Space-time robust representation for action recognition

Publication Type:
Conference Proceeding
Proceedings of the IEEE International Conference on Computer Vision, 2013, pp. 2704 - 2711
Issue Date:
Filename Description Size
sp.pdfPublished version1.15 MB
Adobe PDF
Full metadata record
We address the problem of action recognition in unconstrained videos. We propose a novel content driven pooling that leverages space-time context while being robust toward global space-time transformations. Being robust to such transformations is of primary importance in unconstrained videos where the action localizations can drastically shift between frames. Our pooling identifies regions of interest using video structural cues estimated by differ ent saliency functions. To combine the different structural information, we introduce an iterative structure learning algorithm, WSVM (weighted SVM), that determines the optimal saliency layout of an action model through a sparse regularizer. A new optimization method is proposed to solve the WSVM' highly non-smooth objective function. We evaluate our approach on standard action datasets (KTH, UCF50 and HMDB). Most noticeably, the accuracy of our algorithm reaches 51.8% on the challenging HMDB dataset which outperforms the state-of-the-art of 7.3% relatively. © 2013 IEEE.
Please use this identifier to cite or link to this item: