Space-time robust representation for action recognition

Ballas, N; Yang, Y; Lan, ZZ; Delezoide, B; Preteux, F; Hauptmann, A

Space-time robust representation for action recognition

Ballas, N Yang, Y

Lan, ZZ Delezoide, B Preteux, F Hauptmann, A

Permalink

Publication Type:: Conference Proceeding
Citation:: Proceedings of the IEEE International Conference on Computer Vision, 2013, pp. 2704 - 2711
Issue Date:: 2013-01-01

Closed Access

	Filename	Description	Size
	sp.pdf	Published version	1.15 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Ballas, N	en_US
dc.contributor.author	Yang, Y https://orcid.org/0000-0001-5528-0546	en_US
dc.contributor.author	Lan, ZZ	en_US
dc.contributor.author	Delezoide, B	en_US
dc.contributor.author	Preteux, F	en_US
dc.contributor.author	Hauptmann, A	en_US
dc.date.issued	2013-01-01	en_US
dc.identifier.citation	Proceedings of the IEEE International Conference on Computer Vision, 2013, pp. 2704 - 2711	en_US
dc.identifier.isbn	9781479928392	en_US
dc.identifier.uri	http://hdl.handle.net/10453/119981
dc.description.abstract	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.	en_US
dc.relation.ispartof	Proceedings of the IEEE International Conference on Computer Vision	en_US
dc.relation.isbasedon	10.1109/ICCV.2013.336	en_US
dc.title	Space-time robust representation for action recognition	en_US
dc.type	Conference Proceeding
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US

Abstract:

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:

http://hdl.handle.net/10453/119981