Title
Action Recognition By Weakly-Supervised Discriminative Region Localization
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 comparable to the state-of-the-art.
Publication Date
1-1-2014
Publication Title
BMVC 2014 - Proceedings of the British Machine Vision Conference 2014
Number of Pages
-
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
Copyright Status
Unknown
Socpus ID
84919740284 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84919740284
STARS Citation
Boyraz, Hakan; Masood, Syed Zain; Liu, Baoyuan; Tappen, Marshall; and Foroosh, Hassan, "Action Recognition By Weakly-Supervised Discriminative Region Localization" (2014). Scopus Export 2010-2014. 9158.
https://stars.library.ucf.edu/scopus2010/9158