Technical program of MLVMA'09

　

Monday, September 28

Location: Kyoto University Clock Tower Centennial Hall

　

Schedule:

　

09:30  Opening Remarks

 

S1: Keynote Session (09:40-10:30)

09:40 Keynote: Detecting and Recognizing Moving Humans, Li Fei-Fei (University of Princeton, USA)

 

　

S2: Motion Estimation (10:30-11:10)

 

10:30 Combining Discriminative Appearance and Segmentation Cues for Articulated Human Pose Estimation, Sam Johnson, Mark Everingham (University of Leeds, UK)

 

10:50 Two-layer Generative Models for Estimating Unknown Gait Kinematics, Xin Zhang and Guoliang Fan (Oklahoma State University, USA)

　

 

11:10 - 11:30 Coffee Break


　

S3:  Learning Methods (11:30-12:30)

 

11:30 Fitting Parametric Road Models to Spatio-temporal Derivatives, Manfred Georg and Robert Pless (Washington University in St. Louis, USA)

 

11:50 On-Line Learning of the Transition Model for Recursive Bayesian Estimation, Samuele Salti and Luigi Di Stefano (DEIS, University of Bologna, Italy)

 

12:10 Sparse Learning Approach to the Problem of Robust Estimation of Camera Locations, Arnak Dalalyan and Renaud Keriven (Universit└ Paris Est, Ecole des Ponts ParisTech, France)

 

　

　

12:30 - 14:00 Lunch Break

　

 

　

S4: Motion tracking (14:10-14:50)

 

14:10 Learning mixed-state Markov models for statistical motion texture tracking, Tomas Crivelli, Patrick Bouthemy, Bruno Cernuschi-Frias and Jian-feng Yao (University of Buenos Aires, INRIA, IRMAR University of Rennes I)

 

14:30 H-APF: Using Hierarchical Representation of Human Body for 3-D Articulated Tracking, Leonid Raskin, Michael Rudzsky and Ehud Rivlin (Technion IIT, Israel)

　

　

 

S5: Segmentation (14:50-15:30)

 

14:50 An Improved Local Descriptor and Threshold Learning for Unsupervised Dynamic Texture Segmentation, Jie Chen, Guoying Zhao and Matti Pietikäinen (University of Oulu, Finland)

 

15:10 Randomized Algorithm of Spectral Clustering and Image/Video Segmentation Using a Minority of Pixels, Tomoya Sakai and Atsushi Imiya (IMIT Chiba University, Japan)

 

　

15:30 - 16:00 Coffee Break

　

 

S6: Action recognition (16:00-17:20)

 

16:00 Supervised Neighborhood Topology Learning for Human Action Recognition, J H Ma, Pong C Yuen, W W Zou and J H Lai (Zhongshan University, Hong Kong Baptist University and Sun Yat-Sen University)

 

16:20 Human Action Recognition from a Single Clip per Action, Weilong Yang, Yang Wang and Greg Mori (Simon Fraser University, Canada)

 

16:40 Evaluation of Threshold Model HMMs and Conditional Random Fields for Recognition of Spatiotemporal Gestures in Sign Language, Daniel Kelly, John Mc Donald and Charles Markham (National University of Ireland, Ireland)

 

17:00 Action Exemplar based Real-time Action Detection, Sang-Hack Jung, Yanlin Guo, Harpreet Sawhney, Rakesh Kumar (Sarnoff Corporation, USA)