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

14 Jul 2023  ·  Yuhang Wen, Zixuan Tang, Yunsheng Pang, Beichen Ding, Mengyuan Liu ·

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

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Benchmark
3D Action Recognition Assembly101 ISTA-Net Actions Top-1 28.07 # 5
Verbs Top-1 62.66 # 4
Object Top-1 31.69 # 6
Action Recognition H2O (2 Hands and Objects) ISTA-Net Actions Top-1 89.09 # 5
RGB No # 1
Hand Pose 3D # 1
Object Pose Yes # 1
Object Label No # 1
Skeleton Based Action Recognition H2O (2 Hands and Objects) ISTA-Net Accuracy 89.09±1.21 # 4
Human Interaction Recognition NTU RGB+D 120 ISTA-Net Accuracy (Cross-Subject) 90.5 # 3
Accuracy (Cross-Setup) 91.7 # 3
Human Interaction Recognition SBU / SBU-Refine ISTA-Net Accuracy 98.51±1.47 # 1

Methods


No methods listed for this paper. Add relevant methods here