Web Image Search Re-Ranking With Click-Based Similarity and Typicality

doi:10.1109/TIP.2016.2593653

	Web Image Search Re-Ranking With Click-Based Similarity and Typicality
	Yang, Xiaopeng 1,2; Mei, Tao 3; Zhang, Yongdong 1; Liu, Jie 4; Satoh, Shin'ichi 5
	2016-10-01
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
卷号	25 期号:10 页码:4617-4630
摘要	In image search re-ranking, besides the well-known semantic gap, intent gap, which is the gap between the representation of users' query/demand and the real intent of the users, is becoming a major problem restricting the development of image retrieval. To reduce human effects, in this paper, we use image click-through data, which can be viewed as the implicit feedback from users, to help overcome the intention gap, and further improve the image search performance. Generally, the hypothesis-visually similar images should be close in a ranking list-and the strategy-images with higher relevance should be ranked higher than others-are widely accepted. To obtain satisfying search results, thus, image similarity and the level of relevance typicality are determinate factors correspondingly. However, when measuring image similarity and typicality, conventional re-ranking approaches only consider visual information and initial ranks of images, while overlooking the influence of click-through data. This paper presents a novel re-ranking approach, named spectral clustering re-ranking with click-based similarity and typicality. First, to learn an appropriate similarity measurement, we propose click-based multi-feature similarity learning algorithm, which conducts metric learning based on click-based triplets selection, and integrates multiple features into a unified similarity space via multiple kernel learning. Then, based on the learnt click-based image similarity measure, we conduct spectral clustering to group visually and semantically similar images into same clusters, and get the final re-rank list by calculating click-based clusters typicality and within-clusters click-based image typicality in descending order. Our experiments conducted on two real-world query-image data sets with diverse representative queries show that our proposed re-ranking approach can significantly improve initial search results, and outperform several existing re-ranking approaches.
关键词	Image search search re-ranking click-through data multi-feature similarity image typicality
DOI	10.1109/TIP.2016.2593653
收录类别	SCI
语种	英语
资助项目	National High Technology Research and Development Program of China[2014AA015202] ; National Natural Science Foundation of China[61525206] ; National Natural Science Foundation of China[61571424] ; National Natural Science Foundation of China[61428207] ; Beijing Advanced Innovation Center for Imaging Technology[BAICIT2016009]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000390221100006
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：14[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/2XEOYT63/7849
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Mei, Tao; Liu, Jie
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Microsoft Res, Beijing 100080, Peoples R China 4.Capital Normal Univ, Coll Informat & Engn, Beijing Adv Innovat Ctr Imaging Technol, Beijing 100048, Peoples R China 5.Natl Inst Informat, Tokyo 1018430, Japan
推荐引用方式 GB/T 7714	Yang, Xiaopeng,Mei, Tao,Zhang, Yongdong,et al. Web Image Search Re-Ranking With Click-Based Similarity and Typicality[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2016,25(10):4617-4630.
APA	Yang, Xiaopeng,Mei, Tao,Zhang, Yongdong,Liu, Jie,&Satoh, Shin'ichi.(2016).Web Image Search Re-Ranking With Click-Based Similarity and Typicality.IEEE TRANSACTIONS ON IMAGE PROCESSING,25(10),4617-4630.
MLA	Yang, Xiaopeng,et al."Web Image Search Re-Ranking With Click-Based Similarity and Typicality".IEEE TRANSACTIONS ON IMAGE PROCESSING 25.10(2016):4617-4630.