Modeling spatial and semantic cues for large-scale near-duplicated image retrieval

doi:10.1016/j.cviu.2010.11.003

	Modeling spatial and semantic cues for large-scale near-duplicated image retrieval
	Zhang, Shiliang 2; Tian, Qi 1; Hua, Gang 3; Zhou, Wengang 4; Huang, Qingming 5; Li, Houqiang 4; Gao, Wen 2
	2011-03-01
发表期刊	COMPUTER VISION AND IMAGE UNDERSTANDING
ISSN	1077-3142
卷号	115 期号:3 页码:403-414
摘要	Bag-of-visual Words (BOW) image representation has been illustrated as one of the most promising solutions for large-scale near-duplicated image retrieval. However, the traditional visual vocabulary is created in an unsupervised way by clustering a large number of image local features. This is not ideal because it largely ignores the semantic and spatial contexts between local features. In this paper, we propose the geometric visual vocabulary which captures the spatial contexts by quantizing local features in bi-space, i.e., in descriptor space and orientation space. Then, we propose to capture the semantic context by learning a semantic-aware distance metric between local features, which could reasonably measure the semantic similarities between image patches, from which the local features are extracted. The learned distance is hence utilized to cluster the local features for semantic visual vocabulary generation. Finally, we combine the spatial and semantic contexts in a unified framework by extracting local feature groups, computing the spatial configurations between the local features inside the group, and learning a semantic-aware distance between groups. The learned group distance is then utilized to cluster the extracted local feature groups to generate a novel visual vocabulary. i.e., the contextual visual vocabulary. The proposed visual vocabularies, i.e., geometric visual vocabulary, semantic visual vocabulary and contextual visual vocabulary are tested in large-scale near-duplicated image retrieval applications. The geometric visual vocabulary and semantic visual vocabulary achieve better performance than the traditional visual vocabulary. Moreover, the contextual visual vocabulary, which combines both spatial and semantic clues outperforms the state-of-the-art bundled feature in both retrieval precision and efficiency. (C) 2010 Elsevier Inc. All rights reserved.
关键词	Visual vocabulary Near-duplicated image retrieval Local feature Distance metric learning
DOI	10.1016/j.cviu.2010.11.003
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61025011] ; National Natural Science Foundation of China[60833006] ; National Basic Research Program of China (973 Program)[2009CB320906] ; Beijing Natural Science Foundation[4092042] ; NSF IIS[1052851] ; Akiira Media Systems, Inc.
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000287772400011
出版者	ACADEMIC PRESS INC ELSEVIER SCIENCE
引用统计	被引频次：12[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/12757
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Tian, Qi
作者单位	1.Univ Texas San Antonio, Dept Comp Sci, San Antonio, TX 78249 USA 2.CAS, Inst Comput Tech, Key Lab Intell Info Proc, Beijing 100190, Peoples R China 3.IBM Watson Res Ctr, Elmsford, NY 10523 USA 4.Univ Sci & Technol China, Dept EEIS, Hefei 230026, Peoples R China 5.Chinese Acad Sci, Grad Univ, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Shiliang,Tian, Qi,Hua, Gang,et al. Modeling spatial and semantic cues for large-scale near-duplicated image retrieval[J]. COMPUTER VISION AND IMAGE UNDERSTANDING,2011,115(3):403-414.
APA	Zhang, Shiliang.,Tian, Qi.,Hua, Gang.,Zhou, Wengang.,Huang, Qingming.,...&Gao, Wen.(2011).Modeling spatial and semantic cues for large-scale near-duplicated image retrieval.COMPUTER VISION AND IMAGE UNDERSTANDING,115(3),403-414.
MLA	Zhang, Shiliang,et al."Modeling spatial and semantic cues for large-scale near-duplicated image retrieval".COMPUTER VISION AND IMAGE UNDERSTANDING 115.3(2011):403-414.