Hierarchical Latent Concept Discovery for Video Event Detection

Li, C; Huang, Z; Yang, Y; Cao, J; Sun, X; Shen, HT

Hierarchical Latent Concept Discovery for Video Event Detection

Li, C Huang, Z Yang, Y Cao, J Sun, X Shen, HT

Permalink

Publication Type:: Journal Article
Citation:: IEEE Transactions on Image Processing, 2017, 26 (5), pp. 2149 - 2162
Issue Date:: 2017-05-01

Closed Access

	Filename	Description	Size
	07858791.pdf	Published Version	4.03 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	Li, C	en_US
dc.contributor.author	Huang, Z	en_US
dc.contributor.author	Yang, Y	en_US
dc.contributor.author	Cao, J	en_US
dc.contributor.author	Sun, X	en_US
dc.contributor.author	Shen, HT https://orcid.org/0000-0001-9872-8451	en_US
dc.date.issued	2017-05-01	en_US
dc.identifier.citation	IEEE Transactions on Image Processing, 2017, 26 (5), pp. 2149 - 2162	en_US
dc.identifier.issn	1057-7149	en_US
dc.identifier.uri	http://hdl.handle.net/10453/124501
dc.description.abstract	© 1992-2012 IEEE. Semantic information is important for video event detection. How to automatically discover, model, and utilize semantic information to facilitate video event detection has been a challenging problem. In this paper, we propose a novel hierarchical video event detection model, which deliberately unifies the processes of underlying semantics discovery and event modeling from video data. Specially, different from most of the approaches based on manually pre-defined concepts, we devise an effective model to automatically uncover video semantics by hierarchically capturing latent static-visual concepts in frame-level and latent activity concepts (i.e., temporal sequence relationships of static-visual concepts) in segment-level. The unified model not only enables a discriminative and descriptive representation for videos, but also alleviates error propagation problem from video representation to event modeling existing in previous methods. A max-margin framework is employed to learn the model. Extensive experiments on four challenging video event datasets, i.e., MED11, CCV, UQE50, and FCVID, have been conducted to demonstrate the effectiveness of the proposed method.	en_US
dc.relation.ispartof	IEEE Transactions on Image Processing	en_US
dc.relation.isbasedon	10.1109/TIP.2017.2670782	en_US
dc.subject.classification	Artificial Intelligence & Image Processing	en_US
dc.title	Hierarchical Latent Concept Discovery for Video Event Detection	en_US
dc.type	Journal Article
utslib.citation.volume	5	en_US
utslib.citation.volume	26	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
utslib.for	0906 Electrical and Electronic Engineering	en_US
utslib.for	1702 Cognitive Sciences	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/Faculty of Engineering and Information Technology/School of Software
utslib.copyright.status	closed_access
pubs.issue	5	en_US
pubs.publication-status	Published	en_US
pubs.volume	26	en_US

Abstract:

© 1992-2012 IEEE. Semantic information is important for video event detection. How to automatically discover, model, and utilize semantic information to facilitate video event detection has been a challenging problem. In this paper, we propose a novel hierarchical video event detection model, which deliberately unifies the processes of underlying semantics discovery and event modeling from video data. Specially, different from most of the approaches based on manually pre-defined concepts, we devise an effective model to automatically uncover video semantics by hierarchically capturing latent static-visual concepts in frame-level and latent activity concepts (i.e., temporal sequence relationships of static-visual concepts) in segment-level. The unified model not only enables a discriminative and descriptive representation for videos, but also alleviates error propagation problem from video representation to event modeling existing in previous methods. A max-margin framework is employed to learn the model. Extensive experiments on four challenging video event datasets, i.e., MED11, CCV, UQE50, and FCVID, have been conducted to demonstrate the effectiveness of the proposed method.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/124501