Cross-Modality Bridging and Knowledge Transferring for Image Understanding

doi:10.1109/TMM.2019.2903448

	Cross-Modality Bridging and Knowledge Transferring for Image Understanding
	Yan, Chenggang 1; Li, Liang 2,3; Zhang, Chunjie4 ; Liu, Bingtao 1; Zhang, Yongdong 5; Dai, Qionghai 6
发表期刊	IEEE TRANSACTIONS ON MULTIMEDIA
ISSN	1520-9210
	2019-10-01
卷号	21 期号:10 页码:2675-2685
通讯作者	Li, Liang(liang.li@ict.ac.cn)
摘要	The understanding of web images has been a hot research topic in both artificial intelligence and multimedia content analysis domains. The web images are composed of various complex foregrounds and backgrounds, which makes the design of an accurate and robust learning algorithm a challenging task. To solve the above significant problem, first, we learn a cross-modality bridging dictionary for the deep and complete understanding of a vast quantity of web images. The proposed algorithm leverages the visual features into the semantic concept probability distribution, which can construct a global semantic description for images while preserving the local geometric structure. To discover and model the occurrence patterns between intra- and inter-categories, multi-task learning is introduced for formulating the objective formulation with Capped-l(1) penalty, which can obtain the optimal solution with a higher probability and outperform the traditional convex function-based methods. Second, we propose a knowledge-based concept transferring algorithm to discover the underlying relations of different categories. This distribution probability transferring among categories can bring the more robust global feature representation, and enable the image semantic representation to generalize better as the scenario becomes larger. Experimental comparisons and performance discussion with classical methods on the ImageNet, Caltech-256, SUN397, and Scene15 datasets show the effectiveness of our proposed method at three traditional image understanding tasks.
关键词	Object and scene recognition image semantic search cross-modality bridging multi-task learning knowledge transferring
DOI	10.1109/TMM.2019.2903448
关键词[WOS]	RETRIEVAL ; CLASSIFICATION ; OBJECT
收录类别	SCI
语种	英语
资助项目	National Basic Research Program of China (973-Program)[2015CB351802] ; National Natural Science Foundation of China[61771457] ; National Natural Science Foundation of China[61732007] ; National Natural Science Foundation of China[61572488] ; National Natural Science Foundation of China[61472389] ; National Natural Science Foundation of China[61872362] ; National Natural Science Foundation of China[U163621] ; National Natural Science Foundation of China[61671196] ; National Natural Science Foundation of China[61525206] ; National Natural Science Foundation of China[61672497] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-SYS013] ; Zhejiang Province Nature Science Foundation of China[LR17F030006] ; National Key Research and Development Program of China[2017YFC0820600] ; National Basic Research Program of China (973-Program)[2015CB351802] ; National Natural Science Foundation of China[61771457] ; National Natural Science Foundation of China[61732007] ; National Natural Science Foundation of China[61572488] ; National Natural Science Foundation of China[61472389] ; National Natural Science Foundation of China[61872362] ; National Natural Science Foundation of China[U163621] ; National Natural Science Foundation of China[61671196] ; National Natural Science Foundation of China[61525206] ; National Natural Science Foundation of China[61672497] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-SYS013] ; Zhejiang Province Nature Science Foundation of China[LR17F030006] ; National Key Research and Development Program of China[2017YFC0820600]
项目资助者	National Basic Research Program of China (973-Program) ; National Natural Science Foundation of China ; Key Research Program of Frontier Sciences, CAS ; Zhejiang Province Nature Science Foundation of China ; National Key Research and Development Program of China
WOS研究方向	Computer Science ; Telecommunications
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications
WOS记录号	WOS:000489728400020
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：102[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/26595
专题	复杂系统认知与决策实验室_高效智能计算与学习
通讯作者	Li, Liang
作者单位	1.Hangzhou Dianzi Univ, Inst Informat & Control, Hangzhou 310005, Zhejiang, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Coll Comp & Control Engn, Beijing 100190, Peoples R China 4.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 5.Chinese Acad Sci, Inst Comp Technol, Adv Comp Res Lab, Beijing 100190, Peoples R China 6.Tsinghua Univ, Dept Automat, Beijing 100084, Peoples R China
推荐引用方式 GB/T 7714	Yan, Chenggang,Li, Liang,Zhang, Chunjie,et al. Cross-Modality Bridging and Knowledge Transferring for Image Understanding[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2019,21(10):2675-2685.
APA	Yan, Chenggang,Li, Liang,Zhang, Chunjie,Liu, Bingtao,Zhang, Yongdong,&Dai, Qionghai.(2019).Cross-Modality Bridging and Knowledge Transferring for Image Understanding.IEEE TRANSACTIONS ON MULTIMEDIA,21(10),2675-2685.
MLA	Yan, Chenggang,et al."Cross-Modality Bridging and Knowledge Transferring for Image Understanding".IEEE TRANSACTIONS ON MULTIMEDIA 21.10(2019):2675-2685.