International Journal of Computer Vision
EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation
International Journal of Computer Vision
Key to effective video retrieval: effective cataloging and browsing
MULTIMEDIA '98 Proceedings of the sixth ACM international conference on Multimedia
W4: Real-Time Surveillance of People and Their Activities
IEEE Transactions on Pattern Analysis and Machine Intelligence
The Representation and Recognition of Human Movement Using Temporal Templates
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Cardboard People: A Parameterized Model of Articulated Image Motion
FG '96 Proceedings of the 2nd International Conference on Automatic Face and Gesture Recognition (FG '96)
FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
Extracting Gestural Motion Trajectories
FG '98 Proceedings of the 3rd. International Conference on Face & Gesture Recognition
Recognizing Human Actions in a Static Room
WACV '98 Proceedings of the 4th IEEE Workshop on Applications of Computer Vision (WACV'98)
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Multiple Camera Fusion for Multi-Object Tracking
WOMOT '01 Proceedings of the IEEE Workshop on Multi-Object Tracking (WOMOT'01)
A comprehensive study of visual event computing
Multimedia Tools and Applications
Hi-index | 0.00 |
In a number of applications including surveillance, there is a need to reliably retrieve an action-depicting segment in a video. This is an enormously difficult problem due to the variability in an action's appearance when seen at different times. It requires reliable object and action segmentation, and robust methods for indexing the action content in a video. In this paper, we present a novel approach to action retrieval that extracts salient action events in query and database videos. These events serve as anchor points to initiate action recognition. Actions are recognized by forming a spatio-temporal shape for an action called the action cylinder. Robust recognition is achieved by recovering the viewpoint transformation and time correspondence between a query action and a given action segment in the video. We demonstrate the versatility of our method for the retrieving of complex actions within videos.