Feature Aggregation With Reinforcement Learning for Video-Based Person Re-Identification

doi:10.1109/TNNLS.2019.2899588

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 机器人理论与应用

	Feature Aggregation With Reinforcement Learning for Video-Based Person Re-Identification
	Zhang, Wei 1; He, Xuanyu 1; Lu, Weizhi 1; Qiao, Hong2 ; Li, Yibin 1
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN	2162-237X
	2019-12-01
卷号	30 期号:12 页码:3847-3852
通讯作者	He, Xuanyu(hexiffer@outlook.com)
摘要	Video-based person re-identification (re-id) matches two tracks of persons from different cameras. Features are extracted from the images of a sequence and then aggregated as a track feature. Compared to existing works that aggregate frame features by simply averaging them or using temporal models such as recurrent neural networks, we propose an intelligent feature aggregate method based on reinforcement learning. Specifically, we train an agent to determine which frames in the sequence should be abandoned in the aggregation, which can be treated as a decision making process. By this way, the proposed method avoids introducing noisy information of the sequence and retains these valuable frames when generating a track feature. On benchmark data sets, experimental results show that our method can boost the re-id accuracy obviously based on the state-of-the-art models.
关键词	Feature extraction Task analysis Cameras Noise measurement Learning systems Reinforcement learning Feature aggregation reinforcement learning (RL) sequential decision making video-based person re-identification (re-id)
DOI	10.1109/TNNLS.2019.2899588
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Plan of China[2017YFB1300205] ; NSFC[61573222] ; NSFC[61801264] ; Major Research Program of Shandong Province[2018CXGC1503] ; Fundamental Research Funds of Shandong University[2016JC014] ; Basic Research Program of Shenzhen[JCYJ20170307153635551] ; National Key Research and Development Plan of China[2017YFB1300205] ; NSFC[61573222] ; NSFC[61801264] ; Major Research Program of Shandong Province[2018CXGC1503] ; Fundamental Research Funds of Shandong University[2016JC014] ; Basic Research Program of Shenzhen[JCYJ20170307153635551]
项目资助者	National Key Research and Development Plan of China ; NSFC ; Major Research Program of Shandong Province ; Fundamental Research Funds of Shandong University ; Basic Research Program of Shenzhen
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000502762600028
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：74[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/173211/29440
专题	多模态人工智能系统全国重点实验室_机器人理论与应用
通讯作者	He, Xuanyu
作者单位	1.Shandong Univ, Sch Control Sci & Engn, Jinan 250100, Shandong, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Wei,He, Xuanyu,Lu, Weizhi,et al. Feature Aggregation With Reinforcement Learning for Video-Based Person Re-Identification[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2019,30(12):3847-3852.
APA	Zhang, Wei,He, Xuanyu,Lu, Weizhi,Qiao, Hong,&Li, Yibin.(2019).Feature Aggregation With Reinforcement Learning for Video-Based Person Re-Identification.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,30(12),3847-3852.
MLA	Zhang, Wei,et al."Feature Aggregation With Reinforcement Learning for Video-Based Person Re-Identification".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 30.12(2019):3847-3852.