Part-aligned Bilinear Representations For Person Re-identification

Abstract

We propose a novel network that learns a part-aligned representation for person re-identification. It handles the body part misalignment problem, that is, body parts are misaligned across human detections due to pose/viewpoint change and unreliable detection. Our model consists of a two-stream network (one stream for appearance map extraction and the other one for body part map extraction) and a bilinear-pooling layer that generates and spatially pools a part-aligned map. Each local feature of the part-aligned map is obtained by a bilinear mapping of the corresponding local appearance and body part descriptors. Our new representation leads to a robust image matching similarity, which is equivalent to an aggregation of the local similarities of the corresponding body parts combined with the weighted appearance similarity. This part-aligned representation reduces the part misalignment problem significantly. Our approach is also advantageous over other pose-guided representations (e.g., e

Stats

• citations373
• S2 citations—
• github stars0
• HF likes0
• heat score19.30
• arxiv keysuh2018part

Related papers

• Body Part-based Representation Learning For Occluded Person Re-identification (2022)21.32
• A Pose-sensitive Embedding For Person Re-identification With Expanded Cross Neighborhood Re-ranking (2017)23.25
• Pedestrian Alignment Network For Large-scale Person Re-identification (2017)18.71
• Deep-person: Learning Discriminative Deep Features For Person Re-identification (2017)16.90
• Pgganet: Pose Guided Graph Attention Network For Person Re-identification (2021)0.00
• Interpretable And Generalizable Person Re-identification With Query-adaptive Convolution And Temporal Lifting (2019)20.43
• Advancing Person Re-identification: Tensor-based Feature Fusion And Multilinear Subspace Learning (2023)2.26
• A Discriminatively Learned CNN Embedding For Person Re-identification (2016)20.32