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
Gait Attribute Recognition: A New Benchmark for Learning Richer Attributes From Human Gait Patterns

文献类型：期刊论文

作者Song, Xu1; Hou, Saihui2,3; Huang, Yan4,5; Cao, Chunshui3; Liu, Xu3; Huang, Yongzhen2,3; Shan, Caifeng1,6
刊名IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
出版日期2024
卷号19页码:1-14
关键词Gait attribute recognition gait dataset deep learning
ISSN号1556-6013
DOI10.1109/TIFS.2023.3318934
通讯作者Huang, Yan(yan.huang@cripac.ia.ac.cn) ; Shan, Caifeng(caifeng.shan@gmail.com)
英文摘要Compared to gait recognition, Gait Attribute Recognition (GAR) is a seldom-investigated problem. However, since gait attribute recognition can provide richer and finer semantic descriptions, it is an indispensable part of building intelligent gait analysis systems. Nonetheless, the types of attributes considered in the existing datasets are very limited. This paper contributes a new benchmark dataset for gait attribute recognition named Multi-Attribute Gait (MA-Gait). Our MA-Gait contains 95 subjects recorded from 12 camera views, resulting in more than 13000 sequences, with 16 attributes labeled, including six attributes that have never been considered in the literature. Moreover, we propose a Multi-Scale Motion Encoder (MSME) to extract robust motion features, and an Attribute-Guided Feature Selection Module (AGFSM) to adaptively capture the most discriminative attribute features from static appearance features and dynamic motion features for different attributes. Our method achieves the best GAR accuracy on the new dataset. Comprehensive experiments show the effectiveness of the proposed method through both quantitative and qualitative evaluations.
WOS关键词GENDER CLASSIFICATION ; IMAGE
资助项目National Natural Science Foundation of China[62276025] ; National Natural Science Foundation of China[62206022] ; National Natural Science Foundation of China[62306311] ; Shenzhen Technology Plan Program[KQTD20170331093217368] ; Talent Introduction Program for Youth Innovation Teams of Shandong Province ; Fellowship of China Post-Doctoral Science Foundation[2022T150698]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001106614700005
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Natural Science Foundation of China ; Shenzhen Technology Plan Program ; Talent Introduction Program for Youth Innovation Teams of Shandong Province ; Fellowship of China Post-Doctoral Science Foundation
源URL[http://ir.ia.ac.cn/handle/173211/55076]  
专题多模态人工智能系统全国重点实验室
通讯作者Huang, Yan; Shan, Caifeng
作者单位1.Shandong Univ Sci & Technol, Coll Elect Engn & Automat, Qingdao 266590, Peoples R China
2.Beijing Normal Univ, Sch Artificial Intelligence, Beijing 100875, Peoples R China
3.Watrix Technol Co Ltd, Beijing 100088, Peoples R China
4.Univ Chinese Acad Sci, Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Natl Lab Pattern Recognit,Ctr Res Intelligent Perc, Beijing 100190, Peoples R China
5.Univ Chinese Acad Sci, Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
6.Nanjing Univ, Sch Intelligence Sci & Technol, Nanjing 210023, Peoples R China
推荐引用方式
GB/T 7714		 Song, Xu,Hou, Saihui,Huang, Yan,et al. Gait Attribute Recognition: A New Benchmark for Learning Richer Attributes From Human Gait Patterns[J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,2024,19:1-14.
APA Song, Xu.,Hou, Saihui.,Huang, Yan.,Cao, Chunshui.,Liu, Xu.,...&Shan, Caifeng.(2024).Gait Attribute Recognition: A New Benchmark for Learning Richer Attributes From Human Gait Patterns.IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,19,1-14.
MLA Song, Xu,et al."Gait Attribute Recognition: A New Benchmark for Learning Richer Attributes From Human Gait Patterns".IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 19(2024):1-14.

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。