Abstract | ||
---|---|---|
•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. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1016/j.patcog.2021.108155 | Pattern Recognition |
Keywords | DocType | Volume |
Person re-identification,Graph convolution network | Journal | 120 |
Issue | ISSN | Citations |
1 | 0031-3203 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhong Zhang | 1 | 141 | 32.42 |
Haijia Zhang | 2 | 1 | 1.02 |
Shuang Liu | 3 | 36 | 22.95 |
Yuan Xie | 4 | 6430 | 407.00 |
Tariq S. Durrani | 5 | 117 | 33.56 |