Part-guided graph convolution networks for person re-identification
作者：
Highlights：
• We propose a novel deep graph model to learn the inter-local relationship of the corresponding parts among pedestrian images and the intra-local relationship between adjacent parts to obtain discriminative features for person Re-ID.
• We propose the fractional dynamic mechanism to optimize the adjacency matrix of intra-local graph for accurately describing the correlation between adjacent parts.
• Extensive experiments verify that the proposed PGCN exceeds the state-of-the-art methods.
摘要
•We propose a novel deep graph model to learn the inter-local relationship of the corresponding parts among pedestrian images and the intra-local relationship between adjacent parts to obtain discriminative features for person Re-ID.•We propose the fractional dynamic mechanism to optimize the adjacency matrix of intra-local graph for accurately describing the correlation between adjacent parts.•Extensive experiments verify that the proposed PGCN exceeds the state-of-the-art methods.
论文关键词：Person re-identification,Graph convolution network
论文评审过程：Received 28 June 2020, Revised 30 June 2021, Accepted 3 July 2021, Available online 10 July 2021, Version of Record 14 July 2021.
论文官网地址：https://doi.org/10.1016/j.patcog.2021.108155
