Deep Structured Models For Group Activity Recognition

Zhiwei Deng, Mengyao Zhai, Lei Chen, Yuhao Liu, Srikanth Muralidharan, Mehrsan Javan Roshtkhari and Greg Mori

Abstract

This paper presents a deep neural-network-based hierarchical graphical model for individual and group activity recognition in surveillance scenes. Deep networks are used to recognize the actions of individual people in a scene. Next, a neural-network-based hierarchical graphical model refines the predicted labels for each class by considering dependencies between the classes. This refinement step mimics a message-passing step similar to inference in a probabilistic graphical model. We show that this approach can be effective in group activity recognition, with the deep graphical model improving recognition rates over baseline methods.

Session

Action and Event

Files

PDF iconExtended Abstract (PDF, 1206K)
PDF iconPaper (PDF, 3M)

DOI

10.5244/C.29.179
https://dx.doi.org/10.5244/C.29.179

Citation

Zhiwei Deng, Mengyao Zhai, Lei Chen, Yuhao Liu, Srikanth Muralidharan, Mehrsan Javan Roshtkhari and Greg Mori. Deep Structured Models For Group Activity Recognition. In Xianghua Xie, Mark W. Jones, and Gary K. L. Tam, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 179.1-179.12. BMVA Press, September 2015.

Bibtex

@inproceedings{BMVC2015_179,
	title={Deep Structured Models For Group Activity Recognition},
	author={Zhiwei Deng and Mengyao Zhai and Lei Chen and Yuhao Liu and Srikanth Muralidharan and Mehrsan  Javan Roshtkhari and Greg Mori},
	year={2015},
	month={September},
	pages={179.1-179.12},
	articleno={179},
	numpages={12},
	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
	publisher={BMVA Press},
	editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
	doi={10.5244/C.29.179},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.179}
}