Learning Feature Representation and Partial Correlation for Multimodal Multi-Label Data

doi:10.1109/TMM.2020.3004963

	Learning Feature Representation and Partial Correlation for Multimodal Multi-Label Data
	Song, Guoli 1; Wang, Shuhui 2; Huang, Qingming 1,2,3; Tian, Qi 4
	2021
发表期刊	IEEE TRANSACTIONS ON MULTIMEDIA
ISSN	1520-9210
卷号	23 页码:1882-1894
摘要	User-provided annotations in existing multimodal datasets sometimes are inappropriate for model learning and can hinder the task of cross-modal retrieval. To handle this issue, we propose a discriminative and noise-robust cross-modal retrieval method, called FLPCL, which consists of deep feature learning and partial correlation learning. Deep feature learning is implemented by utilizing label supervised information to guide the training of deep neural network for each modality, which aims to find modality-specific deep feature representations that preserve the similarity and discrimination information among multimodal data. Based on deep feature learning, partial correlation learning is proposed to infer direct association between different modalities by removing the effect of common underlying semantics from each modality. It is achieved by maximizing the canonical correlation of the feature representations of different modalities conditioned on the label modality. Different from existing works that build indirect association between modalities via incorporating semantic labels, our FLPCL method can learn more effective and robust multimodal latent representations by explicitly preserving both intra-modal and inter-modal relationship among multimodal data. Extensive experiments on three cross-modal datasets show that our method outperforms state-of-the-art methods on cross-modal retrieval tasks.
关键词	Semantics Correlation Task analysis Data models Learning systems Kernel Deep learning Cross-modal retrieval correlation learning feature learning partial correlation
DOI	10.1109/TMM.2020.3004963
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China[2018AAA0102003] ; National Natural Science Foundation of China[61672497] ; National Natural Science Foundation of China[61836002] ; National Natural Science Foundation of China[61620106009] ; National Natural Science Foundation of China[U1636214] ; National Natural Science Foundation of China[61931008] ; Key Research Program of Frontier Sciences of CAS[QYZDJ-SSW-SYS013]
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:000668875100005
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：9[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/2XEOYT63/17514
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Wang, Shuhui
作者单位	1.Peng Cheng Lab, Shenzhen, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 101408, Peoples R China 4.Huawei, Cloud BU, Shenzhen 518129, Peoples R China
推荐引用方式 GB/T 7714	Song, Guoli,Wang, Shuhui,Huang, Qingming,et al. Learning Feature Representation and Partial Correlation for Multimodal Multi-Label Data[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2021,23:1882-1894.
APA	Song, Guoli,Wang, Shuhui,Huang, Qingming,&Tian, Qi.(2021).Learning Feature Representation and Partial Correlation for Multimodal Multi-Label Data.IEEE TRANSACTIONS ON MULTIMEDIA,23,1882-1894.
MLA	Song, Guoli,et al."Learning Feature Representation and Partial Correlation for Multimodal Multi-Label Data".IEEE TRANSACTIONS ON MULTIMEDIA 23(2021):1882-1894.