Accommodating Self-attentional Heterophily Topology into High- and Low-pass Graph Convolutional Network for Skeleton-based Action Recognition.
2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN（2023）
Key words
feature extraction,graph topology,heterophily topologies,HLP-GCN framework,HLPGCN framework,homophily topologies,human action dynamics,human skeleton-based action recognition,large-scale action recognition datasets,learned homophily,low-pass graph convolutional network,self-attention modules,self-attentional heterophily topology,skeleton action recognition,skeleton-based action recognition tasks,temporal modeling module
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined