中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Refined Knowledge Transfer for Language-Based Person Search

文献类型:期刊论文

作者Wu, Ziqiang5; Ma, Bingpeng5; Chang, Hong2,3,4; Shan, Shiguang1,2,3
刊名IEEE TRANSACTIONS ON MULTIMEDIA
出版日期2023
卷号25页码:9315-9329
关键词Language-based person search knowledge enhancement knowledge enhancement cross-modal knowledge transfer intra-modal knowledge transfer intra-modal knowledge transfer knowledge refiner
ISSN号1520-9210
DOI10.1109/TMM.2023.3251104
英文摘要This paper proposes a novel method, named Refined Knowledge Transfer (RKT), for language-based person search. Existing state-of-the-art methods do not deal with knowledge imbalance between image and text. In detail, textual identity knowledge is limited, but the image contains more identity knowledge. We propose Cross-Modal Knowledge Transfer (CMKT) to enhance textual identity knowledge by image to address this problem. Besides, multiple texts of one image include more identity knowledge than a single text. Thus, we propose Intra-Modal Knowledge Transfer (IMKT) to enhance textual identity knowledge by other texts. These two types of knowledge transfer will enhance the identity knowledge in text. Additionally, by considering that identity-irrelevant knowledge is transferred to text, we propose Knowledge Refiner (KR) to refine the knowledge in text. KR is capable of preserving identity knowledge and discarding identity-irrelevant knowledge. By combining CMKT, IMKT, and KR, RKT makes textual identity knowledge more salient. Extensive experiments show the state-of-the-art performance of RKT on the CUHK-PEDES and our proposed PRW-PEDES-CN datasets. In addition, the decent generalization ability of RKT is also validated on the Flickr30K, CUB, and Flowers datasets.
资助项目National Natural Science Foundation of China
WOS研究方向Computer Science ; Telecommunications
语种英语
WOS记录号WOS:001133324200011
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/38417]  
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.Chinese Acad Sci, Key Lab Intelligent Informat Proc, ICT, Beijing 100190, Peoples R China
2.Peng Cheng Lab, Shenzhen 518055, Peoples R China
3.UCAS, Sch Comp Sci & Technol, Beijing 100049, Peoples R China
4.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
5.Univ Chinese Acad Sci UCAS, Sch Sci & Technol, Beijing 100049, Peoples R China
推荐引用方式
GB/T 7714
Wu, Ziqiang,Ma, Bingpeng,Chang, Hong,et al. Refined Knowledge Transfer for Language-Based Person Search[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2023,25:9315-9329.
APA Wu, Ziqiang,Ma, Bingpeng,Chang, Hong,&Shan, Shiguang.(2023).Refined Knowledge Transfer for Language-Based Person Search.IEEE TRANSACTIONS ON MULTIMEDIA,25,9315-9329.
MLA Wu, Ziqiang,et al."Refined Knowledge Transfer for Language-Based Person Search".IEEE TRANSACTIONS ON MULTIMEDIA 25(2023):9315-9329.

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。