Analysis of Human Actions for Video Indexing

Authors:
Zhuoyuan Chen;Peng Cui;Lifeng Sun;Shiqiang Yang
Affiliations:
Computer Science Department, Tsinghua University, Beijing, P.R. China;Computer Science Department, Tsinghua University, Beijing, P.R. China;Computer Science Department, Tsinghua University, Beijing, P.R. China;Computer Science Department, Tsinghua University, Beijing, P.R. China
Venue:
PCM '08 Proceedings of the 9th Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
Year:
2008

Citing 9
Cited 0

Learning Patterns of Activity Using Real-Time Tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence
The Recognition of Human Movement Using Temporal Templates

IEEE Transactions on Pattern Analysis and Machine Intelligence
Motion segmentation and pose recognition with motion history gradients

Machine Vision and Applications - Special issue: IEEE WACV
Recognizing Action at a Distance

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Actions Sketch: A Novel Action Representation

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Video Behaviour Profiling and Abnormality Detection without Manual Labelling

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Actions as Space-Time Shapes

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Beyond Tracking: Modelling Activity and Understanding Behaviour

International Journal of Computer Vision
Detecting unusual activity in video

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Automatically understanding human actions is crutial for efficiently indexing many types of videos, such as sports videos, home videos, movies etc. However, it is challenging due to their variances caused by different actors, different scales, and different views. In order to incorporate these variances, most methods in literature have to sacrifice the discriminability of action models. In this paper, we address the tradeoff between invariability and discriminability. We firstly propose a novel set of pixel-wise features which are invariant to actor appearances, scales, and motion directions. Then, multi-prototype action models are constructed to realize view invariance. By leaving the most challenging invariance from feature level to model level, we successfully maintain the discriminability of action models. The extensive experiments demonstrated the good performance of the proposed method.