Learning discriminative representation with global and fine-grained features for cross-view gait recognition

作     者：Jing Xiao Huan Yang Kun Xie Jia Zhu Ji Zhang 

作者机构：School of Computer ScienceSouth China Normal UniversityGuangzhouGuangdongChina Key Laboratory of Intelligent Education Technology and Application of Zhejiang ProvinceZhejiang Normal UniversityJinhuaZhejiangChina School of SciencesUniversity of Southern QueenslandToowoomba QldAustralia 

出 版 物：《CAAI Transactions on Intelligence Technology》 (智能技术学报（英文）)

年 卷 期：2022年第7卷第2期

页      面：187-199页

核心收录：

学科分类：08[工学] 081101[工学-控制理论与控制工程] 0811[工学-控制科学与工程] 081102[工学-检测技术与自动化装置] 

基　　金：Key Area Research and Development Program of Guangdong Province,Grant/Award Number:2019B111101001 Natural Science Foundation of Guangdong Province,Grant/Award Number:2018A030313318 

主　　题：gait database grain 

摘      要：In this study,we examine the cross-view gait recognition *** existing methods establish global feature representation based on the whole human body ***,they ignore some important details of different parts of the human *** the latest literature,positioning partial regions to learn fine-grained features has been verified to be effective in human *** they only consider coarse fine-grained fea-tures and ignore the relationship between neighboring *** the above insights together,we propose a novel model called GaitGP,which learns both important details through fine-grained features and the relationship between neighboring regions through global *** GaitGP model mainly consists of the following two ***,we propose a Channel-Attention Feature Extractor(CAFE)to extract the global features,which aggregates the channel-level attention to enhance the spatial information in a novel convolutional ***,we present the Global and Partial Feature Combiner(GPFC)to learn different fine-grained features,and combine them with the global fea-tures extracted by the CAFE to obtain the relevant information between neighboring *** results on the CASIA gait recognition dataset B(CASIA-B),The OU-ISIR gait database,multi-view large population dataset,and The OU-ISIR gait database gait datasets show that our method is superior to the state-of-the-art cross-view gait recognition methods.