中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Person Search by a Bi-Directional Task-Consistent Learning Model

文献类型：期刊论文

作者Wang, Cheng3; Ma, Bingpeng3; Chang, Hong1,4; Shan, Shiguang1,2,4; Chen, Xilin1,4
刊名IEEE TRANSACTIONS ON MULTIMEDIA
出版日期2023
卷号25页码:1190-1203
关键词Task analysis Detectors Training Robustness Proposals Feature extraction Cameras Deep neural networks Person search
ISSN号1520-9210
DOI10.1109/TMM.2021.3140025
英文摘要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.
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
语种英语
WOS记录号WOS:000970791100013
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/21395]  
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, Beijing 100049, Peoples R China
2.CAS Ctr Excellence Brain Sci & Intelligence Techno, Shanghai 200031, Peoples R China
3.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100049, Peoples R China
4.Chinese Acad Sci, Inst Comp Technol, CAS, Key Lab Intelligent Informat Proc, Beijing 100190, 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.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。