IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition
This work addresses human interaction recognition for applications like surveillance or human-computer interaction, but it appears incremental as it builds on existing graph-based methods for skeleton data.
The paper tackled skeleton-based human interaction recognition by modeling interactive body parts as graphs, and the proposed IGFormer model achieved state-of-the-art performance with significant margins on three benchmark datasets.
Human interaction recognition is very important in many applications. One crucial cue in recognizing an interaction is the interactive body parts. In this work, we propose a novel Interaction Graph Transformer (IGFormer) network for skeleton-based interaction recognition via modeling the interactive body parts as graphs. More specifically, the proposed IGFormer constructs interaction graphs according to the semantic and distance correlations between the interactive body parts, and enhances the representation of each person by aggregating the information of the interactive body parts based on the learned graphs. Furthermore, we propose a Semantic Partition Module to transform each human skeleton sequence into a Body-Part-Time sequence to better capture the spatial and temporal information of the skeleton sequence for learning the graphs. Extensive experiments on three benchmark datasets demonstrate that our model outperforms the state-of-the-art with a significant margin.