This workshop is being held jointly with IEEE Workshop on Applications of Computer Vision (WACV 2007)

General Chairs

Jake Aggarwal
Narendra Ahuja
Tom Huang

Program Chairs
Allen Hanson
Mubarak Shah
Zhengyou Zhang

Publications Chair

Niels da Vitoria Lobo

Papers Due
October 1, 2006

Acceptance of papers

November 1, 2006

Camera Ready copy due
December 1, 2006

Contact Us

Call for Demos (new)
IEEE Workshop on Motion and Video Computing (WMVC 2007)

Authors Must Register by December 5, 2006.

Registration page

Author Instruction Kit

Accepted Papers:


38            Monocular Video Foreground/Background Segmentation by Tracking Spatial-Color Gaussian Mixture Models

55            A Two-stage Multi-view Analysis Framework for Human Activity and Interactions

26            Fusion of Multiple Camera Views for Kernel-Based 3D Tracking

11            Activity Recognition using Dynamic Bayesian Networks with Automatic State Selection.

30            An Analysis-by-Synthesis Approach to Tracking of Textiles

57            Video Representation with Dynamic Features from Multi-Frame Frame-Difference Images

23            Shape Background Modeling : The Shape of Things That Came

18            Real Time Viterbi Optimization of Hidden Markov Models for Multi Target Tracking

39            GPU Acceleration of Real-time Feature Based Algorithms

45            Map-Enhanced Detection and  Tracking from a Moving Platform with Local and Global Data Association

47            Cascaded change detection for foreground segmentation

24            Detection and Tracking of Moving Vehicles in Crowded Scenes

42            Enhanced Video Mosaicing using Camera Motion Properties

31            Object-based spatial segmentation of video guided by depth and motion information

33            Tracking vehicle targets with large aspect change

27            Human Limb Delineation and Joint Position Recovery Using Localized Boundary Models

34            Body Part Detection for Human Pose Estimation and Tracking

51            Non-orthogonal Binary Expansion of Gabor Filters with Applications in Object Tracking



21            Recovering the Basic Structure of Human Activities From a Video-Based Symbol String

53            Performance of Low-Level Motion Estimation Methods for Confocal Microscopy of Plant Cells in vivo.

14            Coupled Hidden Semi Markov Models for Activity Recognition

15            Gait Analysis For Human Identification Through  Manifold Learning and HMM

54            Activity Identification Utilizing Data Mining Techniques

35            Spectral Methods for 3-D Motion Segmentation of Sparse Scene-Flow

29            A New Evaluation Approach for Video Processing Algorithms

37            Analysis of Irregularities in Human Actions with Volumetric Motion History Images

44            Fusion-Based Parameter Estimation for Robust Visual Tracking

28            Motion Analysis In Compressed Video- An Hybrid Approach

43            A Multiscale Parametric Background Model for Stationary Foreground Object Detection

40            Strategies for improving face recognition from video

32            Practical Camera Auto Calibration Using Semidefinite Programming

56            An Alternative Formulation for Five Point Relative Pose Problem


Computer vision has a rich history of work on visual motion, dealing with the problems of computing optical flow (2D motion) and structure from motion (3D motion and shape) using a video sequence.   Recently, in addition to these traditional problems, the motion information present in a video sequence is also being used to solve several other problems: video synthesis, video segmentation, video compression, video registration, and video surveillance and monitoring.   Computer vision is playing an important and somewhat different role in solving these problems compared to the image analysis considered in the early days of vision research. Therefore, this year we are combining new emerging area of video computing with the traditional visual motion.

The purpose of this IEEE Workshop on Motion and Video Computing is to bring together researchers from several different sub-areas of motion and video computing to share innovative research results and exchange ideas.

The program will consist of high quality double blind-reviewed papers and posters, invited talks, panels and demonstrations covering applications of Computer Vision and related technologies, that include, but are not limited to:

Visual Motion
Optical Flow and Point Correspondences
Structure from motion
Non-rigid and articulated motion


Video Surveillance and Monitoring
Human activity Recognition


Video Segmentation
Object-based spatial segmentation of video
Temporal Segmentation of Video:
Shot, scene,and story detection
Scene categorization


Video Registration
Geo registration
Site Modeling


Video Compression
Model and Knowledge-based compression
Object-based compression


Video Synthesis
Image-based Rendering
View Morphing
Augmented Reality