Dyadic relational graph convolutional networks for skeleton-based human interaction recognition

作者：

Highlights：

• 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.

摘要

•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.

论文关键词：3D skeleton-based interaction recognition,Multi-scale graph convolution networks,Graph inference

论文评审过程：Received 21 July 2020, Revised 9 November 2020, Accepted 19 February 2021, Available online 2 March 2021, Version of Record 10 March 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.107920