# Temporal Attention-Augmented Graph Convolutional Network for Efficient Skeleton-Based Human Action Recognition

arXiv: https://arxiv.org/abs/2010.12221 · HTML: https://mlsanity.com/paper/2010.12221/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2020.

## Built on by (most cited first, 8 of 8)

- [Geometric Deep Learning for Computer-Aided Design: A Survey](https://mlsanity.com/paper/2402.17695/) (2024)
- [Continual Spatio-Temporal Graph Convolutional Networks](https://mlsanity.com/paper/2203.11009/) (2022)
- [Non-local Graph Convolutional Network for joint Activity Recognition and Motion Prediction](https://mlsanity.com/paper/2108.01518/) (2021)
- [Extended multi-stream temporal-attention module for skeleton-based human action recognition (HAR)](https://mlsanity.com/paper/2411.06553/) (2024)
- [IoT-Based Real-Time Medical-Related Human Activity Recognition Using Skeletons and Multi-Stage Deep Learning for Healthcare](https://mlsanity.com/paper/2501.07039/) (2025)
- [Koopman pose predictions for temporally consistent human walking estimations](https://mlsanity.com/paper/2205.02737/) (2022)
- [Efficient Online Processing with Deep Neural Networks](https://mlsanity.com/paper/2306.13474/) (2023)
- [Variational Graph Convolutional Neural Networks](https://mlsanity.com/paper/2507.01699/) (2025)

## Abstract (arXiv)

Graph convolutional networks (GCNs) have been very successful in modeling non-Euclidean data structures, like sequences of body skeletons forming actions modeled as spatio-temporal graphs. Most GCN-based action recognition methods use deep feed-forward networks with high computational complexity to process all skeletons in an action. This leads to a high number of floating point operations (ranging from 16G to 100G FLOPs) to process a single sample, making their adoption in restricted computation application scenarios infeasible. In this paper, we propose a temporal attention module (TAM) for increasing the efficiency in skeleton-based action recognition by selecting the most informative skeletons of an action at the early layers of the network. We incorporate the TAM in a light-weight GCN topology to further reduce the overall number of computations. Experimental results on two benchmark datasets show that the proposed method outperforms with a large margin the baseline GCN-based method while having 2.9 times less number of computations. Moreover, it performs on par with the state-of-the-art with up to 9.6 times less number of computations.