Body Part-based Representation Learning For Occluded Person Re-identification

Abstract

Occluded person re-identification (ReID) is a person retrieval task which aims at matching occluded person images with holistic ones. For addressing occluded ReID, part-based methods have been shown beneficial as they offer fine-grained information and are well suited to represent partially visible human bodies. However, training a part-based model is a challenging task for two reasons. Firstly, individual body part appearance is not as discriminative as global appearance (two distinct IDs might have the same local appearance), this means standard ReID training objectives using identity labels are not adapted to local feature learning. Secondly, ReID datasets are not provided with human topographical annotations. In this work, we propose BPBreID, a body part-based ReID model for solving the above issues. We first design two modules for predicting body part attention maps and producing body part-based features of the ReID target. We then propose GiLt, a novel training scheme for learnin

Stats

• citations158
• S2 citations—
• github stars253
• HF likes0
• heat score21.32
• arxiv keysomers2022body

Related papers

• Part-aligned Bilinear Representations For Person Re-identification (2018)19.30
• Pgganet: Pose Guided Graph Attention Network For Person Re-identification (2021)0.00
• Deep-person: Learning Discriminative Deep Features For Person Re-identification (2017)16.90
• Dynamic Dual-attentive Aggregation Learning For Visible-infrared Person Re-identification (2020)19.67
• Part-based Pseudo Label Refinement For Unsupervised Person Re-identification (2022)21.91
• A Pose-sensitive Embedding For Person Re-identification With Expanded Cross Neighborhood Re-ranking (2017)23.25
• Pose-aided Video-based Person Re-identification Via Recurrent Graph Convolutional Network (2022)10.97
• Video-based Visible-infrared Person Re-identification With Auxiliary Samples (2023)13.49