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. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 三维可视计算
GRLN: Gait Refined Lateral Network for gait recognition

文献类型：期刊论文

作者Song, Yukun1; Mao, Xin4; Feng, Xuxiang; Wang, Changwei3; Xu, Rongtao3; Zhang, Man2; Xu, Shibiao2
刊名DISPLAYS
出版日期2024-09-01
卷号84页码:8
关键词Adaptive feature refinement module Coarse-to-fine Gait recognition Horizontally stable mapping
ISSN号0141-9382
DOI10.1016/j.displa.2024.102776
通讯作者Zhang, Man(zhangman@bupt.edu.cn)
英文摘要Gait recognition aims to identify individuals at a distance based on their biometric gait patterns. While offering flexibility in network input, existing set -based methods often overlook the potential of fine-grained local feature by solely utilizing global gait feature and fail to fully exploit the communication between silhouette -level and set -level features. To alleviate this issue, we propose Gait Refined Lateral Network(GRLN), featuring plug -and -play Adaptive Feature Refinement modules (AFR) that extract discriminative features progressively from silhouette -level and set -level representations in a coarse -to -fine manner at various network depths. AFR can be widely applied in set -based gait recognition models to substantially enhance their gait recognition performance. To align with the extracted refined features, we introduce Horizontal Stable Mapping (HSM), a novel mapping technique that reduces model parameters while improving experimental results. To demonstrate the effectiveness of our method, we evaluate GRLN on two gait datasets, achieving the highest recognition rate among all set -based methods. Specifically, GRLN demonstrates an average improvement of 1.15% over the state-of-the-art set -based method on CASIA-B. Especially in the coat -wearing condition, GRLN exhibits a 5% improvement in performance compared to the contrast method GLN.
资助项目Beijing Natural Science Foundation[JQ23014] ; Science and Disruptive Technology Program, AIRCAS[E2Z218020F] ; National Natural Science Foundation of China[62271074] ; National Natural Science Foundation of China[62171321] ; National Natural Science Foundation of China[62162044]
WOS研究方向Computer Science ; Engineering ; Instruments & Instrumentation ; Optics
语种英语
WOS记录号WOS:001259607000001
出版者ELSEVIER
资助机构Beijing Natural Science Foundation ; Science and Disruptive Technology Program, AIRCAS ; National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/59157]  
专题模式识别国家重点实验室_三维可视计算
通讯作者Zhang, Man
作者单位1.Chinese Acad Sci, Aerosp Informat Res Inst, Beijing, Peoples R China
2.Beijing Univ Posts & Telecommun, Sch Artificial Intelligence, Beijing, Peoples R China
3.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing, Peoples R China
4.Beijing Zitiao Network Technol Co Ltd, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Song, Yukun,Mao, Xin,Feng, Xuxiang,et al. GRLN: Gait Refined Lateral Network for gait recognition[J]. DISPLAYS,2024,84:8.
APA Song, Yukun.,Mao, Xin.,Feng, Xuxiang.,Wang, Changwei.,Xu, Rongtao.,...&Xu, Shibiao.(2024).GRLN: Gait Refined Lateral Network for gait recognition.DISPLAYS,84,8.
MLA Song, Yukun,et al."GRLN: Gait Refined Lateral Network for gait recognition".DISPLAYS 84(2024):8.

入库方式： OAI收割

来源：自动化研究所

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。