Zero-shot event detection via event-adaptive concept relevance mining

Li, Z; Yao, L; Chang, X; Zhan, K; Sun, J; Zhang, H

Zero-shot event detection via event-adaptive concept relevance mining

Li, Z Yao, L Chang, X

Zhan, K Sun, J Zhang, H

Permalink

Publisher:: ELSEVIER SCI LTD
Publication Type:: Journal Article
Citation:: Pattern Recognition, 2019, 88, pp. 595-603
Issue Date:: 2019-04-01

Closed Access

	Filename	Description	Size
	1-s2.0-S003132031830431X-main.pdf	Published version	2.14 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, Z
dc.contributor.author	Yao, L
dc.contributor.author	Chang, X https://orcid.org/0000-0002-7778-8807
dc.contributor.author	Zhan, K
dc.contributor.author	Sun, J
dc.contributor.author	Zhang, H
dc.date.accessioned	2022-09-06T02:42:08Z
dc.date.available	2022-09-06T02:42:08Z
dc.date.issued	2019-04-01
dc.identifier.citation	Pattern Recognition, 2019, 88, pp. 595-603
dc.identifier.issn	0031-3203
dc.identifier.issn	1873-5142
dc.identifier.uri	http://hdl.handle.net/10453/161408
dc.description.abstract	Zero-shot complex event detection has been an emerging task in coping with the scarcity of labeled training videos in practice. Aiming to progress beyond the state-of-the-art zero-shot event detection, we propose a new zero-shot event detection approach, which exploits the semantic correlation between an event and concepts. Based on the concept detectors pre-trained from external sources, our method learns the semantic correlation from the concept vocabulary and emphasizes on the most related concepts for the zero-shot event detection. Particularly, a novel Event-Adaptive Concept Integration algorithm is introduced to estimate the effectiveness of semantically related concepts by assigning different weights to them. As opposed to assigning weights by an invariable strategy, we compute the weights of concepts using the area under score curve. The assigned weights are incorporated into the confidence score vector statistically to better characterize the event-concept correlation. Our algorithm is proved to be able to harness the related concepts discriminatively tailored for a target event. Extensive experiments are conducted on the challenging TRECVID event video datasets, which demonstrate the advantage of our approach over the state-of-the-art methods.
dc.language	English
dc.publisher	ELSEVIER SCI LTD
dc.relation.ispartof	Pattern Recognition
dc.relation.isbasedon	10.1016/j.patcog.2018.12.010
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0801 Artificial Intelligence and Image Processing, 0806 Information Systems, 0906 Electrical and Electronic Engineering
dc.subject.classification	Artificial Intelligence & Image Processing
dc.title	Zero-shot event detection via event-adaptive concept relevance mining
dc.type	Journal Article
utslib.citation.volume	88
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0806 Information Systems
utslib.for	0906 Electrical and Electronic Engineering
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 - AAII - Australian Artificial Intelligence Institute
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	closed_access	*
dc.date.updated	2022-09-06T02:41:50Z
pubs.publication-status	Published
pubs.volume	88

Abstract:

Zero-shot complex event detection has been an emerging task in coping with the scarcity of labeled training videos in practice. Aiming to progress beyond the state-of-the-art zero-shot event detection, we propose a new zero-shot event detection approach, which exploits the semantic correlation between an event and concepts. Based on the concept detectors pre-trained from external sources, our method learns the semantic correlation from the concept vocabulary and emphasizes on the most related concepts for the zero-shot event detection. Particularly, a novel Event-Adaptive Concept Integration algorithm is introduced to estimate the effectiveness of semantically related concepts by assigning different weights to them. As opposed to assigning weights by an invariable strategy, we compute the weights of concepts using the area under score curve. The assigned weights are incorporated into the confidence score vector statistically to better characterize the event-concept correlation. Our algorithm is proved to be able to harness the related concepts discriminatively tailored for a target event. Extensive experiments are conducted on the challenging TRECVID event video datasets, which demonstrate the advantage of our approach over the state-of-the-art methods.

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

http://hdl.handle.net/10453/161408