Title | ||
---|---|---|
Dyadic relational graph convolutional networks for skeleton-based human interaction recognition |
Abstract | ||
---|---|---|
•We are the first to construct dynamic graphs on skeleton sequences that capture discriminative relations between skeletons.•Relational Adjacency Matrix is proposed to present relational graphs using geometric features and relative attention.•Proposed Dyadic Relational Graph Convolutional Network achieves state-of-the-art accuracy on three challenging datasets and improvements of 6.63% on NTU-RGB+D and 5.47% on NTU-RGB+D 120 over the baseline model.•Our methods consistently help advanced models achieve higher accuracy of 1.26% on NTU-RGB+D and 2.86% on NTU-RGB+D 120. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1016/j.patcog.2021.107920 | Pattern Recognition |
Keywords | DocType | Volume |
3D skeleton-based interaction recognition,Multi-scale graph convolution networks,Graph inference | Journal | 115 |
Issue | ISSN | Citations |
1 | 0031-3203 | 1 |
PageRank | References | Authors |
0.36 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Liping Zhu | 1 | 6 | 5.20 |
Bohua Wan | 2 | 1 | 0.36 |
Chengyang Li | 3 | 2 | 2.40 |
Gangyi Tian | 4 | 2 | 2.00 |
Yi Hou | 5 | 1 | 1.04 |
Kun Yuan | 6 | 2 | 1.73 |