Thank you to our Supporters & Sponsors Technical Program(PSIVT2017).pdf · hao Sun, entral hina ......

Thank you to our Supporters & Sponsors

The 8th Pacific Rim Symposium on Image and Video Technology

20 – 24 November 2017 I Wuhan, China

2

Contents

Program at a Glance .......................................................................................................................... 3

Welcome ........................................................................................................................................... 4

PSIVT 2017 Steering Committee ....................................................................................................... 6

PSIVT 2017 Organizing Committee ................................................................................................... 7

Maps ................................................................................................................................................. 8

General Information .......................................................................................................................... 9

Banquet ........................................................................................................................................... 11

Survivors Party ................................................................................................................................ 11

Wuhan Visitor Information ............................................................................................................. 12

Keynote Speakers ............................................................................................................................ 14

Program ........................................................................................................................................... 18


3

Program at a Glance Monday, November 20: Registration, day 1 (14:00-18:00, venue: Guiyuan Hotel)

Tuesday, November 21: Registration, day 2 (09:00-18:00, venue: Science Hall, Level 1)

Tuesday, November 21: Workshops, day 2 (9:00-18:00)

Time Workshops Venues

9:00-12:00 Human Behavior Analysis Science Hall: Room 201.

13:30-17:55 Passive and Active Electro-Optical Sensors for Areal and Space Imaging

Science Hall: Room 201.

9:00-11:40 Computer Vision and Modern Vehicles


9:00-17:00 Educational Cloud and Image and Video Enriched Cloud Services

No.9 Teaching Building: Room 731.

9:00-17:00 Vision meets Graphics No. 9 Teaching Building: Room 635.

19:00-21:00 Steering Committee Meeting

Wednesday, November 22nd: Main conference, day 3 (venue: Yifu International Convention Center: Lecture Hall, Level 1)

8:00-8:30 Registration

8:30-8:45 Opening

8:45-9:45 Keynote 1: Biomedical Imaging: A Galisonian Perspective for Sciences

9:45-10:45 Keynote 2: Modern Computer Vision Techniques for X-ray Testing in Baggage Inspection

10:45-11:05 Break

11:05-12:05 Oral Session 1: Best paper candidates

12:05-14:00 Lunch

14:00-15:00 Keynote 3: Color Contrast in the Aesthetic Image: An examination of the complex ways that color contrast manifests in paintings

15:00-16:40 Oral Session 2: Image/Video Processing and Analysis 1

16:40-17:00 Break

17:00-18:20 Oral Session 3: Image/Video Processing and Analysis 2

18:30-20:30 Banquet

Thursday, November 23rd: Main conference, day 4 (venue: Yifu International Convention Center: Lecture Hall, Level 1)

8:00-9:00 Keynote 4: Deep Learning towards on-device Visual Analysis

9:00-10:20 Oral Session 4: Pattern Recognition and Applications 1

10:20-10:40 Break

10:40-12:00 Poster Session

12:00-13:30 Lunch

13:30-14:50 Oral Session 5: Pattern Recognition and Applications 2

14:50 Survivor’s Party



4

Welcome

Welcome to Wuhan and to the 8th Pacific-Rim Symposium on Image and Video

Technology, PSIVT 2017.

PSIVT provides a forum to bring together researchers and practitioners who are being

involved or are contributing to both the theoretical advances and practical

implementations in image and video technology. Previous issues of PSIVT have been

in Taiwan (2006), Chile (2007), Japan (2009), Singapore (2010), Korea (2011), and in

Mexico (2013) and in Auckland (2015).

This year PSIVT 2017 features a single-track main conference which includes: keynote

speakers and technical papers (including oral and poster presentations). It is followed

by a day with workshops.

The PSIVT 2017 call for papers attracted a record number of 92 paper submissions.

The papers were reviewed by a program committee composed of 4 program chairs

and 86 technical reviewers. A double-blind and rebuttal phase composes the whole

review process, which is closely supervised by PSIVT 2017 Program Chairs. As a result,

20 papers were accepted for oral presentation and 20 papers were accepted for

poster presentation. The acceptance rate is 21% for oral presentations and 43%

overall.

This year the symposium will host three invited keynote speakers. They are Xiaoyi

Jiang, who will talk about “Biomedical Imaging: A Galisonian Perspective for Sciences”,

Domingo Mery with the talk on “Modern Computer Vision Techniques for X-ray

Testing in Baggage Inspection”, Martin Constable who will present “Color Contrast in

the Aesthetic Image: An examination of the complex ways that color contrast

manifests in paintings” and Dr. Shuicheng Yan with his talk on “Deep Learning towards

on-device Visual Analytics”.

This year the symposium also features a series of workshops. Especially three new

workshops are open to engage with the widely and fast development of image and

video technologies in affective computing, education and driving, which are closely

related to our daily lives. The all five PSIVT 2017 workshops are:

the Workshop on Human Behavior Analysis. It received 18 papers and 6 were

accepted. The acceptance rate is 33%.

the Workshop on Educational Cloud and Image and Video Enriched Cloud Services.

It received 24 papers and 12 were accepted. The acceptance rate is 50%.

the Workshop on Vision meets Graphics. It received 39 papers and 10 were accepted.

The acceptance rate is 25%.


5

the Workshop on Passive and Active Electro-Optical Sensors for Areal and Space

Imaging. It received 10 papers and 5 were accepted. The acceptance rate is 50%.

the workshop on Computer Vision and Modern Vehicles. It received 12 papers and 5

were accepted. The acceptance rate is 41%.

Outstanding paper awards have also been a tradition at PSIVT. The Program Chairs

considered the top-ranked paper submissions based on the reviews and meta-reviews

and identified a set of nominations for the awards. The nominated papers were

carefully selected and the recipients of these awards will be announced at the banquet.

There is a long list of people we like to thank for contributing to the success of the

symposium. We thank the keynote speakers, authors and presenters who contribute

actively to the symposium program.

Of course, we also thank everyone in the organizing committee and Event Services of

Central China Normal University, and our student helpers.

We thank the International Association for Pattern Recognition (IAPR) for endorsing

the event, and Springer’s Lecture Notes in Computer Science, for having the main

conference and the workshop papers published as post-conference LNCS volumes.

We also thank our sponsors, National Engineering Research Center for E-learning,

Central China Normal University Wollongong Joint Institute and WUHAN JINGTIAN

ELECTRICAL CO., LIMITED.

We wish you all a wonderful PSIVT 2017.

Xinguo Yu

Central China Normal University, Wuhan



6

PSIVT 2017 Steering Committee

Chair

Reinhard Klette - Auckland University of Technology, New Zealand.

Members

Akihiro Sugimoto - National Institute of Informatics, Japan.

Xinguo Yu - Central China Normal University, China.

Kap Luk Chan - Nanyang Technological University, Singapore.

Domingo Mery - Pontificia Universidad Católica, Chile.

Yo-Sung Ho - Gwangju Institute of Science and Technology, Korea.

Wen-Nung Lie - National Chung Cheng University, Taiwan.

Mariano Rivera - Centro de Investigación en Matemáticas, México.

The steering committee invites bids for hosting future issues of PSIVT (the next will be in 2019).

Interested colleagues from the Pacific Rim region please just submit a bid to one of the steering

committee members.


7

PSIVT 2017 Organizing Committee

Hosted by

Central China Normal University, Wuhan,

China

Honorary Chairs

Zhengyou Zhang, Microsoft, USA

Reinhard Klette, Auckland University of

Technology, New Zealand

General Chairs

Larry Davis, University of Maryland, USA

Antonio Robles-Kelly, NICTA, Australia

Xinguo Yu, Central China Normal

University, China

General Workshop Chairs

Shin’ichi Satoh, National Institute of

Informatics, Japan

Chong-Wah Ngo, City University of Hong

Kong

Junsong Yuan, Nanyang Technological

University,Singapore

Local Arrangement Chairs

Jingying Chen, Central China Normal

University, China

Chao Sun, Central China Normal

University, China

Demo / Exhibition Chairs

Tiziana D' Orazio, Institute for Signal and

Image Processing, Italy

Wen-Huang Cheng, Academia Sinica,

Taiwan

Lingyu Duan, Peking University, China

Publicity Chairs

Yong Man Ro, Korea Advanced Institute of

Science and Technology

Jun-Wei Hsieh, National Taiwan Ocean

University, Taiwan

Liyuan Li, Institute for Infocomm Research,

Singapore

Hanqing Lu, National Laboratory of

Pattern Recognition, CAS, China

Program Chairs

Qingming Huang, University of Chinese

Academy of Sciences, China

Carlos H. Morimoto, University of São

Paulo, Brazil

Simon Lucey, CSIRO ICT Centre, Australia

Manoranjan Paul, Charles Sturt University,

Australia

Sponsorship Chairs

Bin He, Central China Normal University,

China

Yue Wang, Institute of Information

Technology, Singapore

Area Chairs

Fay Huang, National Ilan University,

Taiwan

Michael Cree, The University of Waikato,

New Zealand

Nicolai Petkov, Groningen University, The

Netherlands

Phil Bones, University of Canterbury, New

Zealand

Li Chen, University of the DC, USA

Jian Cheng, Chinese Academy of Sciences,

China

Uwe Franke, Daimler A.G., Germany

Hanseok Ko, Korea University, Korea

Chilwoo Lee, Chonnam National

University, Korea

Wen-Nung Lie, National Chung Cheng

University, Taiwan

Chia-Yen Chen, National University of

Kaohsiung, Taiwan

Rick Millane, University of Canterbury,

New Zealand

Takeshi Oishi, Tokyo University, Japan

Lei Qin, CAS, China

Terence Sim, National University of

Singapore, Singapore

Zhixun Su, Dalian University of Technology,

China

Wei Qi Yan, Auckland University of

Technology, New Zealand



8

Maps

Location of Central China Normal University

Locations of registration & conference buildings


9

General Information

The following information is provided as a guide to the conference and to Wuhan. If you have any

queries, please visit the registration desk.

Registration Desk Hours 14:00-18:00, November 20 (Mon)

08:00-18:00, November 21(Tue)-23(Thu)

Conference Venue The main conference will be held on Yifu International Convention Center. The workshops will be

held on Science Hall and No.9 Building. See Program Section for details.

Physical Address NO.152 Luoyu Road, Wuhan, Hubei, China

Catering Morning and afternoon teas will be served outside the conference room. Lunches will be served

at the Guiyuan Hotel. Care is taken to ensure all dietary requirements are catered to. If you have

made a special request please talk to the catering staff.

Mobile Phones Mobile devices should be switched off or put on silence mode during all presentations.

Urgent messages and Lost Property Urgent messages for delegates and lost property can be directed to the registration desk.

Messages and lost property will be held there for collection until the conclusion of the conference.

Name Tags Please wear your name tag at all times during the workshop and social events. You will be asked

to present your name tag to enter the welcome reception and dinner.

No Smoking Policy Delegates should be aware that smoking is banned in all public buildings in China and indoors

throughout the campus. This policy is strictly enforced. Smokers may smoke on public

land/footpaths only.

Presentation Attendees As a courtesy to our presenters, please ensure you arrive at each session venue prior to the start

of the presentations.

WIFI Wifi: ccnu-meeting. Password: ccnu2017.



10

Yifu International Convention Center

Presenting Authors Each session chair will be keeping strictly to time. If you are scheduled to give a presentation,

please ensure your PowerPoint is uploaded well in advance of your presentation time, preferably

during the catering breaks or prior to the start of each day. To upload your presentation, please

take it to your presentation room on a USB memory stick. A member of the organizing team will

be available to assist you.

Rooms and AV Each room features standard audiovisual equipment including white screens, data projector,

Windows lecture computers and lectern microphone.

If you have videos or animations in your presentation, please ensure you have embedded the files

in your presentation and copied and transferred the video file together with your PowerPoint

presentation.

Without doing this, your video may not function. WMV or AVI file types are recommended. Please

bring your presentation on a USB which can easily be loaded onto the lecture theatre computer.

Emergencies, medical needs and illness If you have an emergency you can contact the police, paramedics by calling 110 or 120 from any

landline or mobile phone. If you require non-emergency medical attention during the workshop,

please inform the registration desk.


11

Guiyuan Hotel

Banquet

Thursday 22 November, 18:30pm Xiongchu International Hotel.

The Conference dinner is available to those who have registered for PSIVT 2017.

Please make sure you present your name tag on arrival. Buses will leave from School at 18:00pm.

Survivors Party

Thursday, November 23rd after 14:30 Hubei flavor restaurant. Enjoy the flavors of Hubei cuisine, like Wuchang fish, Tianmen steamed

dishes and Braised crawfish.

The Survivors tour is available to those who have registered for PSIVT 2017.

Please make sure you present your name tag on arrival. Buses will leave from the conference

venue at 14:50pm.



12

Wuhan Visitor Information

The following information is provided as a guide to Wuhan. If you have any queries, please visit

the registration desk.

Getting around

Public Transportation

Subway and Bus is highly recommended if you want to get around Wuhan. Bus fare costs ¥2,

subway fare is between ¥2 and ¥7. Buses begin about 6am and end about 10pm depending on the

route. The metro, depending on the line and direction, begins around 6am and can end any time

between 10.30pm and 11.30pm. You can also find bike sharing services easily in this city.

Taxi

Taxis can be hard to find in crowded areas or at busy times. Fare should not cost more than ¥70 to

get from one side of the city to another.

Car

There is an Avis location in Wuhan where you can rent a vehicle for ¥200 a day. Driving is not ideal

due to the traffic.

Leisure

Yellow Crane Tower Bordering on Yangtze River and crouching on

the top of the Snake Hill, the Yellow Crane Tower is one of the three

most famous towers on the south bank of Yangtze River First built

in 223 AD. The tower has a history of over 1700 years. It is not only

an important scenic spot, but also a symbol of "piping times of

peace" in people's minds.

Wuhan Yangtze River Bridge Completed in 1957, this engineering

marvel is 1,670 meters long and has one level for automobiles and

another for trains. The construction of this bridge provided direct

rail service between north and south China for the first time.

app:ds:Yangtze%20River




13

Wuhan East Lake Scenic Area East Lake is located on the south bank of

the Yangtze River and in the east suburb of Wuchang, Wuhan city. It is

the biggest scenery tourist attraction in Wuhan and also the largest lake

within a city in China.

Special Food

Osmanthus paste rice wine

Many Wuhan locals have several fried rice buns (mianwo) and a cup of

sweet osmanthus paste rice wine for breakfast. This is said to be a

nutritious and flavorful breakfast, a perfect way to start the day.

Wuchang fish

Wuchang fish, known as "Tuantoufang (blunt-snout bream), is a kind

of bream, originally produced in the Liangzi Lake of Echeng County in

Hubei Province. It has been transplanted and fed around China.

Wuhan duck

Wuhan duck refers to several dishes from the city of Wuhan, in Hubei

Province, China. The dishes are specific parts of a duck, including the

tongue, head, feet, liver, kidney, particularly the neck.

Hongshan Vegetable Bolts

Hongshan Vegetable Bolts is a speciality of Wuhan, Hubei. A famous

dish called Hongshan Bolts fried with Smoked Pork can be found on

every menu in any restaurant in Wuhan.



14

Keynote Speakers

Wednesday, 22 November 2017 - 8:45-9:45

Keynote 1:

Biomedical Imaging: A Galisonian Perspective for Sciences

Xiaoyi Jiang

University of Münster, Germany

Abstract

In biology and medicine imaging has become an indispensable tool for basic research and clinical

practice. Many image reconstruction, processing and analysis algorithms have been developed

and successfully adopted to biomedical applications. The specific characteristics of biomedical

image data have. motivated researchers to develop novel concepts and algorithms. This talk

emphasizes the fundamental research view of biomedical computer vision and discusses a number

of related challenges, concepts, and algorithms. In addition to the information processing view the

imposing development in biomedical imaging also provides a driving force for sciences from a

Galisonian perspective.

Biography

Xiaoyi Jiang studied Computer Science at Peking University and received his Ph.D. and Venia

Docendi (Habilitation) degree in Computer Science from University of Bern, Switzerland. He was

an associate professor at Technical University of Berlin, Germany. Since 2002 he is a Full Professor

of Computer Science at University of Münster, Germany. Currently, he is Editor-in-Chief of

International Journal of Pattern Recognition and Artificial Intelligence. In addition, he also serves

on the Advisory Board and Editorial Board of several journals, including IEEE Transactions on

Medical Imaging, International Journal of Neural Systems, Pattern Analysis and Applications,

Pattern Recognition. His research interests include biomedical imaging, 3D image analysis, and

structural pattern recognition. He is a Senior Member of IEEE and Fellow of IAPR


15


Keynote 2:

Modern Computer Vision Techniques for X-ray Testing in Baggage

Inspection

Domingo Mery,

Pontificia Universidad Católica, Chile

Abstract

X-ray screening systems have been used to safeguard environments in which access control is of

paramount importance. Security checkpoints have been placed at the entrances to many public

places to detect prohibited items such as handguns and explosives. Generally, human operators

are in charge of these tasks as automated recognition in baggage inspection is still far from perfect.

Research and development on X-ray testing is, however, exploring new approaches based on

computer vision that can be used to aid human operators. In this talk, we present the state of the

art in computer vision for baggage inspection: several methods will be explained and evaluated.

They are based on bag of words, sparse representations, deep learning and classic pattern

recognition schemes among others. For each method, we i) present a brief explanation, ii) show

experimental results on the same database, and iii) provide concluding remarks discussing pros

and cons of each method.

Biography

Domingo Mery is the Associate Dean for Research and Innovation of the School of Engineering at

the Catholic University of Chile (UC). He is Professor in the Department of Computer Science at UC.

He received the Diploma (M.Sc.) degree in Electrical Engineering from the Technical University of

Karlsruhe, Germany, in 1992, and the Ph.D. degree with distinction at the Technical University of

Berlin. His research interests include image processing for fault detection in aluminum castings, X-

ray imaging, real-time programming and computer vision. He is author of more than 60 technical

SCI publications, and more than 70 conference papers. He served as Local Co-chair ofICCV2015

(Santiago de Chile). He was program general chair of the PSIVT2007, program chair PSIVT2009 and

General Co-chair of PSIVT2011 (Pacific-Rim Symposium on Image and Video Technology), and 2007

Iberoamerican Congress on Pattern Recognition.

http://dmery.ing.puc.cl/index.php/about-me/



16


Keynote 3:

Color Contrast in the Aesthetic Image: An examination of the complex

ways that color contrast manifests in paintings

Martin Constable

Abstract

A painting is a special class of image. Its every element has been crafted by the painter with

obsessive attention to how its influences its visual impact. Informing this are formalities are near-

limitless complexity, formalities which address such things as color, content, texture and

composition. Martin will be addressing one small corner of this complexity-domain: color contrast.

For the last ten years he has been working with a team of engineers attempting to identify and

quantify the many different forms that color contrast takes in the aesthetic domain. The work they

did was uniquely co-dependent, with the artist and the engineers working side-by-side.

Martin will begin by introducing Itten’s six color contrasts, and the influence they have had on his

work and related work by other researchers. He will then describe the six structural contrasts of

painting: global contrast, local contrast, center-corner contrast, regional contrast, neighboring

regional contrast and depth-aware contrast. Following this he will address a range of color spaces:

RGB, RYB, HSL and Munsell. These he will introduce as conceptual models: each addressing the

color experience in different ways, and each playing a different role in his research. He will

conclude with an introduction to his ongoing research on global hue contrast, a topic he believes

is ill-understood in the engineering domain.

With a photographic image being increasingly available to high-level manipulation, now seems a

very apt time for this kind of research. What might we learn from artists? How, perhaps, might a

photograph be aesthetically improved with reference to such information?

Biography

Martin Constable teaches visual effects and painting at the School of Art Design and Media,

Nanyang Technological University, Singapore. As an artist he works in the Singapore - based artists

collaborative, Grieve Perspective and has shown widely in S E Asia. He also works closely with

computer engineers on the subject of computational aesthetics: identifying and investigating

those qualities of an artwork that are available to a computational definition.


17

Thursday, 23 November 2017 - 8:00-9:00

Keynote 4:

Deep Learning towards on-device Visual Analytics

Shuicheng Yan,

National University of Singapore

Abstract

This talk shall cover contents from two aspects related with on-device visual analytics. This first

part shall introduce a set of neural network structures related with 1x1 convolution, explaining

how to decrease the model size, increase inference speed, and improve accuracy. The second part

shall introduce the application of efficient deep learning models for camera-related APPs,

including Livestream, AR Camera, ADAS, etc.

Biography

Dr. Yan Shuicheng is chief scientist of Qihoo/360 company, and also the Dean's Chair Associate

Professor at National University of Singapore. Dr. Yan's research areas include machine learning,

computer vision and multimedia, and he has authored/co-authored hundreds of technical papers

over a wide range of research topics, with Google Scholar citation over 20,000 times and H-index

66. He is ISI Highly-cited Researcher of 2014, 2015 and 2016. His team received 7 times winner or

honorable-mention prizes in PASCAL VOC and ILSVRC competitions, along with more than 10

times best (student) paper prizes. He is also IAPR Fellow.

https://www.ece.nus.edu.sg/stfpage/eleyans/



18

Program

Main Conference Venue:

Lecture Hall, Level 1, Yifu International Convention Center.

Workshop Venues:

Time Workshops Venues

9:00-12:00 Human Behavior Analysis Science Hall: Room 201.

13:30-17:55 Passive and Active Electro-Optical

Sensors for Areal and Space Imaging


9:00-11:40 Computer Vision and Modern

Vehicles


9:00-17:00 Educational Cloud and Image and

Video Enriched Cloud Services

No.9 Teaching Building: Room 731.

9:00-17:00 Vision meets Graphics No. 9 Teaching Building: Room 635.

19:00-21:00 Steering Committee Meeting

Monday, November 20th: Registration, day 1

Time


Tuesday, November 21st: Workshop on Human Behavior Analysis, day 2 (9:00-12:00, Science Hall:

Room 201)

9:00-9:30 Invited Talk: Parse Tensor Discriminative Locality Alignment for Gait Recognition

Du Bo (Wuhan University, China)

9:35-9:55

10:00-10:20

10:25-10:45

10:50-11:10

11:15-11:35

11:40-12:00

Session 1

Deep Transfer Feature based Convolutional Neural Forests for Head Pose

Estimation

Yuanyuan Liu, Zhong Xie, Xi Gong,and Fang Fang.

Biometric System Based on Registration of Dorsal Hand Vein Configurations

Szidónia Lefkovits,Simina Emerich, and László Szilágyi.

A Multi-scale Triplet Deep Convolutional Neural Network for Person Re-

identification

Mingfu Xiong,Jun Chen,Zhongyuan Wang,Chao Liang,Bohan Lei,and Ruimin Hu.

Facial Expression Recognition Using Cascaded Random Forest based on Local

Features

Mingjian Tuo and Jingying Chen.

Detection of salient regions in crowded scenes based on weighted networks

approach

Juan Zheng and Xuguang Zhang.

Selecting Salient Features from Facial Components for Face Recognition

A. Gumede, S. Viriri and M.V. Gwetu.


19

Tuesday, November 21st: Workshop on Passive and Active Electro-Optical Sensors for Aerial &

Space Imaging, day 2 (13:30-17:55, Science Hall: Room 201).

13:30-13:35 Welcome and Invited Talk:

Ralf Reulke (Humboldt-Universität zu Berlin, Germany), Bin Luo (Wuhan

University, China).

13:35-14:30 Invited Talk: Optical Instruments Short Overview in a Nutshell Detection Chain

characterization exemplarily presented for S4

Rüdiger Hohn (Airbus).

14:30-14:45 Break

14:45-15:05

15:05-15:25

Session 1

Extracting Plücker Lines and Their Relations for 3D Reconstruction of Indoor

Scene

Huihui Sun, Xinguo Yu and Chao Sun.

An Aircraft Tracking Method in Simulated Infrared Image Sequences Based on

Regional Distribution

Sijie Wu, Saisai Niu, Kai Zhang and Jie Yan.

15:25-15:40 Break

15:40-16:00

16:00-16:20

16:20-16:40

Session 2

FireBIRD Mission Data for Gas Flaring Analysis

Agnieszka Soszyńska.

DESIS - DLR Earth Sensing Imaging Spectrometer

David Krutz, Holger Venus, Andreas Eckardt, Ingo Walter, Ilse Sebastian, Ralf

Reulke, Burghardt Gu¨nther, Bernd Zender, Simone Arloth, Christian Williges,

Matthias Lieder, Michael Neidhardt, Ute Grote, Friedrich Schrandt and Andreas

Wojtkowiak.

Automatic Ship Detection on Multispectral and Thermal Infrared Aerial Images

Using MACS-Mar Remote Sensing Platform

Joerg Brauchle, Steven Bayer and Ralf Berger

16:40-16:55 Break

16:55-17:15

17:15-17:35

17:35-17:55

Session 3

Design and Implementation of a Mobile Teaching Interactive Platform

Huihui Sun and Xinguo Yu.

DESIS CMOS Detector Verification

Holger Venus (David Krutz).

Image Quality

Ralf Reulke (Andreas Brunn).

Tuesday, November 21st: Workshop on Computer Vision and Modern Vehicles, day 2 (9:00-11:40,

Science Hall, Room 301)

9:00-9:40 Invited Talk: Jian Yao (Wuhan University)

9:40-10:00

Session 1

Robust Expression Recognition using ResNet with a Biologically-plausible



20

10:00-10:20

10:20-10:40

Activation Function

Yunhua Chen, Jin Du, QianLiu and Bi Zeng.

Context-Awareness Based Adaptive Gaussian Mixture Background Modeling

Honggang Xie, Jinsheng Xiao and Junfeng Lei.

A systematic scheme for automatic airplane detection from high-resolution

remote sensing images

Jiao Zhao, Jing Han, Chen Feng and Jian Yao.

11:40-10:55 Break

10:55-11:15

11:15-11:35

Session 2

Mixed-Noise Removal in Images Based on a Convolutional Neural Network

Ling Ding,Huying Zhang,Bijun Li,Jian Zhou and Wenhao Gu.

Local Fast R-CNN Flow for Object-centric Event Recognition in Complex Traffic

Scenes

Qin Gu, Jianyu Yang, Wei Qi Yan, Yanqiang Li and Reinhard Klette.

11:35-11:40 Concluding remarks

Tuesday, November 21st: Workshop on Educational Cloud and Image and Video Enriched Cloud

Services, day 2 (9:00-16:50, No.9 Teaching Building, Room 731)

9:00-9:25

9:25-9:50

9:50-10:15

Session 1

High School Statistical Graph Classification Using Hierarchical Model for

Intelligent Mathematics Problem Solving

Yantao Wei,Yafei Shi,Huang Yao,Gang Zhao,and Qingtang Liu

Machine Solving on Hypergeometric Distribution Problems

Chao Sun,Yao Su,and Xinguo Yu.

Extracting Algebraic Relations from Circuit Images Using Topology Breaking Down

and Shrinking

Bin He,Pengpeng Jian,Meng Xia,Chao Sun and Xinguo Yu.

10:15-10:35 Break

10:35-11:00

11:00-11:25

11:25-11:50

Session 2

China-Finland EduCloud Platform towards Innovative Education

Jiehan Zhou,Jukka Riekki,Mätti Hämäläinen,Pasi Mattila,Xinguo Yu,Xiwei

Liu ,Weishan Zhang.

SPSE: a Smart Phone-based Student Evaluation

Xiang Gao,Jiehan Zhou,Zhitao Yu,Jianli Zhao,Zhengbin Fu,Chunxiu Li.

Research on the Construction of Corpus for Automatic Solution of Elementary

Mathematics Statistics Applications

Chuanyuan Lao,Qingtang Liu, Linjing Wu,Jingxiu Huang and Gang Zhao.

11:50-14:00 Lunch

14:00-14:25

14:25-14:50

Session 3

Constructing a Learning Map with Lattice for a Programming Course

Xin Li,Han Lyu,Jiehan Zhou,Shuai Cao,Xin Liu.

Data Mining as a Cloud Service for Learning Articial Intelligence

Weishan Zhang,Hao Lv,Liang Xu, Xin Liu,Jiehan Zhou.


21

14:50-15:15

Research on Optimization of Point Cloud Registration ICP Algorithm

Jian Liu,Xiuqin Shang,Shuzhan Yang,Zhen Shen,Xiwei Liu, Gang Xiong,Timo R.

Nyberg.

15:15-15:35 Break

15:35-16:00

16:00-16:25

16:25-16:50

Session 4

Parallel Education Systems under Perspective of System Construction for New IT

Era

Xiaoyan Gong,Xiwei Liu,Sifeng Jing,Xiao Wang.

Computerized Adaptive English Ability Assessment Based on Deep Learning

Xiao Wang,Yuanyuan Zhang,Shengnan Yu,Xiwei Liu and Fei-Yue Wang.

Foot modeling based on machine vision and social manufacturing research

Hongli Peng,Zhen Shen,Xiuqin Shang,Xiwei Liu,Gang Xiong,Taozhong Liu,Timo R.

Nyberg.

Tuesday, November 21st: Workshop on Vision meets Graphics, day 2 (9:00-16:20, No.9 Teaching

Building, Room 635)

9:00-9:05 Opening

9:05-9:50 Invited Talk 1: Stereo Vision for Artistic Photo Rendering.

Reinhard Klette (Auckland University of Technology) and Dongwei Liu (Zhejiang

University of Finance and Economics).

9:50-10:15

10:15-10:40

10:40-11:05

Session 1

Crowd counting from a still image using Multi-scale Fully Convolutional Network

with adaptive human-shaped kernel

Jinmeng Cao, Biao Yang, Yuyu Zhang, Ling Zou.

Robust Blind Deconvolution Using Relative Total Variation as a Regularization

Penalty

Yunzhi Lin and Wenze Shao.

On road vehicle detection using an improved Faster RCNN framework with small-

size region up-scaling strategy

Biao Yang, Yuyu Zhang, Jinmeng Cao, and Ling Zou.

11:05-11:25 Break

11:25-12:10 Invited Talk 2: MeshFlow for Application of Video Editing

Shuaicheng Liu (University of Electronic Science and Technology of China).

12:10-12:35

12:35-13:00

Session 2

Fast Haze Removal of UAV Images Based on Dark Channel Prior

Siyu Zhang, Congli Li, and Song Xue.

Structure-Preserving Texture Smoothing via Adaptive Patches

Hui Wang, Yue Wang, Junjie Cao, Xiuping Liu

13:00-14:00 Lunch

14:00-14:45 Invited Talk 3: Weakly supervised image understanding with graphics and vision

applications

Ming-Ming Cheng (Nankai University).

Session 3



22

14:45-15:10

Watercolour Rendering of Portraits

Paul L. Rosin and Yu-Kun Lai.

15:10-15:30 Break

15:30-15:55

15:55-16:20

Session 4

Blind Image Deblurring via Salient Structure Detection and Sparse

Representation

Yu Cai, Jinshan Pan, and Zhixun Su.

Blur Estimation for Natural Edge Appearance in Computational Photography

Dongwei Liu and Reinhard Klette.

Wednesday, November 22nd: Main conference, day 3


8:30-8:45 Opening

8:45-9:45 Keynote 1: Biomedical Imaging: A Galisonian Perspective for Sciences.

Xiaoyi Jiang (University of Münster, Germany)

Session Chair: Xinguo Yu (Central China Normal University)

9:45-10:45 Keynote 2: Modern Computer Vision Techniques for X-ray Testing in Baggage

Inspection

Domingo Mery (Pontificia Universidad Católica, Chile).

Session Chair: Reinhard Klette (Auckland University of Technology)

10:45-11:05 Break

11:05-11:25

11:25-11:45

11:45-12:05

Oral Session 1: Best paper candidates

Session Chair: Manoranjan Paul (Charles Sturt University, Australia)

Unsupervised Domain Adaptation with Robust Deep Logistic Regression

Guangbin Wu, Weishan Chen, Wangmeng Zuo and David Zhang.

Continuous Motion Recognition in Depth Camera based on Recurrent Neural

Networks and Grid-based Average Depth

Tao Rong, Rui Yang and Ruoyu Yang.

Auto-calibration method for active 3D endoscope system using silhouette of

pattern projector

Ryo Furukawa, Masahito Naito, Daisuke Miyazaki, Masahi Baba, Shinsaku Hiura,

Yoji Sanomura, Shinji Tanaka and Hiroshi Kawasaki.

12:05-14:00 Lunch

14:00-15:00 Keynote 3: Color Contrast in the Aesthetic Image: An examination of the

complex ways that color contrast manifests in paintings

Martin Constable.

Session Chair: Kap Luk Chan (Nanyang Technological University)

15:00-15:20

15:20-15:40

Oral Session 2: Image/Video Processing and Analysis 1

Session Chair: Qingming Huang (University of Chinese Academy of Sciences)

Multiset Canonical Correlation Analysis: Texture Feature Level Fusion of Multiple

Descriptors for Intra-Modal Palmprint Biometric Recognition

Raouia Mokni, Anis Mezghani, Hassen Drira and Monji Kherallah.

Complex-Valued Representation for RGB-D Object Recognition


23

15:40-16:00

16:00-16:20

16:20-16:40

Rim Trabelsi, Issam Jabri, Farid Melgani, Fethi Smach, Nicola Conci and Ammar

Bouallegue.

Video Highlight Detection via Deep Ranking Modeling

Yifan Jiao, Xiaoshan Yang, Tianzhu Zhang, Shucheng Huang and Changsheng Xu.

Ink-jet Printer’s Characterization by 3D Gradation Trajectories on an Equidistant

Color Difference Basis

Oleg Milder and Dmitry Tarasov.

Gradation surfaces as a method for multi-color ink-jet printers color

specifications management

Oleg Milder and Dmitry Tarasov.

16:40-17:00 Break

17:00-17:20

17:20-17:40

17:40-18:00

18:00-18:20

Oral Session 3: Image/Video Processing and Analysis 2

Session Chair: Jingying Chen (Central China Normal University)

Multi-objective Visual Odometry

Hsiang-Jen Chien, Jr-Jiun Lin, Tang-Kai Yin and Reinhard Klette.

Visual Comparison Based on Multi-Class Classification Model

Hanqin Shi and Liang Tao.

System Designs for Augmented Reality based Ablation Probe Tracking

Hao Bo Yu and Harvey Ho.

Improved ORB Algorithm for RGB-D SLAM

Zhipeng Yu, Lin Jiang and Chen Guo.

18:30-20:30 Banquet

Thursday, November 23rd: Main conference, day 4

8:00-9:00 Keynote 4: Deep Learning towards on-device Visual Analytics

Shuicheng Yan (National University of Singapore)

Session Chair: Shiqian Wu (Wuhan University of Science and Technology)

09:00-09:20

09:20-09:40

09:40-10:00

10:00-10:20

Oral Session 4: Pattern Recognition and Applications 1

Session Chair: Dheyaa, Wenbin Gan (Central China Normal University)

A Novel No-reference Subjective Quality Metric for Free Viewpoint Video Using

Human Eye Movement

Pallab Podder, Manoranjan Paul and Manzur Murshed.

Research on Color Space Conversion Model from CMYK to CIE-LAB based on

GRNN

Xinyue Bao, Wangan Song and Sheng Liu.

GCP-SLAM: LSD-SLAM with Learning-based Confidence Estimation

Aidi Feng, Weiqi Zhang, Zifei Yan and Wangmeng Zuo.

Layer-wise weight decay for deep neural networks

Masato Ishii and Atsushi Sato.

10:20-10:40 Break

10:40-10:44

Poster Session

Session Chair: Xiwei Liu (Chinese Academy of Science)

Predicting Turn-Taking by Compact Gazing Transition Patterns in Multiparty



24

10:44-10:48

10:48-10:52

10:52-10:56

10:56-11:00

11:00-11:04

11:04-11:08

11:08-11:12

11:12-11:16

11:16-11:20

11:20-11:24

11:24-11:28

11:28-11:32

11:32-11:36

11:36-11:40

11:40-11:44

11:44-11:48

11:48-11:52

Conversation

Li Tian, Qi Jia and Zhen Zhu.

Using Sparse-Point Disparity Estimation and Spatial Propagation to Construct

Dense Disparity Map for Stereo Endoscopic Images

Wen-Nung Lie, Hsi-Hung Huang, Shih-Wei Huang and Kai-Che Liu.

A Critical Review of the Trifocal Tensor Estimation

Laura F. Julia and Pascal Monasse.

Globally Optimal Object Tracking with Complementary Use of Single Shot

Multibox Detector and Fully Convolutional Network

Jinho Lee, Brian Kenji Iwana, Shouta Ide, Hideaki Hayashi and Seiichi Uchida.

Deep Learning-Based Improved Object Recognition in Warehouses

Syeda Fouzia,Mark Bell and Reinhard Klette.

Understanding plane geometry problems by integrating relations extracted from

text and diagram

Wenbin Gan,Xinguo Yu,Chao Sun,Bin He and Mingshu Wang.

Single Image Dehazing Via Image Generating

Shengdong Zhang,Jian Yao,and Edel B. Garcia.

Intelligent Assistant for People with Low Vision Abilities

Oleksandr Bogdan, Oleg Yurchenko, Oleksandr Bailo, Francois Rameau,

Donggeun Yoo and In So Kweon.

Lane Detection Based on Road Module and Extended Kalman Filter

Jinsheng Xiao, Li Luo, Wentao Zou, Yuan Yao and Reinhard Klette.

Gaussian Noise Detection and Adaptive Non-Local Means Filter

Peng Chen, Shiqian Wu, Hongping Fang, Bin Chen and Wei Wang.

Automatic brain tumor segmentation in multispectral MRI volumes using a

random forest approach

Zoltan Kápás, László Lefkovits, David Iclănzan, Ágnes Györfi, Barna László

Iantovics, Szidónia Lefkovits, Sándor M. Szilágyi and László Szilágyi.

Using Facial Expression Recognition for Crowd Monitoring

Ross Philip Holder and Jules-Raymond Tapamo.

Detection of Adulteration in Red Meat Species Using Hyperspectral Imaging

Mahmoud Al-Sarayreh, Marlon M. Reis, Wei Qi Yan and Reinhard Klette.

Age Estimation with Local Ternary Directional Patterns

Raphael Angulu, Jules R. Tapamo and Aderemi O. Adewumi.

A New Scheme for QoE Management of Live Video Streaming in Cloud

Environment

Dheyaa Jasim Kadhim,Xinguo Yu,Saba Qasim Jabbar,Yu Li, Wenxing Luo.

Uncertainty Model for Template Feature Matching

Hongmou Zhang, Denis Grießbach, Jürgen Wohlfeil and Anko Börner.

Hybrid Adaptive Prediction Mechanisms with Multilayer Propagation Neural

Network for Hyperspectral Image Compression

Rui Xiao and Manoranjan Paul.

Secret image sharing for (k,k) threshold based on Chinese remainder theorem

and image characteristics


25

11:52-11:56

11:56-12:00

Xuehu Yan, Yuliang Lu, Lintao Liu, Song Wan, Wanmeng Ding and Hanlin Liu.

Block-Wise Gaze Estimation Based on Binocular Images

Xuemei Wu, Jing Li, Qiang Wu, Jiande Sun and Hua Yan.

Integrated Multi-Scale Event Verification in an Augmented Foreground Motion

Space

Qin Gu, Jianyu Yang, Wei Qi Yan and Reinhard Klette.

12:00-13:30 Lunch

13:30-13:50

13:50-14:10

14:10-14:30

14:10-14:50

Oral Session 5: Pattern Recognition and Applications 2

Session Chair: Chao Sun (Central China Normal University)

Adaptive Dehaze Method for Aerial Image Processing

Rong-Qin Xu, Sheng-Hua Zhong, Gaoyang Tang and Yingying Zhu.

Efficient GPU Implementation of Informed-Filters for Fast Computation

Takuro Oki and Ryusuke Miyamoto.

Automatic Problem Understanding from Circuit Schematics

Xinguo Yu, Pengpeng Jian, Bin He, Gang Zhao and Meng Xia.

Feature Similarity and Frequency-Based Weighted Visual Words Codebook

Learning Scheme for Human Action Recognition

Saima Nazir, Muhammad Haroon Yousaf and Sergio A. Velastin.

14:50 Survivor’s Party



26

Notes


27

Notes



28

In Case of Emergency, please contact:

+86 027-6786 2802 (Ms. Jingwen Luo)

or +86 155 2751 265l8 (Prof. Xinguo Yu)

Thank you to our Supporters & Sponsors Technical Program(PSIVT2017).pdf · hao Sun, entral hina ......

Documents

Transcript of Thank you to our Supporters & Sponsors Technical Program(PSIVT2017).pdf · hao Sun, entral hina ......