# Spatial Temporal Graph Attention Network for Skeleton-Based Action Recognition

Source: [Spatial Temporal Graph Attention Network for Skeleton-Based Action Recognition](<https://www.sota2.com/research/paper/68fa6d651e209131cea39787>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-22T09:36:08.305Z

Authors: Lianyu Hu, Shenglan Liu, Wei Feng

Published: 2022-08-18T02:34:46.000Z

## Abstract

It's common for current methods in skeleton-based action recognition to mainly consider capturing long-term temporal dependencies as skeleton sequences are typically long (\>128 frames), which forms a challenging problem for previous approaches. In such conditions, short-term dependencies are few formally considered, which are critical for classifying similar actions. Most current approaches are consisted of interleaving spatial-only modules and temporal-only modules, where direct information flow among joints in adjacent frames are hindered, thus inferior to capture short-term motion and distinguish similar action pairs. To handle this limitation, we propose a general framework, coined as STGAT, to model cross-spacetime information flow. It equips the spatial-only modules with spatial-temporal modeling for regional perception. While STGAT is theoretically effective for spatial-temporal modeling, we propose three simple modules to reduce local spatial-temporal feature redundancy and further release the potential of STGAT, which (1) narrow the scope of self-attention mechanism, (2) dynamically weight joints along temporal dimension, and (3) separate subtle motion from static features, respectively. As a robust feature extractor, STGAT generalizes better upon classifying similar actions than previous methods, witnessed by both qualitative and quantitative results. STGAT achieves state-of-the-art performance on three large-scale datasets: NTU RGB+D 60, NTU RGB+D 120, and Kinetics Skeleton 400. Code is released.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Action Recognition on NTU RGB+D 60 (X-View)](<https://www.sota2.com/research/sota/action-recognition-on-ntu-rgb-plus-d-60-x-view.md>): Action Recognition; NTU RGB+D X-View 60; Accuracy: 95.4.

- [Action Recognition on NTU RGB+D 60 (X-sub)](<https://www.sota2.com/research/sota/action-recognition-on-ntu-rgb-plus-d-60-x-sub.md>): Action Recognition; NTU RGB+D 60 (X-sub); Accuracy: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2208.08599>)

[PDF](<https://arxiv.org/pdf/2208.08599.pdf>)

[Implementation](<https://github.com/hulianyuyy/STGAT>)
