Exploiting visual word co-occurrence for image retrieval

Shi, M; Sun, X; Tao, D; Xu, C

Exploiting visual word co-occurrence for image retrieval

Shi, M Sun, X Tao, D

Xu, C

Permalink

Publication Type:: Conference Proceeding
Citation:: MM 2012 - Proceedings of the 20th ACM International Conference on Multimedia, 2012, pp. 69 - 78
Issue Date:: 2012-12-26

Closed Access

	Filename	Description	Size
	2012004361OK.pdf		2.81 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	Shi, M	en_US
dc.contributor.author	Sun, X	en_US
dc.contributor.author	Tao, D https://orcid.org/0000-0001-7225-5449	en_US
dc.contributor.author	Xu, C	en_US
dc.date.issued	2012-12-26	en_US
dc.identifier.citation	MM 2012 - Proceedings of the 20th ACM International Conference on Multimedia, 2012, pp. 69 - 78	en_US
dc.identifier.isbn	9781450310895	en_US
dc.identifier.uri	http://hdl.handle.net/10453/22961
dc.description.abstract	Bag-of-visual-words (BOVW) based image representation has received intense attention in recent years and has improved content based image retrieval (CBIR) significantly. BOVW does not consider the spatial correlation between visual words in natural images and thus biases the generated visual words towards noise when the corresponding visual features are not stable. In this paper, we construct a visual word co-occurrence table by exploring visual word co-occurrence extracted from small affine-invariant regions in a large collection of natural images. Based on this visual word co-occurrence table, we first present a novel high-order predictor to accelerate the generation of neighboring visual words. A co-occurrence matrix is introduced to refine the similarity measure for image ranking. Like the inverse document frequency (idf), it down-weights the contribution of the words that are less discriminative because of frequent co-occurrence. We conduct experiments on Oxford and Paris Building datasets, in which the ImageNet dataset is used to implement a large scale evaluation. Thorough experimental results suggest that our method outperforms the state-of-the-art, especially when the vocabulary size is comparatively small. In addition, our method is not much more costly than the BOVW model. © 2012 ACM.	en_US
dc.relation.ispartof	MM 2012 - Proceedings of the 20th ACM International Conference on Multimedia	en_US
dc.relation.isbasedon	10.1145/2393347.2393364	en_US
dc.title	Exploiting visual word co-occurrence for image retrieval	en_US
dc.type	Conference Proceeding
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
dc.location.activity	Nara, Japan	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
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US

Abstract:

Bag-of-visual-words (BOVW) based image representation has received intense attention in recent years and has improved content based image retrieval (CBIR) significantly. BOVW does not consider the spatial correlation between visual words in natural images and thus biases the generated visual words towards noise when the corresponding visual features are not stable. In this paper, we construct a visual word co-occurrence table by exploring visual word co-occurrence extracted from small affine-invariant regions in a large collection of natural images. Based on this visual word co-occurrence table, we first present a novel high-order predictor to accelerate the generation of neighboring visual words. A co-occurrence matrix is introduced to refine the similarity measure for image ranking. Like the inverse document frequency (idf), it down-weights the contribution of the words that are less discriminative because of frequent co-occurrence. We conduct experiments on Oxford and Paris Building datasets, in which the ImageNet dataset is used to implement a large scale evaluation. Thorough experimental results suggest that our method outperforms the state-of-the-art, especially when the vocabulary size is comparatively small. In addition, our method is not much more costly than the BOVW model. © 2012 ACM.

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

http://hdl.handle.net/10453/22961