Edge-Weight-Embedding Graph Convolutional Network for Person Reidentification

Person Re-identification (Re-ID) aims to accurately identify the same person in images from a large dataset captured by non-overlapping cameras. Recently, local-scale features of person representation have been shown to be effective in improving the performance of Re-ID. However, most previous methods have overlooked the inherent and potential relationships among the joint parts of the human skeleton structure. There are inherent differences in the human skeleton structure, such as the bone length between joints, which can be considered a highly distinguishable feature for Re-ID. To address this, we propose a novel graph convolutional network (GCN) based method that embeds the relationships between human joints and bones into a high-level representation for Re-ID. In our method, the relationships between human joints and bones are represented by the biological information of the human skeleton and encoded into a learned adjacency matrix by an Edge Score Predictor (ESP) module. Our proposed method achieves competitive results on several benchmark datasets (Market1501, DukeMTMC-ReID, and CUHK03), demonstrating its effectiveness.