We study the problem of human action recognition using motion capture (MoCap)
sequences. Unlike existing techniques that take multiple manual steps to derive
standardized skeleton representations as model input, we propose a novel
Spatial-Temporal Mesh Transformer (STMT) to directly model the mesh sequences.
The model uses a hierarchical transformer with intra-frame off-set attention
and inter-frame self-attention. The attention mechanism allows the model to
freely attend between any two vertex patches to learn non-local relationships
in the spatial-temporal domain. Masked vertex modeling and future frame
prediction are used as two self-supervised tasks to fully activate the
bi-directional and auto-regressive attention in our hierarchical transformer.
The proposed method achieves state-of-the-art performance compared to
skeleton-based and point-cloud-based models on common MoCap benchmarks. Code is
available at this https URL

本文提出一种利用 Spatial-Temporal Mesh Transformer（STMT） 直接对网格序列进行建模的方法，通过使用层次 Transformer 结构和自监督任务来实现骨架表示和点云表示无法达到的以空间 - 时间域的非局部关系为基础的人类动作识别，实验结果表明该方法在 MoCap 基准测试上表现卓越。