# Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition

arXiv: https://arxiv.org/abs/2010.09978 · HTML: https://mlsanity.com/paper/2010.09978/

## Key facts

- Cited by 91 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Oct 2020.

## Built on by (most cited first, 30 of 91)

- [Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2107.12213/) (2021)
- [Revisiting Skeleton-based Action Recognition](https://mlsanity.com/paper/2104.13586/) (2021)
- [GaitGraph: Graph Convolutional Network for Skeleton-Based Gait Recognition](https://mlsanity.com/paper/2101.11228/) (2021)
- [Gait Recognition in the Wild with Dense 3D Representations and A Benchmark](https://mlsanity.com/paper/2204.02569/) (2022)
- [Skeleton Aware Multi-modal Sign Language Recognition](https://mlsanity.com/paper/2103.08833/) (2021)
- [Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition](https://mlsanity.com/paper/2106.15125/) (2021)
- [Skeleton-Contrastive 3D Action Representation Learning](https://mlsanity.com/paper/2108.03656/) (2021)
- [Learning Discriminative Representations for Skeleton Based Action Recognition](https://mlsanity.com/paper/2303.03729/) (2023)
- [Towards a Deeper Understanding of Skeleton-based Gait Recognition](https://mlsanity.com/paper/2204.07855/) (2022)
- [SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition](https://mlsanity.com/paper/2403.09508/) (2024)
- [Generative Action Description Prompts for Skeleton-based Action Recognition](https://mlsanity.com/paper/2208.05318/) (2022)
- [Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition](https://mlsanity.com/paper/2303.10904/) (2023)
- [GPGait: Generalized Pose-based Gait Recognition](https://mlsanity.com/paper/2303.05234/) (2023)
- [Hypergraph Transformer for Skeleton-based Action Recognition](https://mlsanity.com/paper/2211.09590/) (2022)
- [UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition](https://mlsanity.com/paper/2107.08580/) (2021)
- [Spatial Transformer Network on Skeleton-based Gait Recognition](https://mlsanity.com/paper/2204.03873/) (2022)
- [A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications](https://mlsanity.com/paper/2206.01038/) (2022)
- [Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences](https://mlsanity.com/paper/2302.09018/) (2023)
- [ViA: View-invariant Skeleton Action Representation Learning via Motion Retargeting](https://mlsanity.com/paper/2209.00065/) (2022)
- [Gait Recognition in the Wild with Multi-hop Temporal Switch](https://mlsanity.com/paper/2209.00355/) (2022)
- [Unified Multi-modal Unsupervised Representation Learning for Skeleton-based Action Understanding](https://mlsanity.com/paper/2311.03106/) (2023)
- [GaitMixer: Skeleton-based Gait Representation Learning via Wide-spectrum Multi-axial Mixer](https://mlsanity.com/paper/2210.15491/) (2022)
- [IIP-Transformer: Intra-Inter-Part Transformer for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2110.13385/) (2021)
- [Spatiotemporal Decouple-and-Squeeze Contrastive Learning for Semi-Supervised Skeleton-based Action Recognition](https://mlsanity.com/paper/2302.02316/) (2023)
- [Sign Language Recognition via Skeleton-Aware Multi-Model Ensemble](https://mlsanity.com/paper/2110.06161/) (2021)
- [Self-Supervised 3D Action Representation Learning with Skeleton Cloud Colorization](https://mlsanity.com/paper/2304.08799/) (2023)
- [Fusion-GCN: Multimodal Action Recognition using Graph Convolutional Networks](https://mlsanity.com/paper/2109.12946/) (2021)
- [LAC: Latent Action Composition for Skeleton-based Action Segmentation](https://mlsanity.com/paper/2308.14500/) (2023)
- [PSUMNet: Unified Modality Part Streams are All You Need for Efficient Pose-based Action Recognition](https://mlsanity.com/paper/2208.05775/) (2022)
- [Skeleton-based Action Recognition via Temporal-Channel Aggregation](https://mlsanity.com/paper/2205.15936/) (2022)

## Abstract (arXiv)

One essential problem in skeleton-based action recognition is how to extract discriminative features over all skeleton joints. However, the complexity of the State-Of-The-Art (SOTA) models of this task tends to be exceedingly sophisticated and over-parameterized, where the low efficiency in model training and inference has obstructed the development in the field, especially for large-scale action datasets. In this work, we propose an efficient but strong baseline based on Graph Convolutional Network (GCN), where three main improvements are aggregated, i.e., early fused Multiple Input Branches (MIB), Residual GCN (ResGCN) with bottleneck structure and Part-wise Attention (PartAtt) block. Firstly, an MIB is designed to enrich informative skeleton features and remain compact representations at an early fusion stage. Then, inspired by the success of the ResNet architecture in Convolutional Neural Network (CNN), a ResGCN module is introduced in GCN to alleviate computational costs and reduce learning difficulties in model training while maintain the model accuracy. Finally, a PartAtt block is proposed to discover the most essential body parts over a whole action sequence and obtain more explainable representations for different skeleton action sequences. Extensive experiments on two large-scale datasets, i.e., NTU RGB+D 60 and 120, validate that the proposed baseline slightly outperforms other SOTA models and meanwhile requires much fewer parameters during training and inference procedures, e.g., at most 34 times less than DGNN, which is one of the best SOTA methods.