Multi-Pose Learning based Head-Shoulder Re-identification

被引：3

作者：

Li, Jia ^{[1
,2
]}

Zhai, Yunpeng ^{[3
]}

Wang, Yaowei ^{[4
]}

Shi, Yemin ^{[2
]}

Tian, Yonghong ^{[2
]}

机构：

[1] Peking Univ, Shenzhen Grad Sch, Sch Elect & Comp Engn, Shenzhen, Peoples R China

[2] Peking Univ, Natl Engn Lab Video Technol, Beijing, Peoples R China

[3] BUPT, Sch Informat & Commun Engn, Beijing, Peoples R China

[4] Beijing Inst Technol, Sch Informat & Elect, Beijing, Peoples R China

来源：

IEEE 1ST CONFERENCE ON MULTIMEDIA INFORMATION PROCESSING AND RETRIEVAL (MIPR 2018) | 2018年

基金：

中国国家自然科学基金; 国家重点研发计划;

关键词：

D O I：

10.1109/MIPR.2018.00057

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

The whole body of person is probably invisible in video surveillance because of occlusion and view angles (such as in crowded public places), on which occasion conventional person re-identification (i.e., whole-body based ReID) approaches may not work. To address this problem, we propose a novel deep pairwise model based on multi-pose learning (MPL) which aims at head-shoulder part instead of the whole body. The proposed method explicitly tackles pose variations by learning an ensemble verification conditional probability distribution about relationship among multiple poses. To facilitate the research on this problem, we contribute three head-shoulder datasets based on CUHK03, CUHK01 and VIPeR. Experiments on these datasets demonstrate that our proposed method achieves the state-of-the-art performance.

引用

页码：238 / 243

页数：6