Pgganet: Pose Guided Graph Attention Network For Person Re-identification

Abstract

Person re-identification (reID) aims at retrieving a person from images captured by different cameras. For deep-learning-based reID methods, it has been proved that using local features together with global feature could help to give robust representation for person retrieval. Human pose information could provide the locations of human skeleton to effectively guide the network to pay more attention on these key areas and could also help to reduce the noise distractions from background or occlusion. However, methods proposed by previous pose-based works might not be able to fully exploit the benefits of pose information and few of them take into consideration the different contributions of separate local features. In this paper, we propose a pose guided graph attention network, a multi-branch architecture consisting of one branch for global feature, one branch for mid-granular body features and one branch for fine-granular key point features. We use a pre-trained pose estimator to gener

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhe2021pgganet

Related papers

• Pose-aided Video-based Person Re-identification Via Recurrent Graph Convolutional Network (2022)10.97
• A Pose-sensitive Embedding For Person Re-identification With Expanded Cross Neighborhood Re-ranking (2017)23.25
• Body Part-based Representation Learning For Occluded Person Re-identification (2022)21.32
• Multi-granularity Graph Pooling For Video-based Person Re-identification (2022)12.17
• Person Re-identification With Deep Similarity-guided Graph Neural Network (2018)17.55
• GLAD: Global-local-alignment Descriptor For Pedestrian Retrieval (2017)18.69
• Pedestrian Alignment Network For Large-scale Person Re-identification (2017)18.71
• Pose Invariant Embedding For Deep Person Re-identification (2017)19.34