Action Recognition by Weakly-Supervised Discriminative Region Localization

Hakan Boyraz, Syed Zain Masood, Baoyuan Liu, Marshall Tappen and Hassan Foroosh

In Proceedings British Machine Vision Conference 2014
http://dx.doi.org/10.5244/C.28.111

Abstract

We present a novel probabilistic model for recognizing actions by identifying and extracting information from discriminative regions in videos. The model is trained in a weakly-supervised manner: training videos are annotated only with training label without any action location information within the video. Additionally, we eliminate the need for any pre-processing measures to help shortlist candidate action locations. Our localization experiments on UCF Sports dataset show that the discriminative regions produced by this weakly supervised system are comparable in quality to action locations produced by systems that require training on datasets with fully annotated location information. Furthermore, our classification experiments on UCF Sports and two other major action recognition benchmark datasets, HMDB and UCF101, show that our recognition system significantly outperforms the baseline models and is better than or comparable to the state-of-the-art.

Session

Poster Session

Files

Extended Abstract (PDF, 1 page, 2.2M)

Paper (PDF, 13 pages, 3.1M)

Bibtex File

Citation

Hakan Boyraz, Syed Zain Masood, Baoyuan Liu, Marshall Tappen and Hassan Foroosh. Action Recognition by Weakly-Supervised Discriminative Region Localization. Proceedings of the British Machine Vision Conference. BMVA Press, September 2014.

BibTex

@inproceedings{BMVC.28.111
	title = {Action Recognition by Weakly-Supervised Discriminative Region Localization},
	author = {Boyraz, Hakan and Masood, Syed Zain and Liu, Baoyuan and Tappen, Marshall and Faroosh, Hassan},
	year = {2014},
	booktitle = {Proceedings of the British Machine Vision Conference},
	publisher = {BMVA Press},
	editors = {Valstar, Michel and French, Andrew and Pridmore, Tony}
	doi = { http://dx.doi.org/10.5244/C.28.111 }
}