Hybrid textual-visual relevance learning for content-based image retrieval

被引:20
作者
Cui, Chaoran [1 ]
Lin, Peiguang [1 ]
Nie, Xiushan [1 ]
Yin, Yilong [2 ]
Zhu, Qingfeng [1 ]
机构
[1] Shandong Univ Finance & Econ, Sch Comp Sci & Technol, Jinan 250014, Shandong, Peoples R China
[2] Shandong Univ, Sch Comp Sci & Technol, Jinan 250101, Shandong, Peoples R China
关键词
Content-based image retrieval; Tag completion; Semantics modeling; Rank aggregation; Sparse linear method; REPRESENTATIONS;
D O I
10.1016/j.jvcir.2017.03.011
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Learning effective relevance measures plays a crucial role in improving the performance of content-based image retrieval (CBIR) systems. Despite extensive research efforts for decades, how to discover and incorporate semantic information of images still poses a formidable challenge to real-world CBIR systems. In this paper, we propose a novel hybrid textual-visual relevance learning method, which mines textual relevance from image tags and combines textual relevance and visual relevance for CBIR. To alleviate the sparsity and unreliability of tags, we first perform tag completion to fill the missing tags as well as correct noisy tags of images. Then, we capture users' semantic cognition to images by representing each image as a probability distribution over the permutations of tags. Finally, instead of early fusion, a ranking aggregation strategy is adopted to sew up textual relevance and visual relevance seamlessly. Extensive experiments on two benchmark datasets well verified the promise of our approach. (C) 2017 Elsevier Inc. All rights reserved.
引用
收藏
页码:367 / 374
页数:8
相关论文
共 50 条
[31]   Long-term learning in content-based image retrieval [J].
Li, Jing ;
Allinson, Nigel M. .
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY, 2008, 18 (2-3) :160-169
[32]   Unsupervised Feature Learning for Content-based Histopathology Image Retrieval [J].
Vanegas, Jorge A. ;
Arevalo, John ;
Gonzalez, Fabio A. .
2014 12TH INTERNATIONAL WORKSHOP ON CONTENT-BASED MULTIMEDIA INDEXING (CBMI), 2014,
[33]   A comprehensive study on learning to rank for content-based image retrieval [J].
Li, Yangxi ;
Zhou, Chao ;
Geng, Bo ;
Xu, Chao ;
Liu, Hong .
SIGNAL PROCESSING, 2013, 93 (06) :1426-1434
[34]   Unsupervised Visual Hashing with Semantic Assistant for Content-Based Image Retrieval [J].
Zhu, Lei ;
Shen, Jialie ;
Xie, Liang ;
Cheng, Zhiyong .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2017, 29 (02) :472-486
[35]   Content-based image retrieval model based on cost sensitive learning [J].
Jin, Cong ;
Jin, Shu-Wei .
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2018, 55 :720-728
[36]   Supporting visual query expression in a content-based image retrieval environment [J].
Venters, CC .
HUMAN-COMPUTER INTERACTION - INTERACT '99, 1999, :698-700
[37]   Content-based image retrieval with WISFC [J].
Zhang, H. (guwenjiao1989@126.com), 1600, Binary Information Press (10) :3871-3877
[38]   A new content-based image retrieval [J].
Zhang, Zhen-Hua ;
Quan, Yong ;
Li, Wen-Hui ;
Guo, Wu .
PROCEEDINGS OF 2006 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7, 2006, :4013-+
[39]   Content-based image retrieval - A survey [J].
Choras, Ryszard S. .
BIOMETRICS, COMPUTER SECURITY SYSTEMS AND ARTIFICIAL INTELLIGENCE APPLICATIONS, 2006, :31-44
[40]   Content-Based Histopathological Image Retrieval [J].
Nunez-Fernandez, Camilo ;
Farias, Humberto ;
Solar, Mauricio .
SENSORS, 2025, 25 (05)