx.doi.org/10.1145/2557450

http://dx.doi.org/10.1145/2557450

http://dx.doi.org/10.1145/2517151

http://dx.doi.org/10.1145/2517151

http://dx.doi.org/10.1145/2534328

http://dx.doi.org/10.1145/2534328

http://dx.doi.org/10.1145/2534408

http://dx.doi.org/10.1145/2534408

http://dx.doi.org/10.1145/2534408

http://dx.doi.org/10.1145/2534409

http://dx.doi.org/10.1145/2534409

http://dx.doi.org/10.1145/2534409

http://dx.doi.org/10.1145/2540990

http://dx.doi.org/10.1145/2540990





http://dx.doi.org/10.1145/2568194

http://dx.doi.org/10.1145/2568194

http://dx.doi.org/10.1145/2568223

http://dx.doi.org/10.1145/2568223

http://dx.doi.org/10.1145/2556942

http://dx.doi.org/10.1145/2556942

http://dx.doi.org/10.1145/2556942

http://dx.doi.org/10.1145/2535938

http://dx.doi.org/10.1145/2535938

http://dx.doi.org/10.1145/2535938

http://dx.doi.org/10.1145/2535555

http://dx.doi.org/10.1145/2535555

http://dx.doi.org/10.1145/2540991

http://dx.doi.org/10.1145/2540991

http://dx.doi.org/10.1145/2568224

http://dx.doi.org/10.1145/2568224

http://dx.doi.org/10.1145/2575978

http://dx.doi.org/10.1145/2575978

http://dx.doi.org/10.1145/2575978

http://records.sigmm.ndlab.net/?job-opp=phd-in-ip-based-media-content-delivery

http://records.sigmm.ndlab.net/?job-opp=phd-in-ip-based-media-content-delivery

.

Job Opportunities



For further information please see http://caia.swin.edu.au/scholarships/netflix-phd-2014.html

Employer: Swinburne University of Technology / NetflixInc.Expiration date: Sunday, April 27, 2014More information date: http://caia.swin.edu.au/scholarships/netflix-phd-2014.html

PhD position in ComputerScience

Multimodal sensing for Ambient Assisted Living

The Distributed Multimedia Systems (DMMS) researchgroup is aiming to improve future networks andmiddleware for advanced multimedia applications.Multimedia does not only mean audio and video, but alsosensor data of any kind. We investigate context-awareand self-adapting solutions for transmission, distributionand management of (multimedia) data.

We are aiming to enforce our current research inthe area of multi-modal sensor systems for smartenvironments and especially interdisciplinary researchfor Ambient Assisted Living and ubiquitous home care.

Employer: University of Oslo, NorwayExpiration date: Sunday, April 20, 2014More information date: http://uio.easycruit.com/vacancy/1149321/64290?iso=no

PhD position in computerscience: Model-checking formalware detection

PhD position in LIAFA==================

Contact: Tayssir TOUILI ([email protected])

A PhD position is available in the “Verification” team inLIAFA, Paris.

The topic of the thesis is the development of neworiginal model-checking and static analysis techniquesfor malware detection. Indeed, the number of malwaresis growing extraordinarily fast. Therefore, it is importantto have efficient malware detectors. To identify viruses,existing antivirus systems use either code emulation orsignature (pattern) detection. These techniques havesome limitations. Indeed, emulation based techniquescan only check the program’s behavior in a limited timeinterval, whereas signature based systems are easy to

get around. To sidestep these limitations, instead ofexecuting the program or making a syntactic check overit, virus detectors need to use analysis techniques thatcheck the behavior (not the syntax) of the program in astatic way, i.e. without executing it. Towards this aim, wepropose in this thesis to develop new model-checkingand static analysis techniques for virus detection.

How to apply:==========The positions are available immediately. Candidatesmust have a master in computer science.The candidate must send a CV, university grades,recommendation letters, and a motivation letter toTayssir TOUILI ([email protected]

Employer: CNRS, FranceExpiration date: Monday, March 31, 2014More information date: mailto:[email protected]

PhD position in computerscience: MultimediaNetworking

A PhD position is available at the Expertise Centre forDigital Media, Hasselt University.

The subject of the research is multimedianetworking. Current research within the groupincludes networked virtual environments & on-line gaming (architectural design and scalabilityassessment), adaptive multimedia delivery (streamingof non-traditional media types), constrained networkenvironments (mobile and ad-hoc network applicationsand protocols) and high-performance web technology(replacing dedicated applications by web-basedalternatives). The specific PhD topic will be determinedin consultation with the selected candidate.

Deadline for application is Monday, April 21, 2014.

More information and application through http://www.uhasselt.be/vacancies_detail?taal=04&vacid=672

Employer: Hasselt University, BelgiumExpiration date: Tuesday, April 22, 2014More information date: http://www.uhasselt.be/vacancies_detail?taal=04&vacid=672

PhD position in computerscience: Software verification

PhD position in LIAFA

http://records.sigmm.ndlab.net/?job-opp=phd-position-in-computer-science

http://records.sigmm.ndlab.net/?job-opp=phd-position-in-computer-science

http://records.sigmm.ndlab.net/?job-opp=phd-position-in-computer-science-model-checking-for-malware-detection



http://records.sigmm.ndlab.net/?job-opp=phd-position-in-computer-science-multimedia-networking



http://records.sigmm.ndlab.net/?job-opp=phd-position-in-computer-science-software-verification

http://records.sigmm.ndlab.net/?job-opp=phd-position-in-computer-science-software-verification

.

Calls for Contribution



==================

Contact: Tayssir TOUILI ([email protected])

A PhD position is available in the “Verification” team inLIAFA, Paris.

The subject of the thesis is about concurrent programsverification. The PhD student is expected to investigateand develop novel techniques, algorithms and tools forthe analysis of software.

Indeed, nowadays, software is everywhere: intelecommunication, in navigation, in nuclear plants,etc. The tasks that software deal with are becomingmore and more complex and critical, in the sensethat any small error can cause huge human and/oreconomical damages. Therefore, it is crucial to besure that a software does not contain any error beforeusing it. Programmers need then to have rigorousformal mathematical techniques that allow to verify andcheck their programs. Unfortunately, programs presentseveral complex features that make their analysisvery complex: concurrency, synchronisation, recursion,procedure calls, pointers, manipulation of integer andreal variables, etc. Thus, the objective of this thesis isto develop new techniques for software model-checkingthat can deal with all these complex features.

How to apply:==========The positions are available immediately. Candidatesmust have a master in computer science.The candidate must send a CV, university grades,recommendation letters, and a motivation letter toTayssir TOUILI ([email protected])

Employer: CNRS, FranceExpiration date: Monday, March 31, 2014More information date: mailto:[email protected]

PostDoc position: MultimediaCommunication

The Multimedia Communication (MMC) group atKlagenfurt University, Austria, is offering a full,three-year PostDoc position (available now) in abasic international research project called CONCERT(“A Context-Adaptive Content Ecosystem UnderUncertainty”). Important facts about the project areavailable at: http://www.concert-project.org/. We seekcandidates with strong expertise in one or several of thefollowing areas: Multimedia Communication, MachineLearning, Multi-Agent Systems, Uncertainty in Artificial

Intelligence (Probabilistic Models, Bayesian Networks,Game Theory). Applications should be sent to Prof.Hermann Hellwagner ([email protected]).

Employer: Klagenfurt University, AustriaExpiration date: Wednesday, April 30, 2014More information date: https://blog.tewi.uni-klu.ac.at/postdoc-position/

Researcher, MultimediaSearch and Mining

Walk the halls of Microsoft Research labs and you’llfind some of the world’s finest computer scientists,social scientists, mathematicians, physicists, biologists,economists, communication scientists, and engineers.We’re charged with a job that constantly evolves:advancing the state of the art in computer science. Giventhe freedom to pursue our passions, we look for gapsin current technologies and dedicate ourselves to fillingthem. As diverse as our research and accomplishmentsmay be, we share the motivation to see our ideas andinnovations tackle the world’s toughest challenges andimprove the lives of people everywhere.

Employer: Microsoft Research, Beijing, ChinaExpiration date: Monday, September 1, 2014More information date: http://research.microsoft.com/en-us/jobs/fulltime/researcher.aspx


CFPs: Sponsored by ACMSIGMM

3rd BAMMF

3rd Bay Area Multimedia Forum

Submission deadline: 01. January 1972Location: George E. Pake Auditorium, 3333 Coyote HillRoad, Palo Alto, CA 94304Dates: 27. May 2014 -27. May 2014More information: http://www.bammf.orgSponsored by ACM SIGMM and IEEE

3rd BAMMF Tech Forum on May 27th at PARCAuditorium www.bammf.org Agenda: 1:00pm-1:30pmAttendee Networking 1:30pm-2:30pm From Quality ofService to Quality of Experiences in 3D Tele-immersiveEnvironments by Klara Nahrstedt 2:30pm-3:00pmTelemedicine for Iraq Kurdistan, Shell Nigeria, and 3M

http://records.sigmm.ndlab.net/?job-opp=postdoc-position-multimedia-communication

http://records.sigmm.ndlab.net/?job-opp=postdoc-position-multimedia-communication

http://records.sigmm.ndlab.net/?job-opp=researcher-multimedia-search-and-mining

http://records.sigmm.ndlab.net/?job-opp=researcher-multimedia-search-and-mining

http://www.bammf.org

.




Americans by Milton Chen 3:00pm-3:30pm NetworkingBreak 3:30pm-4:30pm Current and … Read more →

ACM MM 2014

The 22nd ACM International Conferenceon Multimedia

Submission deadline: 31. March 2014Location: Orlando, FloridaDates: 03. November 2014 -07. November 2014More information: http://www.acmmm.org/2014/Sponsored by ACM SIGMM

ACM Multimedia is the worldwide premier conferenceand a key world event to display scientific achievementsand innovative industrial products in the multimediafield. At ACMMM 2014, we will celebrate its 22nditeration with an extensive program consisting oftechnical sessions covering all aspects of themultimedia field, tutorials, panels, … Read more →

CrowdMM @ ACM MM 2014

International ACM Workshop onCrowdsourcing for Multimedia

Submission deadline: 30. June 2014Location: Orlando, FLDates: 07. November 2014 -07. November 2014More information: http://www.crowdmm.org/Sponsored by ACM SIGMM

CrowdMM 2014 solicits novel contributions tomultimedia research that make use of humanintelligence, but also take advantage of humanplurality. We encourage theoretical, experimental,and methodological developments advancing state-of-the-art knowledge of crowdsourcing techniques formultimedia research. We encourage submission thatemploy crowdsourcing, wisdom of the crowd, gameswith a … Read more →

Demos @ ACM MM 2014

Demos at ACM Multimedia 2014

Submission deadline: 19. May 2014Location: Orlando, FL, USADates: 03. November 2014 -07. November 2014More information: http://acmmm.org/2014/call_technical_demos.htmlSponsored by ACM SIGMM

ACM Multimedia will provide demonstration sessions.Demos are intended as real, practical, and interactive

proof of the presenters’ research ideas and scientificor engineering contributions, with the goal of providingmultimedia researchers and practitioners with theopportunity to discuss working multimedia systems,applications, prototypes, or proof-of-concepts. Such asetting allows … Read more →

ICIMCS 2014

ACM International Conference on InternetMultimedia Computing and Service

Submission deadline: 15. April 2014Location: Xiamen, ChinaDates: 10. July 2014 -12. July 2014More information: http://icimcs2014.xmu.edu.cn/Sponsored by ACM SIGMM

The submission deadline is extended to April 15, 2014(final extension). The 6th International Conference onInternet Multimedia Computing and Service (ICIMCS)will be held from July 10−12, 2014 at Xiamen, Fujian,China. The three-day conference will include invitedkeynotes, oral and poster presentations. ICIMCS2014will serve as an international … Read more →

Open Source @ ACM MM 2014

Open Source Software Competition atACM Multimedia 2014

Submission deadline: 19. May 2014Location: Orlando, FL, USADates: 03. November 2014 -07. November 2014More information: http://acmmm.org/2014/call_open_source.htmlSponsored by ACM SIGMM

The ACM Multimedia Open-Source SoftwareCompetition is designed to promote the contribution offreely available resources such as codecs, middleware,frameworks, toolkits, libraries, applications, and othermultimedia software. These resources advance the fieldby providing a common set of tools for building andimproving multimedia research prototypes. The use of… Read more →

Short Paper Deadline @ ACMMM2014

22nd ACM International Conference onMultimedia

Submission deadline: 14. April 2014

http://records.sigmm.ndlab.net/?cfp=bammf-2

http://www.acmmm.org/2014/

http://records.sigmm.ndlab.net/?cfp=acmmm-2014

http://www.crowdmm.org/

http://records.sigmm.ndlab.net/?cfp=crowdmm-acm-mm-2014

http://acmmm.org/2014/call_technical_demos.html

http://acmmm.org/2014/call_technical_demos.html

http://records.sigmm.ndlab.net/?cfp=demos-acm-mm-2014

http://icimcs2014.xmu.edu.cn/

http://records.sigmm.ndlab.net/?cfp=icimcs-2014-2

http://acmmm.org/2014/call_open_source.html

http://acmmm.org/2014/call_open_source.html

http://records.sigmm.ndlab.net/?cfp=open-source-acm-mm-2014

.




Location: Orlando, FloridaDates: 03. November 2014 -07. November 2014More information: http://acmmm.org/2014/call_full_short_papers.htmlSponsored by ACM SIGMM

ACM Multimedia is the worldwide premier conferenceand a key world event to display scientific achievementsand innovative industrial products in the multimediafield. ACMMM will have an extensive programconsisting of technical sessions covering all aspectsof the multimedia field, tutorials, panels, exhibits,demonstrations and workshops, competitions ofresearch … Read more →

CFPs: Sponsored by ACM(any SIG)

ACM ICMI 2014

ACM International Conference onMultimodal Interaction

Submission deadline: 09. May 2014Location: Istanbul - TurkeyDates: 12. November 2014 -16. November 2014More information: http://icmi.acm.org/2014/Sponsored by ACM

The International Conference on Multimodal Interaction,ICMI 2014, will take place at Bogazici University,Istanbul (Turkey), November 12-16th, 2014. ICMI isthe premier international forum for multidisciplinaryresearch on multimodal human-human and human-computer interaction, interfaces, and systemdevelopment. The conference focuses on theoreticaland empirical foundations, component technologies,and combined … Read more →

ACM SAP 2014

Symposium on Applied Perception

Submission deadline: 07. April 2014Location: Vancouver CanadaDates: 08. August 2014 -09. August 2014More information: http://sap2014.cs.mtu.edu/Sponsored by ACM

The ACM Symposium on Applied Perception (ACMSAP), aims to advance and promote research thatcrosses the boundaries between perception anddisciplines such as graphics, visualization, vision,haptics and acoustics. These fields can benefit from

the exchange of ideas. The scope of the conferenceincludes applications and algorithms in any … Readmore →

ACM TIIS

ACM Transactions on InteractiveIntelligent Systems

Behavior Understanding for Arts andEntertainment

Submission deadline: 26. March 2014Special issueMore information: http://tiis.acm.org/special-issues.html#si-call-buaeSponsored by ACM

This special issue aims to encourage and publishresearch about the challenges and opportunitiesassociated with human behavior understanding inarts and entertainment. The subject of the behaviorunderstanding may be either a creator, such as a visualartist or a performer; or a person who engages with a(possibly … Read more →

MAED @ ACMMM 2014

The 3rd ACM International Workshop onMultimedia Analysis for Ecological Data

Submission deadline: 30. June 2014Location: Orlando, FloridaDates: 07. November 2014 -07. November 2014More information: http://maed2014.dieei.unict.itSponsored by ACM

The 3rd ACM International Workshop on MultimediaAnalysis for Ecological Data features two tracks: –Regular Track aiming to present and report on themost recent methods for the management, processing,interpretation, and visualization of multimedia datarecorded for monitoring ecological systems, withparticular attention to the understanding of the … Readmore →

SMI @ ACM ICMI 2014

3rd Workshop on Smart MaterialInterfaces

Submission deadline: 15. July 2014Location: Istanbul, Turkey

http://acmmm.org/2014/call_full_short_papers.html

http://acmmm.org/2014/call_full_short_papers.html

http://records.sigmm.ndlab.net/?cfp=short-paper-deadline-acmmm-2014

http://icmi.acm.org/2014/

http://records.sigmm.ndlab.net/?cfp=acm-icmi-2014

http://sap2014.cs.mtu.edu/

http://records.sigmm.ndlab.net/?cfp=acm-sap-2014

http://records.sigmm.ndlab.net/?cfp=acm-sap-2014

http://tiis.acm.org/special-issues.html#si-call-buae

http://tiis.acm.org/special-issues.html#si-call-buae

http://records.sigmm.ndlab.net/?cfp=acm-tiis

http://maed2014.dieei.unict.it

http://records.sigmm.ndlab.net/?cfp=maed-acmmm-2014

http://records.sigmm.ndlab.net/?cfp=maed-acmmm-2014

.




Dates: 16. November 2014 -16. November 2014More information: http://smartmaterialinterfaces.wordpress.com/Sponsored by ACM

The objective of this workshop is to draw attention tothe emerging field of smart material interfaces whichspans the areas of design, engineering and architecture.These novel composites are generally referred to asmaterials that are capable of sensing the environmentand actively responding to by changing their physical …Read more →

CFPs: Sponsored by IEEE(any TC)

HPCC 2014

International Conference on HighPerformance Computing andCommunications

Submission deadline: 28. April 2014Location: ParisDates: 20. August 2014 -22. August 2014More information: http://www.computational-science.org/HPCC2014Sponsored by IEEE

The HPCC-2014 conference is the 16th IEEEInternational Conference on High Performance andCommunications. It will provide a forum for engineersand scientists in academia, industry, and governmentto address the resulting profound challenges and topresent and discuss their new ideas, research results,applications and experience on all aspects … Readmore →

IEEE CIT 2014

The 14th IEEE International Conference onComputer and Information Technology

Submission deadline: 01. April 2014Location: Xiían, Shaanxi, ChinaDates: 11. September 2014 -13. September 2014More information: http://meeting.xidian.edu.cn/conference/cit2014/Sponsored by IEEE

CIT has become a major platform for researchers andindustry practitioners from different fields of computerand information technology. Each year, CIT attendeesappreciate and benefit from multidisciplinary exchanges

in computer and information technology. In previousyears, CIT has attracted many high quality researchpapers spanning over the various aspects … Read more

→

IEEE CSS 2014

The 6th International Symposium onCyberspace Safety and Security

Submission deadline: 28. April 2014Location: Paris, FranceDates: 20. August 2014 -22. August 2014More information: http://www.computational-science.org/CSS2014Sponsored by IEEE

The CSS-2014 provides a leading edge forum tofoster interaction between researchers and developerswith the cyberspace safety and security communities,and to give attendees an opportunity to network withexperts in this area. It focusses on Cyberspace Safetyand Security, such as authentication, access control,availability, integrity, privacy, confidentiality, … Readmore →

IEEE ICMLA 2014

International Conference on MachineLearning and Applications

Submission deadline: 06. July 2014Location: Detroit, MI, USADates: 03. December 2014 -06. December 2014More information: http://www.icmla-conference.org/icmla14/Sponsored by IEEE

The aim of the 13th International Conference onMachine Learning and Applications is to bring togetherresearchers working in the areas of machine learningand applications. Recent emergence for big dataprocessing particularly brings the urgent need formachine learning to be able to address the challengesraised from real-time … Read more →

IEEE ISM 2014

IEEE International Symposium onMultimedia

Submission deadline: 18. July 2014Location: Taichung, TaiwanDates: 10. December 2014 -12. December 2014More information: http://ism2014.asia.edu.tw/

http://smartmaterialinterfaces.wordpress.com/

http://smartmaterialinterfaces.wordpress.com/

http://records.sigmm.ndlab.net/?cfp=smi-acm-icmi-2014

http://www.computational-science.org/HPCC2014

http://www.computational-science.org/HPCC2014

http://records.sigmm.ndlab.net/?cfp=hpcc-2014

http://records.sigmm.ndlab.net/?cfp=hpcc-2014

http://meeting.xidian.edu.cn/conference/cit2014/

http://meeting.xidian.edu.cn/conference/cit2014/

http://records.sigmm.ndlab.net/?cfp=ieee-cit-2014

http://records.sigmm.ndlab.net/?cfp=ieee-cit-2014

http://www.computational-science.org/CSS2014

http://www.computational-science.org/CSS2014

http://records.sigmm.ndlab.net/?cfp=ieee-css-2014

http://records.sigmm.ndlab.net/?cfp=ieee-css-2014

http://www.icmla-conference.org/icmla14/

http://www.icmla-conference.org/icmla14/

http://records.sigmm.ndlab.net/?cfp=ieee-icmla-2014-2

http://ism2014.asia.edu.tw/

.




Sponsored by IEEE

The IEEE International Symposium on Multimedia(ISM2014) is an international forum for researchers toexchange information regarding advances in the state ofthe art and practice of multimedia computing, as well asto identify the emerging research topics and define thefuture of multimedia computing. The technical programof ISM2014 … Read more →

IEEE ISMAR 2014

International Symposium on Mixed andAugmented Reality

Submission deadline: 25. March 2014Location: Munich, GermanyDates: 10. September 2014 -12. September 2014More information: http://ismar.vgtc.org/Sponsored by IEEE

Augmented Reality (AR) and Mixed Reality (MR) meltthe barriers between virtual media, the physical worldand our imagination by enriching our ability to interactwith all three. New applications in diverse areas suchas Engineering, Entertainment, Arts, Education Mediaand Humanities push the boundaries of science andtechnology. As … Read more →

IEEE VCIP 2014

IEEE Visual Communications and ImageProcessing 2014

Submission deadline: 05. May 2014Location: Valletta, MaltaDates: 07. December 2014 -10. December 2014More information: http://www.um.edu.mt/events/vcip2014/Sponsored by IEEE

Since 1986, Visual Communications and ImageProcessing (VCIP) has served as a premier forumin SPIE for the exchange of fundamental researchresults and technological advances in the field ofvisual communications and image processing. The 2014edition will be the fourth time that VCIP will be held underthe … Read more →

ISMAR 2014

International Symposium on Mixed andAugmented Reality

Submission deadline: 25. March 2014

Location: Munich, GermanyDates: 10. September 2014 -12. September 2014More information: http://ismar.vgtc.org/Sponsored by IEEE

Augmented Reality (AR) and Mixed Reality (MR) meltthe barriers between virtual media, the physical worldand our imagination by enriching our ability to interactwith all three. New applications in diverse areas suchas Engineering, Entertainment, Arts, Education Mediaand Humanities push the boundaries of science andtechnology. As … Read more →

MAC @ ICME2014

1st International Workshop on MultimediaAffective Computing In conjunction withICME2014

Submission deadline: 23. March 2014Location: Chengdu, ChinaDates: 14. July 2014 -18. July 2014More information: http://mac2014.cse.sc.eduSponsored by IEEE

This workshop is to increase the attention of multimediasociety on human-centered multimedia computing,where sensing human affect and emotion plays anessential role; present the state-of-the-art researchin the related areas; and discuss the challengesand potential opportunities in multimedia affectivecomputing. We welcome research papers focusing on,but … Read more →

VidEv 2014

The 3rd IEEE WoWMoM Workshop onVideo Everywhere (co-located with TheIEEE International Symposium on aWorld of Wireless, Mobile and MultimediaNetworks, WoWMoM 2014)

Submission deadline: 27. March 2014Location: June 16, 2014 - Sydney, Australia (immediatelyafter the IEEE ICC 2014)Dates: 16. June 2014 -16. June 2014More information: http://www.videv2014.tuc.gr/Sponsored by IEEE

This highly selective workshop is devoted to coveringall aspects of current work on mobile video and toproviding a forum for researchers and practitioners topresent and discuss their most recent contributions inthe field. Accepted papers will appear in the symposium

http://records.sigmm.ndlab.net/?cfp=ieee-ism-2014

http://ismar.vgtc.org/

http://records.sigmm.ndlab.net/?cfp=ieee-ismar-2014

http://www.um.edu.mt/events/vcip2014/

http://records.sigmm.ndlab.net/?cfp=ieee-vcip-2014

http://ismar.vgtc.org/

http://records.sigmm.ndlab.net/?cfp=ismar-2014

http://mac2014.cse.sc.edu

http://records.sigmm.ndlab.net/?cfp=mac-icme2014

http://www.videv2014.tuc.gr/

.




proceedings published by IEEE. At least one … Readmore →

Workshops @ ICME 2014

IEEE International Conference onMultimedia and Expo 2014 Workshops

Submission deadline: 23. March 2014Location: Chengdu, ChinaDates: 14. July 2014 -18. July 2014More information: http://www.icme2014.org/workshopsSponsored by IEEE

With around 1000 submissions and 500 participantseach year, the IEEE International Conference onMultimedia & Expo (ICME) has been the flagshipmultimedia conference sponsored by four IEEEsocieties since 2000. It serves as a forum to promotethe exchange of the latest advances in multimediatechnologies, systems, and applications … Read more

→

CFPs: Not ACM-/IEEE-sponsored

3DTV-CON 2014

3DTV Conference 2014

Submission deadline: 28. March 2014Location: Budapest, HungaryDates: 02. July 2014 -04. July 2014More information: http://3dtv-con.org/

3DTV-CON 2014

3DTV Conference 2014

Submission deadline: 28. March 2014Location: Budapest, HungaryDates: 02. July 2014 -04. July 2014More information: http://3dtv-con.org/

ACE 2014

11th Advances in Computer EntertainmentTechnology Conference

Submission deadline: 12. May 2014Location: Funchal, Madeira

Dates: 11. November 2014 -14. February 2014More information: http://www.ace2014.info

ComSec 2014

International Conference on ComputerSecurity and Digital Investigation(ComSec2014)

Submission deadline: 18. February 2014Location: Asia Pacific University of Technology andInnovation (APU) Kuala Lumpur, MalaysiaDates: 18. March 2014 -20. March 2014More information: http://sdiwc.net/conferences/2014/comsec2014/

CyberForensics 2014

The International Conference on Cyber-Crime Investigation and Digital Forensics(CyberForensics2014)

Submission deadline: 17. October 2014Location: Asia Pacific University of Technology andInnovation (APU) Kuala Lumpur, MalaysiaDates: 17. November 2014 -19. November 2014More information: http://sdiwc.net/conferences/2014/cyberforensics2014/

DINWC 2014

The Second International Conferenceon Digital Information, Networking, andWireless Communications (DINWC2014)

Submission deadline: 14. September 2014Location: Bhagwant Institute of Technology, Ghaziabad,IndiaDates: 14. October 2014 -16. October 2014More information: http://sdiwc.net/conferences/dinwc14/

DIPECC 2014

The Second International Conferenceon Digital Information Processing, E-Business and Cloud Computing (DIPECC2014)

Submission deadline: 10. March 2014Location: Islamic Azad University, Dubai, UAEDates: 09. April 2014 -11. April 2014

http://records.sigmm.ndlab.net/?cfp=videv-2014

http://records.sigmm.ndlab.net/?cfp=videv-2014

http://www.icme2014.org/workshops

http://records.sigmm.ndlab.net/?cfp=workshops-icme-2014

http://records.sigmm.ndlab.net/?cfp=workshops-icme-2014

http://3dtv-con.org/

http://3dtv-con.org/

http://www.ace2014.info

http://sdiwc.net/conferences/2014/comsec2014/

http://sdiwc.net/conferences/2014/comsec2014/

http://sdiwc.net/conferences/2014/cyberforensics2014/

http://sdiwc.net/conferences/2014/cyberforensics2014/

http://sdiwc.net/conferences/dinwc14/

.




More information: http://sdiwc.net/conferences/2014/dipecc2014/

DIPECC 2014


Submission deadline: 10. March 2014Location: Knowlegde Village, Dubai, UAEDates: 09. April 2014 -11. April 2014More information: http://sdiwc.net/conferences/2014/dipecc2014/

DIPECC 2014


Submission deadline: 20. March 2014Location: Knowlegde Village, Dubai, UAEDates: 09. April 2014 -11. April 2014More information: http://sdiwc.net/conferences/2014/dipecc2014/

ES BID 2014

Int. workshop on Enabling Science fromBig Image Data

Submission deadline: 15. March 2014Location: Stanford, CA, USADates: 27. May 2014 -27. May 2014More information: http://www.scienceengineering.org/ase/conference/2014/bigdata/sanjose/website/workshop-5/

ESAA 2014

International Workshop on EnhancingParallel Scientific Applications withAccelerated HPC (ESAA 2014)

Submission deadline: 25. April 2014Location: Chicada, USADates: 26. May 2014 -30. May 2014More information: http://www.arcos.inf.uc3m.es/~esaa2014/

HBU @ ECCV 2014

5th International Workshop on HumanBehavior Understanding

Submission deadline: 13. June 2014Location: Zurich, SwitzerlandDates: 12. September 2014 -12. September 2014More information: http://www.cmpe.boun.edu.tr/hbu/2014/

HBU @ ECCV 2014

5th International Workshop on HumanBehavior Understanding

Submission deadline: 13. June 2014Location: Zurich, SwitzerlandDates: 12. September 2014 -12. September 2014More information: http://www.cmpe.boun.edu.tr/hbu/2014/

ICEEE @ WCIT 2014

The Third International Conference on E-Learning and E-Technologies in Education

Submission deadline: 25. February 2014Location: Kuala Lumpur, MalaysiaDates: 18. March 2014 -20. March 2014More information: http://sdiwc.net/conferences/2014/iceee2014/

ICIMCS 2014

The 6th International Conference onInternet Multimedia Computing andService

Submission deadline: 01. April 2014Location: Xiamen, ChinaDates: 10. July 2014 -12. July 2014More information: http://icimcs2014.xmu.edu.cnIn cooperation with ACM SIGMM

ICIST 2014

International Conference on Informationand Software Technologies

Submission deadline: 28. April 2014Location: Druskininkai, LithuaniaDates: 09. October 2014 -10. October 2014More information: http://icist.if.ktu.lt

http://sdiwc.net/conferences/2014/dipecc2014/






http://www.scienceengineering.org/ase/conference/2014/bigdata/sanjose/website/workshop-5/

http://www.scienceengineering.org/ase/conference/2014/bigdata/sanjose/website/workshop-5/

http://www.arcos.inf.uc3m.es/~esaa2014/

http://www.arcos.inf.uc3m.es/~esaa2014/

http://www.cmpe.boun.edu.tr/hbu/2014/

http://www.cmpe.boun.edu.tr/hbu/2014/

http://sdiwc.net/conferences/2014/iceee2014/

http://sdiwc.net/conferences/2014/iceee2014/

http://icimcs2014.xmu.edu.cn

http://icist.if.ktu.lt

.




ICVSS 2014

nternational Computer Vision SummerSchool

Submission deadline: 31. March 2014Location: SIcily, ItalyDates: 14. July 2014 -19. July 2014More information: http://www.dmi.unict.it/icvss

ISDF 2014

The International Conference inInformation, Security, and DigitalForensics (ISDF2014)

Submission deadline: 12. October 2014Location: Ghaziabad, Uttar Pradesh, IndiaDates: 14. October 2014 -16. October 2014More information: http://sdiwc.net/conferences/dinwc14/

MCSS 2014

7th conference on MultimediaCommunications, Services and Security

Submission deadline: 12. February 2014Location: Krakow, PolandDates: 11. June 2014 -12. June 2014More information: http://mcss2014.indect-project.eu/

MMAP @ FedCSIS 2014

7th International Symposium onMultimedia Applications and Processing(MMAP'14)

Submission deadline: 11. April 2014Location: Warsaw, PolandDates: 07. September 2014 -10. September 2014More information: http://fedcsis.org/mmapIn cooperation with ACM

MMSJ

Springer Multimedia Systems Journal

How Can Multimedia Help Ecology

Submission deadline: 15. March 2014Special issueMore information: htttp://i3s-lab-research.dieei.unict.it/cfp/CfP_MMSJ_ecology.pdf

MT4BD 2014

Workshop on New Methods and Tools forBig Data

Submission deadline: 22. April 2014Location: Island of Rhodes, GreeceDates: 19. September 2014 -21. September 2014More information: http://mt4bd2014.ceid.upatras.gr/

PCM 2014

Pacific-Rim Conference on Multimedia(PCM) 2014

Submission deadline: 31. May 2014Location: Kuching, Sarawak, MalaysiaDates: 01. December 2014 -04. December 2014More information: http://conference.cs.cityu.edu.hk/pcm2014/

PR

Elsevier Journal of Pattern Recognition

Discriminative Feature Learning from BigData for Visual Recognition

Submission deadline: 10. August 2014Special issueMore information: http://www.umiacs.umd.edu/~zhuolin/PRSI_DFL.html

SLAM 2014

International Workshop on Speech,Language and Audio in Multimedia

Submission deadline: 12. June 2014Location: Penang, MalaysiaDates: 11. September 2014 -12. September 2014More information: http://language.cs.usm.my/SLAM2014

VidEv 2014

The 3rd IEEE WoWMoM Workshop onVideo Everywhere (co-located with TheIEEE International Symposium on aWorld of Wireless, Mobile and MultimediaNetworks, WoWMoM 2014)

Submission deadline: 27. March 2014

http://www.dmi.unict.it/icvss

http://sdiwc.net/conferences/dinwc14/

http://mcss2014.indect-project.eu/

http://fedcsis.org/mmap

http://mt4bd2014.ceid.upatras.gr/

http://conference.cs.cityu.edu.hk/pcm2014/

http://conference.cs.cityu.edu.hk/pcm2014/

http://www.umiacs.umd.edu/~zhuolin/PRSI_DFL.html

http://www.umiacs.umd.edu/~zhuolin/PRSI_DFL.html

http://language.cs.usm.my/SLAM2014

.

Back Matter



Location: June 16, 2014 - Sydney, Australia (immediatelyafter the IEEE ICC 2014)Dates: 16. June 2014 -16. June 2014More information: http://www.videv2014.tuc.gr/

WCCS 2014

2nd World Conference on ComplexSystems

Submission deadline: 15. May 2014Location: Agadir-MoroccoDates: 10. November 2014 -13. November 2014More information: http://www.wccs14.org/

Back Matter

Notice to ContributingAuthors to SIG Newsletters

By submitting your article for distribution in this SpecialInterest Group publication, you hereby grant to ACM thefollowing non-exclusive, perpetual, worldwide rights:

• to publish in print on condition of acceptance by theeditor

• to digitize and post your article in the electronicversion of this publication

• to include the article in the ACM Digital Library and inany Digital Library related services

• to allow users to copy and distribute the article fornoncommercial, educational or research purposes

However, as a contributing author, you retain copyrightto your article and ACM will refer requests forrepublication directly to you.

Impressum

Editor-in-Chief

Carsten Griwodz, Simula Research Laboratory

Editors

Stephan Kopf, University of MannheimViktor Wendel, Darmstadt University of TechnologyLei Zhang, Microsoft Research AsiaPradeep Atrey, University of WinnipegChristian Timmerer, Klagenfurt UniversityPablo Cesar, CWIMathias Lux, Klagenfurt University

Herman Engelbrecht, Stellenbosch University

http://www.videv2014.tuc.gr/

http://www.wccs14.org/

Table of Contentsheim.ifi.uio.no/griff/SIGMM-records-1401.pdfCommittee Draft for Green Metadata...

Documents

Transcript of Table of Contentsheim.ifi.uio.no/griff/SIGMM-records-1401.pdfCommittee Draft for Green Metadata...