Call for Paper
   Important Dates
   Organizing Committee
   Program Committee
   Online Submission
   Camera-Ready Submission
   Technical Program
   Conference Venue
   Travel Information
   Hotel Information
   Invited Speakers
   Paper Awards
   Contact Information

ACCV 2009 Program

Information for Presenters:

  • For Orals: Each oral paper is limited to 25 minutes, which includes 20-minute presentation and a 5-minute discussion. Please note that all the workshop presentations will be in the Oral form.
  • For Posters: The poster boards are approximately 120cm (h) x 90cm (w). Also please note that though the poster sessions will be held in the afternoons, the authors can put up your posters in the mornings in advance.

ACCV¨09 Program at a Glance





September 23

9:00 C 17:30


18:00 C 20:00

Welcome Reception (Chang'an Hall)


September 24

Full day

(Tutorial & Workshops)

Qin Huang Hall

Tai Bai Shan Hall

Li Shan Hall

Hua Shan Hall

Board Room




Invited workshop 1:

Vision Based Human Modeling and Synthesis


Invited workshop 2:



Workshop 1:

3D Content and Its Applications






Workshop 2:




Workshop 3:



September 25

8:30 C 8:50

Opening (Chang'an Hall, A Zone)

8:50 C 10:10

Oral Session 1: Multiple View & Stereo (Chang'an Hall, A Zone)


10:10 C 10:30



10:30 - 12:10

Oral Session 2: Face & Pose Analysis (Chang'an Hall, A Zone)

12:10 C 13:30



13:30 - 14:30

Plenary Talk 1: Prof. Larry S. Davis (Chang'an Hall, A Zone)


14:30 - 14:50



14:50 - 16:30

Oral Session 3: Motion Analysis & Tracking (Chang'an Hall, A Zone)


16:30 - 18:30

Poster Session 1: Stereo, Motion Analysis, & Tracking (Chang'an Hall, B Zone)

Demo Session (Board Room)


September 26

8:30 C 10:10

Oral Session 4: Segmentation (Chang'an Hall, A Zone)

10:10 C10:30




Oral Session 5: Feature Extraction & Object Detection (Chang'an Hall, A Zone)

12:10 C 13:30




Plenary Talk 2: Prof. Long Quan (Chang'an Hall, A Zone)






Oral Session 6: Image Enhancement & Visual Attention (Chang'an Hall, A Zone)



Poster Session 2: Segmentation, Detection, Color & Texture (Chang'an Hall, B Zone)

19:30 C

Banquet (Tang Dynasty Theatre Restaurant)

September 27

8:30 C10:10

Oral Session 7: Machine Learning Algorithms for Vision (Chang'an Hall, A Zone)

10:10 C10:30




Oral Session 8: Object Categorization & Face Recognition (Chang'an Hall, A Zone)

12:10 C 13:30




Plenary Talk 3: Prof. Roberto Cipolla (Chang'an Hall, A Zone)






Oral Session 9: Biometrics & Surveillance (Chang'an Hall, A Zone)



Poster Session 3: Machine Learning, Recognition, Biometrics & Surveillance (Chang'an Hall, B Zone)

Demo Session (Board Room)


Closing (Chang'an Hall, A Zone)

Conference Site Map

Fig.1. Sketch map of the conference room

Chang'an Hall!!Reception

Chang'an Hall, A Zone!!Main Conference Room

Chang'an Hall, B Zone!!Poster/Coffee Break

Board Room!!Demo/Workshop

Qin Huang Hall!!Tutorial/Workshop

Hua Shan Hall!!Workshop

Tai Bai Shan Hall!!Workshop

Li Shan Hall!!Workshop


Wednesday, September 23

9:00 C 17:30 Registration

18:00 C 20:00 Welcome Reception


Thursday, September 24 (Tutorial & Workshops)


(Location: Qinhuang Hall)





Title: Image and Video Analysis using Local Binary Patterns (LBP)

Speaker: Dr. Abdenour Hadid (Senior Research Scientist, Machine Vision Group, University of Oulu, Finland)


WORKSHOPS (click this hyperlink)



Friday, September 25 (Main Conference, Day One)


8:30 C8:50




8:50 C10:10

Oral Session 1: Multiple View & Stereo

Chair: Prof. Katsushi Ikeuchi (University of Tokyo)

  • [MO1-1]: Multiple view reconstruction of a quadric of revolution from its occluding contours
    Pierre Gurdjos, Vincent Charvillat, G└raldine Morin, J└rôme Gu└nard (IRIT-ENSEEIHT-Toulouse, France)
  • [MO1-2]: Robust focal length estimation by voting in multi-view scene reconstruction
    Martin Bujnak, Zuzana Kukelova, Tomas Pajdla (Center for Machine Perception Czech Technical University in Prague)
  • [MO1-3]: Support aggregation via non-linear diffusion with disparity-dependent support-weights for stereo matching
    Kuk-Jin Yoon (GIST, Korea), Yekeun Jeong, In So Kweon (KAIST, Korea)

10:10 C10:30 Break


Oral Session 2: Face & Pose Analysis

Chair: Prof. Edwin R. Hancock (University of York)

  • [MO2-1]: Manifold estimation in view-based feature space for face synthesis across poses
    Xinyu Huang, Jizhou Gao, Sen-ching S. Cheung, Ruigang Yang (University of Kentucky)
  • [MO2-2]: Estimating human pose from occluded images
    Jia-Bin Huang, Ming-Hsuan Yang (University of California at Merced)
  • [MO2-3]: Head pose estimation based on manifold embedding and distance metric learning
    Xiangyang Liu (Shanghai Jiao Tong University, Hohai University), Hongtao Lu, Daqiang Zhang (Shanghai Jiao Tong University)
  • [MO2-4]: 3D reconstruction of human motion and skeleton from uncalibrated monocular video
    Yen-Lin Chen, Jinxiang Chai (Texas A&M University)

12:10 C 13:30 Lunch


Plenary Talk 1


Title: Mixed network AND/OR search for tracking people¨s hands and feet

Speaker: Prof. Larry S. Davis (University of Maryland)

14:30-14:50 Break


Oral Session 3: Motion Analysis & Tracking

Chair: Prof. Shigeo Morishima (Waseda University)

  • [MO3-1]: Mean-shift object tracking with a novel back-projection calculation method
    Lingfeng Wang (Institute of Automation, Chinese Academy of Sciences), Huai-Yu Wu (Peking University), Chunhong Pan (Institute of Automation, Chinese Academy of Sciences)
  • [MO3-2]: A shape derivative based approach for crowd flow segmentation
    Si Wu (City University of Hong Kong), Zhiwen Yu (South China University of Technology), Hau-San Wong (City University of Hong Kong)
  • [MO3-3]: Learning group activity in soccer videos from local motion
    Yu Kong (Institute of Automation, Chinese Academy of Sciences /Beijing Institute of Technology), Weiming Hu, Xiaoqin Zhang (Institute of Automation, Chinese Academy of Sciences), Hanzi Wang (The University of Adelaide), Yunde Jia (Beijing Institute of Technology)
  • [MO3-4]: Combining discriminative and descriptive models for tracking
    Jing Zhang, Duowen Chen, Ming Tang (Institute of Automation, Chinese Academy of Sciences)

16:30-18:30 Poster Session 1: Stereo, Motion Analysis, & Tracking (Chang'an Hall, B Zone)

  • [MP1-1]: A dynamic programming approach to maximizing tracks for structure from motion
    Jonathan Mooser, Suya You, Ulrich Neumann (University of Southern California), Raphael Grasset, Mark Billinghurst (University of Canterbury)
  • [MP1-2]: Dense and accurate spatio-temporal multi-view stereovision
    J└rôme Courchay (Imagine Universit└ Paris Est), Jean-Philippe Pons (CSTB), Pascal Monasse, Renaud Keriven (Imagine Universit└ Paris Est)
  • [MP1-3]: Semi-supervised feature selection for gender classification
    Jing Wu, William A.P. Smith, Edwin R. Hancock (University of York)
  • [MP1-4]: Planar scene modeling from quasiconvex subproblems
    Visesh Chari (CVIT IIIT-H, INRIA), Anil Nelakanti (CVIT IIIT-H, MirriAd), Chetan Jakkoju, C.V. Jawahar (CVIT IIIT-H)
  • [MP1-5]: Fast depth map compression and meshing with compressed tritree
    Michel Sarkis, Waqar Zia, Klaus Diepold (Institute for Data Processing (LDV) TU Munich)
  • [MP1-6]: A three-phase approach to photometric calibration for multi-projector display using LCD projectors
    Lei Zhang, Siyu Liang, Bo Qin, Zhongding Jiang (Fudan University)
  • [MP1-7]: Twisted cubic:degeneracy degree and relationship with general degeneracy
    Tian Lan, Yihong Wu, Zhanyi Hu (Institute of Automation, Chinese Academy of Science)
  • [MP1-8]: Two-view geometry and reconstruction under quasi-perspective projection
    Guanghui Wang, Q.M. Jonathan Wu (University of Windsor)
  • [MP1-9]: Similarity scores based on background samples
    Lior Wolf (Tel-Aviv University), Tal Hassner (The Open University of Israel), Yaniv Taigman (Tel-Aviv University, face.com)
  • [MP1-10]: Human action recognition using spatio-temporal classification  
    Chin-Hsien Fang, Ju-Chin Chen, Chien-Chung Tseng, Jenn-Jier James Lien (National Cheng Kung University)
  • [MP1-11]: Face alignment using boosting and evolutionary search
    Hua Zhang, Duanduan Liu (Southeast University), Mannes Poel, Anton Nijholt (University of Twente)
  • [MP1-12]: Tracking eye gaze under coordinated head rotations with an ordinary camera
    Haibo Wang, Chunhong Pan (Institute of Automation, Chinese Academy of Sciences), Christophe Chaillou (University of Lille)
  • [MP1-13]: Orientation and scale invariant kernel-based object tracking with probabilistic emphasizing
    Kwang Moo Yi, Soo Wan Kim, Jin Young Choi (Seoul National University)
  • [MP1-14]: Combining edge and color features for tracking partially occluded humans
    Mandar Dixit, Venkatesh K. S. (IIT Kanpur)
  • [MP1-15]: Incremental multi-view face tracking based on general view manifold
    Wei Wei, Yanning Zhang (Northwestern Polytechnical University)
  • [MP1-16]: Hierarchical model for joint detection and tracking of multi-target
    Jianru Xue, Zheng Ma, Nanning Zheng (Xi'an Jiao Tong University)
  • [MP1-17]: Heavy-tailed model for visual tracking via robust subspace learning
    Daojing Wang, Chao Zhang (Peking University), Pengwei Hao (Peking University, Queen Mary, University of London)
  • [MP1-18]: Efficient scale-space spatiotemporal saliency tracking for distortion-free video retargeting
    Gang Hua (Microsoft Research), Cha Zhang, Zicheng Liu, Zhengyou Zhang (Microsoft Corporation), Ying Shan (Microsoft Research)
  • [MP1-19]: Visual saliency based object tracking
    Geng Zhang, Zejian Yuan, Nanning Zheng, Xingdong Sheng (Xi'an Jiao Tong University), Tie Liu (IBM China Research Lab)
  • [MP1-20]: People tracking and segmentation using efficient shape sequences matching
    Junqiu Wang, Yasushi Yagi, Yasushi Makihara (Osaka University)
  • [MP1-21]: Monocular template-based tracking of inextensible deformable surfaces under L2-norm
    Shuhan Shen, Wenhuan Shi, Yuncai Liu (Shanghai Jiao Tong University)
  • [MP1-22]: A graph-based feature combination approach to object tracking
    Quang Anh Nguyen, Antonio Robles-Kelly, Jun Zhou (Australian National University, National ICT Australia)
  • [MP1-23]: A smarter particle filter
    Xiaoqin Zhang, Weiming Hu (Institute of Automation, Chinese Academy of Sciences), Steve Maybank (Birkbeck College, UK)
  • [MP1-24]: Robust real-time multiple target tracking
    Nicolai von Hoyningen-Huene, Michael Beetz (TU Munich)
  • [MP1-25]: Dynamic kernel-based progressive particle filter for 3D human motion tracking
    Shih-Yao Lin (National Taiwan University), I-Cheng Chang (National Dong Hwa University)
  • [MP1-26]: Bayesian 3D human body pose tracking from depth image sequences
    Youding Zhu, Kikuo Fujimura (Honda Research Institute USA)
  • [MP1-27]: Crowd flow characterization with optimal control theory
    Pierre Allain, Nicolas Courty (Universit└ Europ└enne de Bretagne - VALORIA/UBS), Thomas Corpetti (CNRS/COSTEL - INRIA Rennes - LIAMA)
  • [MP1-28]: Human action recognition using HDP by integrating motion and location information
    Yasuo Ariki, Takuya Tonaru, Tetsuya Takiguchi (Kobe University)
  • [MP1-29]: Detecting spatiotemporal structure boundaries: beyond motion discontinuities
    Konstantinos G. Derpanis, Richard P. Wildes (York University)
  • [MP1-30]: An accelerated human motion tracking system based on voxel reconstruction under complex environments
    Junchi Yan, Yin Li, Enliang Zheng, Yuncai Liu (Shanghai Jiao Tong University)
  • [MP1-31]: Automated center of radial distortion estimation, using active targets
    Hamed Rezazadegan Tavakoli (Islamic Azad University, Mashhad), Hamid Reza Pourreza (Ferdowsi University of Mashhad)
  • [MP1-32]: Rotation averaging with application to camera-rig calibration    
    Yuchao Dai (Northwestern Polytechnical University and Australian National University), Jochen Trumpf (Australian National University), Hongdong Li, Nick Barnes (NICTA and Australian National University), Richard Hartley (Australian National University and NICTA)
  • [MP1-33]: Conics with a common axis of symmetry: properties and applications to camera calibration
    Zijian Zhao, Yuncai Liu (Shanghai Jiao Tong University)
  • [MP1-34]: Single-camera multi-baseline stereo using fish-eye lens and mirrors
      Wei Jiang (Zhejiang University), Masao Shimizu (Nihon University), Masatoshi Okutomi (Tokyo Institute of Technology)
  • [MP1-35]: Generation of an omnidirectional video without invisible areas using image inpainting
      Norihiko Kawai, Kotaro Machikita, Tomokazu Sato, Naokazu Yokoya (Nara Institute of Science and Technology)
  • [MP1-36]: Accurate and efficient cost aggregation strategy for stereo correspondence based on approximated joint bilateral filtering
    Stefano Mattoccia, Simone Giardino, Andrea Gambini (University of Bologna, Italy)
  • [MP1-37]: Detecting critical configurations for dividing long image sequences for factorization-based 3-D scene reconstruction
    Ping Li (Eindhoven University of Technology), Rene Klein Gunnewiek (Philips Research Europe), Peter de With (CycloMedia Technology B.V.)
  • [MP1-38]: Scene gist: a holistic generative model of natural image
    Bolei Zhou, Liqing Zhang (Shanghai Jiao Tong University)
  • [MP1-39]: A robust algorithm for color correction between two stereo images  
    Qi Wang, Xi Sun, Zengfu Wang (University of Science and Technology of China)
  • [MP1-40]: Efficient human action detection using a transferable distance function   Weilong Yang, Yang Wang, Greg Mori (Simon Fraser University)
  • [MP1-41]: Crease detection on noisy meshes via probabilistic scale selection
    Tao Luo, Huai-Yu Wu, Hongbin Zha (Peking University)
  • [MP1-42]: Improved uncalibrated view synthesis by extended positioning of virtual cameras and image quality optimization
    Fabian Gigengack, Xiaoyi Jiang (University of M┨nster)
  • [MP1-43]: Region based color image retrieval using curvelet transform
    Md Monirul Islam, Dengsheng Zhang, Guojun Lu (Monash University)
  • [MP1-44]: Extracting spatio-temporal local features considering consecutiveness of motions
    Akitsugu Noguchi, Keiji Yanai (The University of Electro-Communication)
  • [MP1-45]: Multi-view texturing of imprecise mesh
    Ehsan Aganj, Pascal Monasse, Renaud Keriven (IMAGINE, École des Ponts ParisTech)



Saturday, September 26 (Main Conference, Day Two)


8:30 C10:10

Oral Session 4: Segmentation

Chair: Prof. Q.M. Jonathan Wu (University of Windsor)

  • [MO4-1]: From ramp discontinuities to segmentation tree
    Emre Akbas, Narendra Ahuja (University of Illinois at Urbana-Champaign)
  • [MO4-2]: Natural image segmentation with adaptive texture and boundary encoding
    Shankar R. Rao, Hossein Mobahi (University of Illinois at Urbana-Champaign), Allen Y. Yang, S. Shankar Sastry (University of California, Berkeley), Yi Ma (University of Illinois at Urbana-Champaign, Microsoft Research Asia)
  • [MO4-3]: Gradient vector flow over manifold for active contours
    Shaopei Lu, Yuanquan Wang (Tianjin University of Technology)
  • [MO4-4]: 3D motion segmentation using intensity trajectory
    Hua Yang (Kitware Inc.), Greg Welch, Jan-Michael Frahm, Marc Pollefeys (University of North Carolina at Chapel Hill)

10:10 C10:30 Break


Oral Session 5: Feature Extraction & Object Detection

Chair: Prof. Takio Kurita (National Institute of Advanced Industrial Science and Technology, Japan)

  • [MO5-1]: Vehicle headlights detection using Markov random fields
    Wei Zhang, Q. M. Jonathan Wu, Guanghui Wang (University of Windsor)
  • [MO5-2]: A novel visual organization based on topological perception
    Yongzhen Huang, Kaiqi Huang, Tieniu Tan (Institute of Automation, Chinese Academy of Sciences), Dacheng Tao (Nanyang Technological University)
  • [MO5-3]: Multilevel algebraic invariants extraction by incremental fitting scheme
    Bo Zheng (The University of Tokyo), Jun Takamatsu (Nara Institute of Science and Technology), Katsushi Ikeuchi (The University of Tokyo)
  • [MO5-4]: Towards robust object detection: integrated background modeling based on spatio-temporal features
    Tatsuya Tanaka, Atsushi Shimada, Rin-ichiro Taniguchi (Kyushu University), Takayoshi Yamashita (OMRON Corporation), Daisaku Arita (Institute of Systems, Information Technologies and Nanotechnologies)

12:10 C 13:30 Lunch


Plenary Talk 2


Title: Image-based modeling

Speaker: Prof. Long Quan (Hong Kong University of Science and Technology)

14:30-14:50 Break


Oral Session 6: Image Enhancement & Visual Attention

Chair: Prof. Hong Zhang (University of Alberta)

  • [MO6-1]: Image enhancement of low-light scenes with near-infrared flash images
    Sousuke Matsui, Takahiro Okabe (The University of Tokyo), Mihoko Shimano (The University of Tokyo, PRESTO, Japan Science and Technology Agency), Yoichi Sato (The University of Tokyo)
  • [MO6-2]: A novel hierarchical model of attention: maximizing information acquisition
    Yang Cao, Liqing Zhang (Shanghai Jiao Tong University)
  • [MO6-3]: Interactive shadow removal from a single image using hierarchical graph cut
    Daisuke Miyazaki (The University of Tokyo), Yasuyuki Matsushita (Microsoft Research Asia), Katsushi Ikeuchi (The University of Tokyo)
  • [MO6-4]: Visual saliency based on conditional entropy
    Yin Li, Yue Zhou, Junchi Yan, Zhibin Niu, Jie Yang (Shanghai Jiao Tong University)

16:30-18:30 Poster Session 2: Segmentation, Detection, Color & Texture (Chang'an Hall, B Zone)

  • [MP2-1]: Semantic classification in aerial imagery by integrating appearance and height information
    Stefan Kluckner, Thomas Mauthner, Peter M. Roth, Horst Bischof (Institute for Computer Graphics and Vision, Austria)
  • [MP2-2]: Real-time video matting based on bilayer segmentation
    Viet-Quoc Pham, Keita Takahashi, Takeshi Naemura (The University of Tokyo)
  • [MP2-3]: Transductive segmentation of textured meshes
    Anne-Laure Chauve, Jean-Philippe Pons, Jean-Yves Audibert, Renaud Keriven (IMAGINE, ENPC/CSTB/LIGM, University Paris-Est)
  • [MP2-4]: Levels of details for gaussian mixture models
    Vincent Garcia (Ecole Polytechnique), Frank Nielsen (Ecole Polytechnique, Sony Computer Science Laboratories, Inc.), Richard Nock (Universite des Antilles-Guyane, CEREGMIA)
  • [MP2-5]: A blind robust watermarking scheme based on ica and image dividing blocks
    Yuqiang Cao, Weiguo Gong (Chongqing University)
  • [MP2-6]: MIFT: a mirror reflection invariant feature descriptor
    Xiaojie Guo, Xiaochun Cao, Jiawan Zhang, Xuewei Li (Tianjin university)
  • [MP2-7]: Detection of vehicle manufacture logos using contextual information
    Wenting Lu, Honggang Zhang, Kunyan Lan, Jun Guo (Beijing University of Posts and Telecommunications)
  • [MP2-8]: Part-based object detection using cascades of boosted classifiers
    Xiaozhen Xia (Institute of Automation, Chinese Academy of Sciences), Wuyi Yang (Xiamen University), Heping Li, Shuwu Zhang (Institute of Automation, Chinese Academy of Sciences)
  • [MP2-9]: A novel self-created tree structure based multi-view face detection
    Xu Yang, Xin Yang, Huilin Xiong (Shanghai Jiao Tong University)
  • [MP2-10]: Multilinear nonparametric feature analysis   
    Xu Zhang (Beijing Institute of Technology), Xiangqun Zhang (Xuchang University), Jian Cao, Yushu Liu (Beijing Institute of Technology)
  • [MP2-11]: A harris-like scale invariant feature detector
    Yinan Yu, Kaiqi Huang, Tieniu Tan (Institute of Automation, Chinese Academy of Sciences)
  • [MP2-12]: Probabilistic cascade random fields for man-made structure detection
    Songfeng Zheng (Missouri State University)
  • [MP2-13]: A novel system for robust text location and recognition of book covers
    Zhiyuan Zhang, Kaiyue Qi, Kai Chen, Chenxuan Li, Jianbo Chen, Haibin Guan (Shanghai Jiao Tong University)
  • [MP2-14]: A multi-scale bilateral structure tensor based corner detector
    Lin Zhang, Lei Zhang, David Zhang (The Hong Kong Polytechnic University)
  • [MP2-15]: Pedestrian recognition using second-order HOG feature
    Hui Cao, Koichiro Yamaguchi, Takashi Naito, Yoshiki Ninomiya (Toyota Central R&D LABS.,INC)
  • [MP2-16]: Fabric defect detection and classification using Gabor filters and gaussian mixture model
    Zhang Yu, Zhaoyang Lu, Jing Li (Xidian University)
  • [MP2-17]: Moving object segmentation in the H.264 compressed domain
    Changfeng Niu, Yushu Liu (Beijing Institute of Technology)
  • [MP2-18]: Video segmentation using iterated graph cuts based on spatio-temporal volumes
    Tomoyuki Nagahashi, Hironobu Fujiyoshi (Chubu University), Takeo Kanade (Carnegie Mellon University)
  • [MP2-19]: Spectral graph partitioning based on a random walk diffusion similarity measure
    Xi Li, Weiming Hu (Institute of Automation, Chinese Academy of Sciences), Zhongfei Zhang (State University of New York), Yang Liu (Institute of Automation, Chinese Academy of Sciences)
  • [MP2-20]: Iterated graph cuts for image segmentation  
    Bo Peng, Lei Zhang (The Hong Kong Polytechnic University), Jian Yang (Nanjing University of Science and Technology)
  • [MP2-21]: Contour extraction based on surround inhibition and contour grouping
    Yuan Li, Jianzhou Zhang, Ping Jiang (Sichuan University)
  • [MP2-22]: Confidence-based color modeling for online video segmentation
    Fan Zhong (Zhejiang University), Xueying Qin (Shandong University), Jiazhou Chen, Wei Hua, Qunsheng Peng (Zhejiang University)
  • [MP2-23]: Multicue graph mincut for image segmentation
    Wei Feng (City University of Hong Kong), Lei Xie (Northwestern Polytechnical University), Zhi-Qiang Liu (City University of Hong Kong)
  • [MP2-24]: Exploiting intensity inhomogeneity to extract textured objects from natural scenes
    Jundi Ding (Nanjing University of Science and Technology, Singapore Management University), Jialie Shen, Hwee Hwa Pang (Singapore Management University), Songcan Chen (Nanjing University of Aeronautics and Astronautics), Jingyu Yang (Nanjing University of Science and Technology)
  • [MP2-25]: Convolutional virtual electric field external force for active contours
    Yuanquan Wang (Tianjin University of Technology), Yunde Jia (Beijing Institute of Technology)
  • [MP2-26]: An effective segmentation for noise-based image verification using gamma mixture models
    Ling Cai, Yiren Xu (Shanghai Jiao Tong University), Lei He (The National Library of Medicine, National Institutes of Health, Bethesda), Yuming Zhao, Xin Yang (Shanghai Jiao Tong University),
  • [MP2-27]: Refined exponential filter with applications to image restoration and interpolation
    Yanlin Geng, Tong Lin (Peking University), Zhouchen Lin (Microsoft Research Asia), Pengwei Hao (Peking University, Queen Mary University of London),
  • [MP2-28]: Color correction and compression for multi-view video using H.264 features
    Boxin Shi, Yangxi Li, Lin Liu, Chao Xu (Peking Univeristy)
  • [MP2-29]: A subjective method for image segmentation evaluation
    Qi Wang, Zengfu Wang (University of Science and Technology of China)
  • [MP2-30]: Real-time object detection with adaptive background model and margined sign correlation
    Ayaka Yamamoto, Yoshio Iwai (Osaka University)
  • [MP2-31]: A 7-round parallel hardware-saving accelerator for gaussian and DoG pyramid construction part of SIFT
    Jingbang Qiu, Tianci Huang, Takeshi Ikenaga (Waseda University)
  • [MP2-32]: Weighted map for reflectance and shading separation using a single image
    Sung-Hsien Hsieh, Chih-Wei Fang, Te-Hsun Wang, Chien-Hung Chu, Jenn-Jier James Lien (National Cheng Kung University)
  • [MP2-33]: Polygonal light source estimation
    Dirk Schnieders, Kwan-Yee K. Wong, Zhenwen Dai (The University of Hong Kong)
  • [MP2-34]: Face relighting based on multi-spectral quotient image and illumination tensorfaces
    Ming Shao, Yunhong Wang, Peijiang Liu (Beihang University)
  • [MP2-35]: Perception-based lighting adjustment of image sequences  
    Xiaoyue Jiang (Northwestern Polytechnic University), Ping Fan, Ilse Ravyse, Hichem Sahli (ETRO Vrije Universiteit Brussel), Jianguo Huang, Rongchun Zhao, Yanning Zhang (Northwestern Polytechnic University)
  • [MP2-36]: Ultrasound speckle reduction via super resolution and nonlinear diffusion
    Bo Wang, Tian Cao, Yuguo Dai, Dong C. Liu (Sichuan University)
  • [MP2-37]: Background estimation based on device pixel structures for silhouette extraction
    Yasutomo Kawanishi, Takuya Funatomi (Kyoto University), Koh Kakusho (Kwansei University), Michihiko Minoh (Kyoto University)
  • [MP2-38]: Local spatial co-occuurence for background subtraction via adaptive binned kernel estimation
    Bineng Zhong, Shaohui Liu, Hongxun Yao (Harbin Institute of Technology)
  • [MP2-39]: Gable roof description by self-avoiding polygon
    Qiongchen Wang, Zhiguo Jiang, Junli Yang, Danpei Zhao, Zhenwei Shi (Beihang University)
  • [MP2-40]: Tracking endocardial boundary and motion via graph cut distribution matching and multiple model filtering
    Kumaradevan Punithakumar, Ismail Ben Ayed (GE Healthcare, London, Ontario, Canada), Ali Islam (St. Joseph's Health Care, London, Ontario, Canada), Ian Ross (London Health Science Center, London, Ontario, Canada), Shuo Li (GE Healthcare, London, Ontario, Canada; University of Western Ontario)
  • [MP2-41]: Object detection with multiple motion models
    Zhijie Wang, Hong Zhang (University of Alberta)
  • [MP2-42]: An improved template matching method for object detection
    Nguyen Duc Thanh, Wanqing Li, Philip Ogunbona (University of Wollongong, Australia)

19:30 C  Banquet (Tang Dynasty Theatre Restaurant)



Sunday, September 27 (Main Conference, Day Three)


8:30 C10:10

Oral Session 7: Machine Learning Algorithms for Vision

Chair: Prof. Guodong Guo (West Virginia University)

  • [MO7-1]: Evolving mean shift with adaptive bandwidth: a fast and noise robust approach
    Qi Zhao, Zhi Yang, Hai Tao, Wentai Liu (University of California at Santa Cruz)
  • [MO7-2]: An online framework for learning novel concepts over multiple cues
    Luo Jie (Idiap Research Institute; EPFL), Francesco Orabona, Barbara Caputo (Idiap Research Institute)
  • [MO7-3]: Efficient partial shape matching of outer contours
    Michael Donoser, Hayko Riemenschneider, Horst Bischof (Graz University of Technology)
  • [MO7-4]: Level set segmentation based on local Gaussian distribution fitting
    Li Wang (Nanjing University of Science and Technology), Jim Macione (University of Connecticut), Quansen Sun, Deshen Xia (Nanjing University of Science and Technology), Chunming Li (Vanderbilt University)

10:10 C10:30 Break


Oral Session 8: Object Categorization & Face Recognition

Chair: Prof. P.J. Narayanan (IIIT: International Institute of Information Technology)

  • [MO8-1]: Categorization of multiple objects in a scene without semantic segmentation
    Lei Yang, Nanning Zheng (Xi'an Jiao Tong University), Mei Chen (Intel Labs Pittsburgh), Yang Yang (Xi'an Jiao Tong University), Jie Yang (Carnegie Mellon University)
  • [MO8-2]: Distance-based multiple paths quantization of vocabulary tree for object and scene retrieval
    Heng Yang, Qing Wang (Northwestern Polytechnical University), Ellen Yi-Luen Do (Georgia Institute of Technology)
  • [MO8-3]: Image-set based face recognition using boosted global and local principal angles
    Xi Li (Xi'an Jiao Tong University, China), Kazuhiro Fukui (University of Tsukuba, Japan), Nanning Zheng (Xi'an Jiao Tong University, China)
  • [MO8-4]: Incorporating spatial correlogram into bag-of-features model for scene categorization
    Yingbin Zheng, Hong Lu, Cheng Jin, Xiangyang Xue (Fudan University)

12:10 C 13:30 Lunch


Plenary Talk 3


Title: Acquisition of 3D shape from uncalibrated video

Speaker: Prof. Roberto Cipolla (University of Cambridge)

14:30-14:50 Break


Oral Session 9: Biometrics & Surveillance

Chair: Prof. Brendan McCane (University of Otago)

  • [MO9-1]: Human action recognition under Log-Euclidean Riemannian metric
    Chunfeng Yuan, Weimin Hu, Xi Li (Institute of Automation, Chinese Academy of Sciences), Stephen Maybank (Birkbeck College), Guan Luo (Institute of Automation, Chinese Academy of Sciences)
  • [MO9-2]: Clustering-based descriptors for fingerprint indexing and fast retrieval
    Shihua He, Chao Zhang (Peking University), Pengwei Hao (Peking University, Queen Mary, University of London)
  • [MO9-3]: Temporal-spatial local Gaussian process experts for human pose estimation
    Xu Zhao (Shanghai Jiao Tong University), Yun Fu (BBN Technologies), Yuncai Liu (Shanghai Jiao Tong University)
  • [MO9-4]: Finger-vein recognition based on a bank of Gabor filters
    Jinfeng Yang, Yihua Shi, Jinli Yang (Civil Aviation University of China)

16:30-18:30 Poster Session 3: Machine Learning, Recognition, Biometrics & Surveillance (Chang'an Hall, B Zone)

  • [MP3-1]: Unfolding a face: from singular to manifold
    Ognjen Arandjelović (Trinity College, University of Cambridge)
  • [MP3-2]: Fingerspelling recognition through classification of letter-to-letter transitions
    Susanna Ricco, Carlo Tomasi (Duke University)
  • [MP3-3]: Human action recognition using non-separable oriented 3D dual-tree complex wavelets
    Rashid Minhas, Aryaz Baradarani, Sepideh Seifzadeh, Q.M.Jonathan Wu (University of Windsor Canada)
  • [MP3-4]: Gender from body: a biologically-inspired approach with manifold learning
    Guodong Guo (West Virginia University), Guowang Mu (North Carolina Central University), Yun Fu (BBN Technologies)
  • [MP3-5]: Fingerprint orientation field estimation: model of primary ridge for global structure and model of secondary ridge for correction
    Huanxi Liu, Xiaowei Lv, Xiong Li, Yuncai Liu (Shanghai Jiao Tong University)
  • [MP3-6]: Gait recognition using Procrustes shape analysis and shape context   
    Yuanyuan Zhang, Niqing Yang, Wei Li, Xiaojuan Wu (Shandong University), Qiuqi Ruan (Beijing Jiao Tong University)
  • [MP3-7]: Person de-identification in videos
    Prachi Agrawal, P. J. Narayanan (IIIT Hyderabad)
  • [MP3-8]: A variant of the trace quotient formulation for dimensionality reduction
    Peng Wang (Beihang University, Beijing, China), Chunhua Shen (NICTA, Canberra Research Laboratory / Australian National University), Hong Zheng, Zhang Ren (Beihang University)
  • [MP3-9]: Adaptive-scale robust estimator using distribution model fitting
    Thanh Trung Ngo, Hajime Nagahara, Ryusuke Sagawa, Yasuhiro Mukaigawa (Osaka University), Masahiko Yachida (Osaka Institute of Technology), Yasushi Yagi (Osaka University)
  • [MP3-10]: A scalable algorithm for learning a Mahalanobis distance metric
    Junae Kim (The Australian National University and NICTA), Chunhua Shen (NICTA and The Australian National University), Lei Wang (The Australian National University)
  • [MP3-11]: Lorentzian discriminant projection and its applications
    Risheng Liu, Zhixun Su (Dalian University of Technology), Zhouchen Lin (Microsoft Research Asia), Xiaoyu Hou (Dalian University of Technology)
  • [MP3-12]: Learning bundle manifold by double neighborhood graphs
    Chun-guang Li, Jun Guo, Hong-gang Zhang (Beijing University of Posts and Telecommunications)
  • [MP3-13]: Training support vector machines on large sets of image data
    Ignas Kukenys, Brendan McCane, Tim Neumegen (University of Otago)
  • [MP3-14]: Learning logic rules for scene interpretation based on Markov logic networks
    Mai Xu, Maria Petrou (Imperial College London)
  • [MP3-15]: Efficient classification of images with taxonomies
    Alexander Binder (Fraunhofer Institute FIRST), Motoaki Kawanabe (Fraunhofer Institute FIRST, TU Berlin), Ulf Brefeld (TU Berlin)
  • [MP3-16]: Adapting SVM image classifiers to changes in imaging conditions using incremental SVM: an application to car detection
    Epifanio Bagarinao, Takio Kurita (National Institute of Advanced Industrial Science and Technology, Japan), Masakatsu Higashikubo (Sumitomo Electric Industries, Ltd, Japan), Hiroaki Inayoshi (National Institute of Advanced Industrial Science and Technology, Japan)
  • [MP3-17]: Incrementally discovering object classes using similarity propagation and graph clustering
    Shengping Xia (National University of Defense Technology), Edwin R. Hancock (University of York)
  • [MP3-18]: Image classification using probability higher-order local auto-correlations
    Tetsu Matsukawa (University of Tsukuba), Takio Kurita (National Institute of Advanced Industrial Science and Technology)
  • [MP3-19]: Disparity estimation in a layered image for reflection stereo
    Masao Shimizu (Nihon University), Masatoshi Okutomi (Tokyo Institute of Technology), Wei Jiang (Zhejiang University)
  • [MP3-20]: Model-based 3D object localization using occluding contours
    Kenichi Maruyama, Yoshihiro Kawai, Fumiaki Tomita (National Institute of Advanced Industrial Science and Technology, Japan)
  • [MP3-21]: A probabilistic model for correspondence problems using random walks with restart
    Tae Hoon Kim, Kyoung Mu Lee, Sang Uk Lee (Seoul National University)
  • [MP3-22]: Highly-automatic MI based multiple 2D/3D image registration using self-initialized geodesic feature correspondences
    Hongwei Zheng, Ioan Cleju, Dietmar Saupe (University of Konstanz)
  • [MP3-23]: Better correspondence by registration
    Shufei Fan (McGill University), Rupert Brooks (National Research Council Canada), Frank P. Ferrie (McGill University)
  • [MP3-24]: Image content based curve matching using HMCD descriptor
    Zhiheng Wang, Hongmin Liu (Henan Polytechnic University), Fuchao Wu (Institute of Automation, Chinese Academy of Sciences)
  • [MP3-25]: Skeleton graph matching based on critical points using path similarity
    Yao Xu, Bo Wang, Wenyu Liu, Xiang Bai (Huazhong University of Science and Technology)
  • [MP3-26]: A statistical-structural constraint model for cartoon face wrinkle representation and generation      
    Ping Wei, Yuehu Liu, Nanning Zheng, Yang Yang (Xi'an Jiao Tong University)
  • [MP3-27]: Spatially varying regularization of image sequences super-resolution
    Yaozu An, Yao Lu (Beijing Institute of Technology), Zhengang Zhai (Beijing Institute of Technology, Air Defense Forces Command College)
  • [MP3-28]: Image search result summarization with informative priors
    Rui Liu (Tsinghua University, Microsoft Research Asia), Linjun Yang, Xian-Sheng Hua (Microsoft Research Asia)
  • [MP3-29]: Interactive super-resolution through neighbor embedding
    Jian Pu, Junping Zhang (Fudan University), Peihong Guo, Xiaoru Yuan (Peking University)
  • [MP3-30]: Scalable image retrieval based on feature forest
    Jinlong Song (Shanghai Jiao Tong University), Yong Ma (Core Technology Center, Omron Corporation, Kyoto, Japan), Fuqiao Hu, Yuming Zhao (Shanghai Jiao Tong University), Shihong Lao (Core Technology Center, Omron Corporation, Kyoto, Japan)
  • [MP3-31]: Super-resolution of multiple moving 3D objects with pixel-based registration
    Takuma Yamaguchi (The Nippon Signal Co., LTD.), Hiroshi Kawasaki (Saitama University), Ryo Furukawa (Hiroshima City University), Toshihiro Nakayama (The Nippon Signal Co., LTD.)
  • [MP3-32]: Human action recognition using pyramid vocabulary tree   
    Chunfeng Yuan, Xi Li, Weiming Hu (Institute of Automation, Chinese Academy of Sciences), Hanzi Wang (University of Adelaide)
  • [MP3-33]: Auto-scaled incremental tensor subspace learning for region based rate control application
    Peng Zhang, Sabu Emmanuel (Nanyang Technological University), Yanning Zhang (Northwestern Polytechnical University, Xi'an, China), Xuan Jing (Nanyang Technological University)
  • [MP3-34]: Visual focus of attention recognition in the ambient kitchen
    Ligeng Dong, Huijun Di, Linmi Tao, Guangyou Xu (Tsinghua University), Patrick Oliver (Newcastle University)
  • [MP3-35]: Polymorphous facial trait code
    Ping-Han Lee (National Taiwan University), Gee-Sern Hsu (National Taiwan University of Science and Technology), Yi-ping Hung (National Taiwan University)
  • [MP3-36]: Face recognition by estimating facial distinctive information distribution
    Bangyou Da, Nong Sang, Chi Li (Huazhong University of Science and Technology)
  • [MP3-37]: Robust 3D face recognition based on rejection and adaptive region selection
    Xiaoli Li, Feipeng Da (Southeast University)
  • [MP3-38]: Face recognition via AAM and multi-features fusion on Riemannian manifolds
    Hongwen Huo, Jufu Feng (Peking University)
  • [MP3-39]: Gender recognition via locality preserving tensor analysis on face images
    Huining Qiu (Sun Yat-sen University, Curtin University of Technology), Wan-quan Liu (Curtin University of Technology), Jian-Huang Lai (Sun Yat-sen University)
  • [MP3-40]: A chromosome image recognition method based on subregions 
    Toru Abe, Chieko Hamada, Tetsuo Kinoshita (Tohoku University )
  • [MP3-41]: Classifying pathological prostate images by texture features of multi-categories
    Po-Whei Huang, Cheng-Hsiung Lee (National Chung-Hsing University), Phen-Lan Lin (Providence University)
  • [MP3-42]: Putting local spatial relations for image classification by semi-supervised learning
    Dongfeng Han, Zhiliang Zhu, Guoqi Liu, Huiyan Jiang (Northeastern University), Wenhui Li (Jilin University)
  • [MP3-43]: Co-occurrence random forests for object localization and classification
    Yu-Wu Chu, Tyng-Luh Liu (Institute of Information Science, Academia Sinica)
  • [MP3-44]: Solving multilabel MRFs using incremental alpha-expansion on the GPUs
    Vibhav Vineet, P. J. Narayanan (International Institute of Information Technology, Hyderabad, India)
  • [MP3-45]: Non-rigid shape matching using geometry and photometry
    Nicolas Thorstensen, Renaud Keriven (Universite Paris-Est, Ecole des Ponts ParisTech, IMAGINE)
  • [MP3-46]: Beyond pairwise shape similarity analysis
    Peter Kontschieder, Michael Donoser, Horst Bischof (Graz University of Technology)
  • [MP3-47]: Globally optimal spatio-temporal reconstruction from cluttered videos
    Ehsan Aganj (IMAGINE, École des Ponts ParisTech), Jean-Philippe Pons (CSTB), Renaud Keriven (IMAGINE, École des Ponts ParisTech)

18:30C18:50 Closing



Demo Session (Friday, September 25 & Sunday, September 27; 16:30-18:30)

Location: Board Room

l         [D-1]: Example based 3D Motion Recovery by Searching with Compact and Discriminative Silhouette Feature

Cheng Chen, Yueting Zhuang, Jun Xiao (Zhejiang University)

l         [D-2]: Household Virtual Sports System

Jun Cheng (Shenzhen Institute of Advanced Integration Technology, Chinese Academy of Sciences / The Chinese University of Hong Kong)

l         [D-3]: Real-time image matching and tracking system for Augmented Reality

Yinan Yu , Kaiqi Huang, Tieniu Tan (Institute of Automation, Chinese Academy of Sciences)

l         [D-4-1]: Rotation Free Recognition of Handwritten Chinese Words

Lianwen Jin , Kai Ding, Tao Wang, Zhibin Huang, Shengmin Huang (South China University of Technology)

l         [D-4-2]: SCUT-SwiftPost!A Camera-based Real Time Postal Envelope Recognition System

Xue Gao, Lianwen Jin , Bin Zhang, Zhijie He, Zhibin Huang (South China University of Technology)

l         [D-5]: CGAL Point Set Processing and Surface Reconstruction

Nader Salman (INRIA Sophia Antipolis)

l         [D-6]: 3D Medical Image Processing and Analyzing System

Wenbo Ning, Jinzhou Li, Jie Li, Xinbo Gao (Xidian University)

l         [D-7]: FlyingSword: A Real-time Motion Video Registration, Stabilization, Mosaicing and Moving Object Tracking System

Tao Yang Yanning Zhang (Northwestern Polytechnical University)

l         [D-8]: AdAction: Interactive In-Image Advertising

Tao Mei, Xian-Sheng Hua (Microsoft Research Asia)




Workshops (Thursday, September 24)



(Location: Hua Shan Hall)


This workshop aims to explore creative technological solutions and potential applications of such a mobile internet environment. While traditional computer vision technology no doubt plays a central role in 3D content acquisition and processing, innovative solutions that fuse multimodal information and exploit mobile internet features are worthwhile as well. Topics of interests include all aspects of devices, data acquisition, processing, fusion and applications.



Opening Remarks



Invited Talk


Title: Multiple-view geometry and symmetry for image-based 3D reconstruction

Speaker: Yi Ma (University of Illinois at Urbana-Champaign)



Invited Talk


Title: Internet community based 3D content cocreation and consumption in mobile environment

Speaker: Lixin Fan (Nokia Research Center)

10:10C10:30 Group Photo and Tea Break


Session A


l         [W1-1]: Visual sun compass

Liang Wang, Hehua Ju (Beijing University of Technology)

l         [W1-2]: PCA-based linear adjustment for sparse reconstruction of 3D scene

Qinxun Bai, Yihong Wu (Institute of Automation, Chinese Academy of Sciences), and Lixin Fan (Nokia Research Center)

l         [W1-3]: Automatic 3D facial feature localization and face alignment using binary neural network

Quan Ju, Simon O'Keefe (The University of York)

12:10 C 13:30 Lunch


Session B


l           [W1-4]: Robust 3D motion capture from challenging video sequences

Xiaoming Deng, Shihong Xia, Wenzhong Wang, Wu Huang, Zhaoqi Wang (Institute of Computing Technology, Chinese Academy of Sciences)

l           [W1-5]: A biological stereo vision model based on Markov random field

Yansheng Ming (Institute of Automation, Chinese Academy of Sciences)

l           [W1-6]: Segmentation of point cloud scanned from trees

Minrui Dai, Xiaopeng Zhang, Yikuan Zhang (Institute of Automation, Chinese Academy of Sciences)

l           [W1-7]: Catadioptric camera calibration based on RANSAC

Fuqing Duan (Beijing normal university), Fuchao Wu (Institute of Automation, Chinese Academy of Sciences), Xiaoming Deng (Institute of Computing Technology, Chinese Academy of Sciences)

15:30-15:50 Break  

l           [W1-8]: Quasi-dense matching by match propagation for uncalibrated fisheye images

Jing Li, Xiaoming Li, Yaping Tian, Shunyong Li (ShanXi University)

l           [W1-9]: Feature correspondence via random sampling

Lixin Fan (Nokia Research Center)



Award Session





(Location: Board Room)


One of the remarkable capabilities of human visual perception system is to interpret and recognize thousands of events in videos, despite high level of video object clutters, different types of scene context, variability of motion scales, appearance changes, occlusions and object interactions. As an ultimate goal of computer vision system, the interpretation and recognition of visual events is one of the most challenging problems and has increasingly become very popular for decades. This task remains exceedingly difficult. Despite the difficulties, in recent years, steady progress has been made towards better models for video event categorisation and recognition, e.g., from modelling events with bag of spatial temporal features to discovering event context, from detecting events using a single camera to inferring events through a distributed camera network, and from low-level event feature extraction and description to high-level semantic event classification and recognition. The goal of this workshop is to provide a forum for recent research advances in the area of video event categorisation, tagging and retrieval.



Opening Remarks





Keynote Speech


Title: Concept based video retrieval

Speaker: Prof. Jianmin Li (Tsinghua University)





l           [W2-1]: Interactive inquiry of indoor scene transition with awareness and automatic correction of mis-understanding

Kazuhiro Maki, Nobutaka Shimada, Yoshiaki Shirai (Ritsumeikan University)

l           [W2-2]: Object movement event detection for household environments via layered-background model and keypoint-based tracking

Shigeyuki Odashima, Taketoshi Mori, Masamichi Shimosaka, Hiroshi Noguchi, Tomomasa Sato (University of Tokyo)

15:30-15:50 Break

l           [W2-3]: Discriminative visual words selection for visual categorization

Yanyun Qu, Xiaofeng Du, Zejian Yuan, Cuihua Li (Xiamen University)

l           [W2-4]: A dynamic texture model for fire recognition

Zhangxian Wu, Guotian Yang, Xiangjie Liu, Pengyuan Yang, Sifei Liu (North China Electric Power University)

l           [W2-5]: Vision-based group-behavior evaluation in delivery simulation training: a view-independent approach (invited paper)

Jungong Han, Minwei Feng, Peter De With (Eindhoven University of Technology)

l           [W2-6]: A face clustering algorithm using SIFT for video surveillance

Gaopeng Gou, Yunhong Wang, Jiangwei Li (Beihang University)

l           [W2-7]: Projected orthogonal shape contexts for human action description and categorization

Ruoyun Gao (Leiden University), Ling Shao (The University of Sheffield)





(Location: Qinhuang Hall)


Recent advances in sensor and modeling technologies enable the development of novel techniques that offer both feasibility and robust performance on reconstruction of large-scale environments. Improvements on the performance of traditional/novel vision techniques such as structure from motion, multi-view stereo, and image-based modeling have made high-end acquisition of 3D structure and motion a reality. Advances in sensor technologies such as depth camera, closer-range laser range finder, and Light Detection and Ranging (LIDAR) permit to deploy modeling systems on terrestrial, airborne, static, moving, and even handheld platforms to quickly capture 3D structure of a large environment with high degree of accuracy. Progresses in computer graphics enable effective representation, rendering and visualization of photorealistic models on PCs. The advances in high-speed network technology allow effective delivery of 3D models throughout the networked world. As part of the ACCV 2009, the Modeling-3D 2009 Workshop will bring together researchers to present results and innovations in all aspects of modeling and representation of large-scale 3D environments.



Opening Remarks


Suya You, Jonathan Wu, Wanquan Liu, Richard Xu



Session A


Chair: Jonathan Wu


         [W3-1]: Fast 3D shape recovery from shadow and shading projected on arbitrary curved surfaces

Yukihiro Yamashita, Fumihiko Sakaue, Jun Sato (Nagoya Institute of Technology)

         [W3-2]: Image-based modeling of Haussmannian facades

Chun Liu, Andr└ Gagalowicz (INRIA Rocquencourt)

         [W3-3]: Image-based modeling from a high-resolution route panorama

Ryuji Shibata, Hajime Nagahara (Osaka University)

12:10 C 13:30 Lunch


Invited Talk


Title: The gentlest introduction to expectation-maximization (EM) on mixture densities

Speaker: Richard Xu



Session B


Chair: Suya You

         [W3-4]: Surface reconstruction from multi-view stereo

Nader Salman, Mariette Yvinec (INRIA)

         [W3-5]: Refinement of surface mesh for accurate multi-view reconstruction

Radim Tylecek, Radim Sara (CMP FEE CTU)

15:30-15:50 Break


Session C


Chair: Richard Xu


         [W3-6]: Space time carving for simultaneous shape and motion recovery

Fumihiko Sakaue, Masaaki Takami, Jun Sato (Nagoya Institute of Technology)

         [W3-7]: Free-viewpoint rendering from omnidirectional video using a deformable 3-D mesh model

Hiroyuki Koshizawa (NAIST, Japan), Tomokazu Sato, Naokazu Yokoya (Nara Institute of Science and Technology, Japan)

         [W3-8]: An optimal rectangle-intersection algorithm using linear arrays only

Frank Devai (London South Bank University), Laszlo Neumann (Universitat de Girona and ICREA)





Suya You, Jonathan Wu, Wanquan Liu, Richard Xu




(Location: Tai Bai Shan Hall)


Human modeling in motion and expression is focused recently in both CV and CG areas that can be applied to user attainable entertainment (movie, TV-game or cell-phone application) and biometrics authentication system. Vision based system is very important to reduce the cost and pressure to the user without special equipments like suit, glove and markers. The goal of this workshop is to discuss about how to capture and model personality in motion and expression with vision based approach. The final goal is the markerless motion capture in body and face.



 Instant Casting and Face


Chair: Prof. Shigeo Morishima


l           [IW1-1]: Instant movie casting with personality: dive into the movie system

Shigeo Morishima (Waseda University), Yasushi Yagi (Osaka University), Satoshi Nakamura (National Institute of Information and Communications Technology)

l           [IW1-2]: An automatic individual character head modeling for instant casting

 Akinobu Maejima, Takanori Suzuki, Hiroto Yarimizu, Hiroyuki Kubo, Shigeo Morishima (Waseda University)

l           [IW1-3]: The online gait measurement for the audience-participant digital entertainment

Mayu Okumura, Yasushi Makihara, Yasushi Yagi (Osaka University), Shinsuke Nakamura, Shigeo Morishima (Waseda University)

10:10C10:30 Break

l           [IW1-4]: Scenario speech assignment technique for instant casting movie system

Shin-ichi Kawamoto (National Institute of Information and Communications Technology) , Yoshihiro Adachi (Waseda University), Yamato Ohtani, Tatsuo Yotsukura (Advanced Telecommunication Research Institute International), Shigeo Morishima (Waseda University), Satoshi Nakamura (Advanced Telecommunication Research Institute International)

l           [IW1-5]: Efficient facial feature localization and its application

Yingzhen Yang, Chunxiao Liu, Zhangye Wang, Guanyu Xing (Zhejiang University)

l           [IW1-6]: Facial expression recognition based on AAM and PCA for human computer interaction

Yun Ha Nam, Eun Jung Han (Dongguk University), Byung Jun Kang (Electronic and Telecommunications Research Institute), Min Cheol Whang (Sangmyoung University), Ryoung Park (Dongguk University)

12:10C13:30 Lunch


 Gesture and Authentication


Chair: Prof. Yasushi Yagi


l           [IW1-7]: Trimmed optical flow using localized region-based active contour

Hao Wang, Ling Shao (The University of Sheffield)

l           [IW1-8]: A study on eliminating the ghost region for iris recognition

Dae Sik Jeong (Dongguk University), Byung Jun Kang (ETRI), Kang Ryoung Park (Dongguk University)

l           [IW1-9]: A wearable gaze tracking system and its applications

Ji Woo Lee, Chul Woo Cho (Dongguk University), Eul Chul Lee, Min Cheol Whang (Sangmyung University), Kang Ryoung Park (Dongguk University)

l           [IW1-10]: Mobile biometric system and its performance evaluations

Gi Pyo Nam (Dongguk University), Byung Jun Kang (ETRI), Kang Ryoung Park (Dongguk University)




(Location: Li Shan Hall)


A new human-centered science and technology is needed to perform digital support tailored to individual activities. This requires adjustment of higher dimension, of various demands of service and security by creating access space that connects individuals-environment, individuals-society, individuals-individuals, and so on. Especially, the analysis of digital media and interface technology have received widespread attention because it targets human five senses directly. The creation of these disciplines above enables the development of personal access space and the offering of safe, secure and advanced services in the future. Today, high speed Internet allows us to access huge amount of rich content such as photos and videos, which are difficult to be handled personally. To handle such huge amount of content, Computer Vision plays an important role. Internet Vision is a research field of such research that utilizes these contents via Internet. In the Control System research field, high speed communication system realizes Haptics based Bilateral Control System. With this system, we can get pseudo haptic sense. These topics have been studied within each research field such as Human Interaction, Haptic Communication, Image Processing, and Computer Vision respectively but we believe that they are related. The objective of this workshop is to provide a forum for exchange of the latest results related to these research fields and discuss about the possibility of the cross-disciplinary study.



Opening Remarks



Invited Talk


TitleDetecting humans and visualizing human motions for people image analysis

Speaker: Hironobu Fujiyoshi(Chubu University)



Session A


l           [IW2-1]: Correcting incomplete text stroke by 3D tensor voting

Toan Nguyen Dinh, Jonghyun Park, GueeSang LeeChonnam National University

l           [IW2-2]: Four channel bilateral teleoperation with varying time delay: experiments

Ugur Tumerdem, Kouhei OhnishiKeio University

10:15C10:35 Break

l           [IW2-3]: Change detection based on SURF and color edge matching

Ryo Mitsumori, Hideaki Uchiyama, Hideo SaitoKeio University), Myriam Servieres, Guillaume MoreauEcole Centrale de Nantes - CERMA IRST

l           [IW2-4]: Pavement scene interpretation and obstacle detection by large margin image labeling

Ke Jia (Australia¨s ICT Center of Excellence, Australian National University), Li Cheng (Toyota Technological Institute at Chicago), Lei Wang, Nianjun Liu (Australia¨s ICT Center of Excellence, Australian National University)

l           [IW2-5]: Improved transparency for time delayed teleoperation

Baris Yalcin, Kouhei Ohnishi (Keio University)

12:10C13:30 Lunch



Invited Talk


Title: Real World Haptics for Medical Access Space

Speaker: Tomoyuki Shimono(Yokohama National University)



Session B

l           [IW2-6]: Robust tracking of multiple football players considering occlusion and crowded situations

Hirokatsu Kataoka, Yoshimitsu Aoki(Keio University)

l           [IW2-7]: Extracting vibration signal for tactile sensation from single image

Xin Yin, Kazuyoshi Nomura, Hiromi T.Tanaka (Ritsumeikan University), Naoki Saiwaki (Nara Women¨s University)

15:30-15:50 Break

l           [IW2-8]: Human support system using human joint model

Wataru Yamanouchi, Seiichiro Katsura (Keio University)

l           [IW2-9]: Image segmentation with improved star shape prior via graph cut

Xianpeng Lang, Feng Zhu (Shenyang Institute of Automation, Chinese Academy of Sciences)

l           [IW2-10]: Reproduction of multi degree-of-freedom haptic motion by motion copying system

Yuki Yokokura, Seiichiro Katsura (Keio University)



Panel Discussion