Pyramid-resolution person restoration for cross-resolution person re-identification
作者机构:State Key Laboratory of Integrated Services NetworksXidian University School of Cyber EngineeringXidian University School of Telecommunications EngineeringXidian University Chongqing Key Laboratory of Image CognitionChongqing University of Posts and Telecommunications
出 版 物:《Science China(Information Sciences)》 (中国科学:信息科学(英文版))
年 卷 期:2024年第67卷第6期
页 面:451-452页
核心收录:
学科分类:0808[工学-电气工程] 08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 0812[工学-计算机科学与技术(可授工学、理学学位)]
基 金:supported in part by National Natural Science Foundation of China (Grant Nos. 62276198, U22A2035, U22A2096, 62306227) Key Research and Development Program of Shaanxi (Grant No. 2023-YBGY231) Young Elite Scientists Sponsorship Program by CAST (Grant No. 2022QNRC001) Guangxi Natural Science Foundation Program (Grant No. 2021GXNSFDA075011) Natural Science Basic Research Plan in Shaanxi Province of China (Grant No. 2022JQ-696) Xi’an Science and Technology Plan Project (Grant No. 23GJSY0004) Open Research Project of Key Laboratory of Artificial Intelligence Ministry of Education (Grant No. AI202401) Fundamental Research Funds for the Central Universities (Grant Nos. QTZX23083, QTZX23042, ZYTS24142)
主 题:Restoration
摘 要:Person images captured by surveillance cameras are typically with various resolutions and are susceptible to pose changes,occlusion and background variations,thus affecting the performance of person Re *** approaches[1,2]either use an image restoration model to restore the lowresolution images to obtain a corresponding high-resolution image,