Paper Info
Title
High-Order Information Matters: Learning Relation And Topology For Occluded Person Re-Identification
Abstract
Occluded person re-identification (ReID) aims to match occluded person images to holistic ones across disjoint cameras. In this paper, we propose a novel framework by learning high-order relation and topology information for discriminative features and robust alignment. At first, we use a CNN backbone and a key-points estimation model to extract semantic local features. Even so, occluded images still suffer from occlusion and outliers. Then, we view the local features of an image as nodes of a graph and propose an adaptive direction graph convolutional (ADGC) layer to pass relation information between nodes. The proposed ADGC layer can automatically suppress the message passing of meaningless features by dynamically learning direction and degree of linkage. When aligning two groups of local features from two images, we view it as a graph matching problem and propose a cross-graph embedded-alignment (CGEA) layer to jointly learn and embed topology information to local features, and straightly predict similarity score. The proposed CGEA layer not only take full use of alignment learned by graph matching but also replace sensitive one-to-one matching with a robust soft one. Finally, extensive experiments on occluded, partial, and holistic ReID tasks show the effectiveness of our proposed method. Specifically, our framework significantly outperforms state-of-the-art by 6.5% mAP scores on Occluded-Duke dataset. Code is available at https://github.com/wangguanan/HOReID.
Year
DOI
Venue
2020
10.1109/CVPR42600.2020.00648
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
DocType
ISSN
Citations 
Conference
1063-6919
9
PageRank 
References 
Authors
0.44
22
9
Name
Order
Citations
PageRank
Guan'an Wang1334.82
Yang Shuo290.44
Huanyu Liu3200.92
Wang Zhicheng490.77
Yang Yang529914.19
Shuliang Wang620232.66
Gang Yu738219.85
ErjinZhou890.44
Jian Sun925842956.90