Person Search by a Bi-Directional Task-Consistent Learning Model

doi:10.1109/TMM.2021.3140025

	Person Search by a Bi-Directional Task-Consistent Learning Model
	Wang, Cheng 1; Ma, Bingpeng 1; Chang, Hong 2,3; Shan, Shiguang 2,3,4; Chen, Xilin 2,3
	2023
发表期刊	IEEE TRANSACTIONS ON MULTIMEDIA
ISSN	1520-9210
卷号	25 页码:1190-1203
摘要	Two-stage person search methods achieve the state-of-the-art performance by separate detection and re-ID stages, but neglect the consistency needs between these two stages. The re-ID stage needs more accurate query bounding boxes and fewer boxes of distractors; The detection stage needs the re-ID stage to have robustness against unavailable detection errors. In this paper, we introduce a novel Bi-directional Task-Consistent Learning (BTCL) person search framework, including a Target-Specific Detector (TSD) and a re-ID model with Dynamic Adaptive Learning Structure (DALS). For the former consistency need, we add a verification head for predicting the similarity scores between query and proposals in parallel with the existing heads for bounding box recognition. Thus, TSD generates accurate boxes for the query-like pedestrians, which are suitable for the re-ID stage. For the re-ID robustness need, DALS dynamically generates a large number of possible detection results in line with the real distribution. By training the re-ID model on data with different types of detection errors, DLAS improves the model robustness to detection inputs. Experimental results show our framework achieves state-of-the-art performance on two widely-used person search datasets.
关键词	Task analysis Detectors Training Robustness Proposals Feature extraction Cameras Deep neural networks Person search
DOI	10.1109/TMM.2021.3140025
收录类别	SCI
语种	英语
资助项目	Natural Science Foundation of China (NSFC)[61876171] ; Natural Science Foundation of China (NSFC)[61976203]
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:000970791100013
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/2XEOYT63/21396
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Ma, Bingpeng
作者单位	1.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, CAS, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 4.CAS Ctr Excellence Brain Sci & Intelligence Techno, Shanghai 200031, Peoples R China
推荐引用方式 GB/T 7714	Wang, Cheng,Ma, Bingpeng,Chang, Hong,et al. Person Search by a Bi-Directional Task-Consistent Learning Model[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2023,25:1190-1203.
APA	Wang, Cheng,Ma, Bingpeng,Chang, Hong,Shan, Shiguang,&Chen, Xilin.(2023).Person Search by a Bi-Directional Task-Consistent Learning Model.IEEE TRANSACTIONS ON MULTIMEDIA,25,1190-1203.
MLA	Wang, Cheng,et al."Person Search by a Bi-Directional Task-Consistent Learning Model".IEEE TRANSACTIONS ON MULTIMEDIA 25(2023):1190-1203.