Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognition

About

Recognizing interactive action plays an important role in human-robot interaction and collaboration. Previous methods use late fusion and co-attention mechanism to capture interactive relations, which have limited learning capability or inefficiency to adapt to more interacting entities. With assumption that priors of each entity are already known, they also lack evaluations on a more general setting addressing the diversity of subjects. To address these problems, we propose an Interactive Spatiotemporal Token Attention Network (ISTA-Net), which simultaneously model spatial, temporal, and interactive relations. Specifically, our network contains a tokenizer to partition Interactive Spatiotemporal Tokens (ISTs), which is a unified way to represent motions of multiple diverse entities. By extending the entity dimension, ISTs provide better interactive representations. To jointly learn along three dimensions in ISTs, multi-head self-attention blocks integrated with 3D convolutions are designed to capture inter-token correlations. When modeling correlations, a strict entity ordering is usually irrelevant for recognizing interactive actions. To this end, Entity Rearrangement is proposed to eliminate the orderliness in ISTs for interchangeable entities. Extensive experiments on four datasets verify the effectiveness of ISTA-Net by outperforming state-of-the-art methods. Our code is publicly available at https://github.com/Necolizer/ISTA-Net

Yuhang Wen, Zixuan Tang, Yunsheng Pang, Beichen Ding, Mengyuan Liu• 2023

Related benchmarks

TaskDatasetResultRank
Action RecognitionAssembly101
Action Accuracy28.14
18
Action RecognitionH2O
Action Accuracy89.09
8
Human Interaction RecognitionNTU-Inter 120 X-Sub120
Top-1 Accuracy91.7
4
Human Interaction RecognitionNTU-Inter X-Sub60
Top-1 Accuracy90.6
4
Showing 4 of 4 rows

Other info

Follow for update