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

TL;DR

The paper introduces ISTA-Net, a novel neural network that models spatial, temporal, and interactive relations in skeleton-based action recognition, outperforming existing methods and handling diverse interacting entities effectively.

Contribution

It proposes a unified spatiotemporal token attention network with entity rearrangement for better interactive action recognition.

Findings

Outperforms state-of-the-art methods on four datasets.

Effectively models diverse interacting entities.

Demonstrates robustness in recognizing interactive actions.

Abstract

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