Joint Token and Feature Alignment Framework for Text-Based Person Search

doi:10.1109/LSP.2022.3217682

CASIA OpenIR > 智能感知与计算研究中心

	Joint Token and Feature Alignment Framework for Text-Based Person Search
	Li, Shangze 1; Lu, Andong 1; Huang, Yan3 ; Li, Chenglong 2; Wang, Liang3
发表期刊	IEEE SIGNAL PROCESSING LETTERS
ISSN	1070-9908
	2022
卷号	29 页码:2238-2242
通讯作者	Li, Chenglong(lcl1314@foxmail.com)
摘要	Text-based person search is a challenging cross-modal retrieval task. Existing works reduce the inter-modality and intra-class gaps by aligning local features extracted from image and text modalities, which easily lead to mismatching problems due to the lack of annotation information. Besides, it is sub-optimal to reduce two gaps simultaneously in the same feature space. This work proposes a novel joint token and feature alignment framework to reduce the inter-modality and intra-class gaps progressively. Specifically, we first build a dual-path feature learning network to extract features and conduct feature alignment to reduce the inter-modality gap. Second, we design a text generation module to generate token sequences using visual features, and then token alignment is performed to reduce the intra-class gap. Last, a fusion interaction module is introduced to further eliminate the modality heterogeneity using the strategy of multi-stage feature fusion. Extensive experiments on the CUHK-PEDES dataset demonstrate the effectiveness of our model, which significantly outperforms previous state-of-the-art methods.
关键词	Feature extraction Visualization Representation learning Logic gates Image reconstruction Transformers Training Cross-modal generation feature alignment text-based person search token alignment transformer
DOI	10.1109/LSP.2022.3217682
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61976003] ; National Natural Science Foundation of China[62076003] ; Anhui Provincial Key Research and Development Program[202104d07020008] ; Open Project Program of the National Laboratory of Pattern Recognition (NLPR) ; Gaofeng Discipline Construction Project (Computer Science and Technology)[Z010111016]
项目资助者	National Natural Science Foundation of China ; Anhui Provincial Key Research and Development Program ; Open Project Program of the National Laboratory of Pattern Recognition (NLPR) ; Gaofeng Discipline Construction Project (Computer Science and Technology)
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:000880641600004
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：2[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/173211/50679
专题	智能感知与计算研究中心
通讯作者	Li, Chenglong
作者单位	1.Anhui Univ, Sch Comp Sci & Technol, Anhui Prov Key Lab Multimodal Cognit Computat, Hefei 230601, Peoples R China 2.Anhui Univ, Sch Artificial Intelligence, Informat Mat & Intelligent Sensing Lab Anhui Prov, Anhui Prov Key Lab Multimodal Cognit Computat, Hefei 230601, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Li, Shangze,Lu, Andong,Huang, Yan,et al. Joint Token and Feature Alignment Framework for Text-Based Person Search[J]. IEEE SIGNAL PROCESSING LETTERS,2022,29:2238-2242.
APA	Li, Shangze,Lu, Andong,Huang, Yan,Li, Chenglong,&Wang, Liang.(2022).Joint Token and Feature Alignment Framework for Text-Based Person Search.IEEE SIGNAL PROCESSING LETTERS,29,2238-2242.
MLA	Li, Shangze,et al."Joint Token and Feature Alignment Framework for Text-Based Person Search".IEEE SIGNAL PROCESSING LETTERS 29(2022):2238-2242.