2020/12/11 by Chiara Plizzari, Marco Cannici, Matteo Matteucci
Computer Science · #cs.CV
paper · pdf · doi:10.1007/978-3-030-68796-0_50
published as Pattern Recognition. ICPR International Workshops and Challenges. ICPR 2021. Lecture Notes in Computer Science, Springer, vol 12663, 694-701, ISBN: 978-3-030-68796-0 · Accepted as ICPRW2020 (FBE2020, Workshop on Facial and Body Expressions, micro-expressions and behavior recognition) 8 pages, 2 figures. arXiv admin note: substantial text overlap with arXiv:2008.07404
arxiv created 2020/12/11 · arxiv updated 2021/06/24
Skeleton-based human action recognition has achieved a great interest in recent years, as skeleton data has been demonstrated to be robust to illumination changes, body scales, dynamic camera views, and complex background. Nevertheless, an effective encoding of the latent information underlying the 3D skeleton is still an open problem. In this work, we propose a novel Spatial-Temporal Transformer network (ST-TR) which models dependencies between joints using the Transformer self-attention operator. In our ST-TR model, a Spatial Self-Attention module (SSA) is used to understand intra-frame interactions between different body parts, and a Temporal Self-Attention module (TSA) to model inter-frame correlations. The two are combined in a two-stream network which outperforms state-of-the-art models using the same input data on both NTU-RGB+D 60 and NTU-RGB+D 120.