# AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognition

arXiv: https://arxiv.org/abs/2103.11770 · HTML: https://mlsanity.com/paper/2103.11770/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 43 references that are in the map.
- First posted on arXiv 22 Mar 2021.

## Builds on (most cited first, 28 of 28)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification](https://mlsanity.com/paper/1712.04851/) (2017)
- [Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks](https://mlsanity.com/paper/1711.10305/) (2017)
- [Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2003.14111/) (2020)
- [Temporal Action Detection with Structured Segment Networks](https://mlsanity.com/paper/1704.06228/) (2017)
- [Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/1904.12659/) (2019)
- [An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1902.09130/) (2019)
- [Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN](https://mlsanity.com/paper/1803.04831/) (2018)
- [Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition](https://mlsanity.com/paper/1904.01189/) (2019)
- [AdaFrame: Adaptive Frame Selection for Fast Video Recognition](https://mlsanity.com/paper/1811.12432/) (2018)
- [SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition](https://mlsanity.com/paper/1904.04289/) (2019)
- [View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data](https://mlsanity.com/paper/1703.08274/) (2017)
- [AR-Net: Adaptive Frame Resolution for Efficient Action Recognition](https://mlsanity.com/paper/2007.15796/) (2020)
- [Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching](https://mlsanity.com/paper/1911.04131/) (2019)
- [Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition](https://mlsanity.com/paper/1907.13369/) (2019)
- [LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition](https://mlsanity.com/paper/1912.01601/) (2019)
- [Skeleton-based Action Recognition with Convolutional Neural Networks](https://mlsanity.com/paper/1704.07595/) (2017)
- [Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning](https://mlsanity.com/paper/1805.02335/) (2018)
- [Self-Attention Network for Skeleton-based Human Action Recognition](https://mlsanity.com/paper/1912.08435/) (2019)
- [Action Recognition via Pose-Based Graph Convolutional Networks with Intermediate Dense Supervision](https://mlsanity.com/paper/1911.12509/) (2019)

## Built on by (most cited first, 21 of 21)

- [Masked Motion Predictors are Strong 3D Action Representation Learners](https://mlsanity.com/paper/2308.07092/) (2023)
- [3Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition](https://mlsanity.com/paper/2303.14474/) (2023)
- [CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation](https://mlsanity.com/paper/2208.12448/) (2022)
- [Topology-aware Convolutional Neural Network for Efficient Skeleton-based Action Recognition](https://mlsanity.com/paper/2112.04178/) (2021)
- [Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/2105.01563/) (2021)
- [DVANet: Disentangling View and Action Features for Multi-View Action Recognition](https://mlsanity.com/paper/2312.05719/) (2023)
- [Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in Videos](https://mlsanity.com/paper/2404.07645/) (2024)
- [GCNext: Towards the Unity of Graph Convolutions for Human Motion Prediction](https://mlsanity.com/paper/2312.11850/) (2023)
- [Pyramid Self-attention Polymerization Learning for Semi-supervised Skeleton-based Action Recognition](https://mlsanity.com/paper/2302.02327/) (2023)
- [Dynamic Dense Graph Convolutional Network for Skeleton-based Human Motion Prediction](https://mlsanity.com/paper/2311.17408/) (2023)
- [Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignment](https://mlsanity.com/paper/2402.04599/) (2024)
- [ERA: Expert Retrieval and Assembly for Early Action Prediction](https://mlsanity.com/paper/2207.09675/) (2022)
- [Action Selection Learning for Multi-label Multi-view Action Recognition](https://mlsanity.com/paper/2410.03302/) (2024)
- [Towards To-a-T Spatio-Temporal Focus for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2202.02314/) (2022)
- [MultiSensor-Home: A Wide-area Multi-modal Multi-view Dataset for Action Recognition and Transformer-based Sensor Fusion](https://mlsanity.com/paper/2504.02287/) (2025)
- [Dual-view Spatio-Temporal Feature Fusion with CNN-Transformer Hybrid Network for Chinese Isolated Sign Language Recognition](https://mlsanity.com/paper/2506.06966/) (2025)
- [Learning Snippet-to-Motion Progression for Skeleton-based Human Motion Prediction](https://mlsanity.com/paper/2307.14006/) (2023)
- [I2MD: 3D Action Representation Learning with Inter- and Intra-modal Mutual Distillation](https://mlsanity.com/paper/2310.15568/) (2023)
- [Diffusion-based Target Sampler for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2303.12724/) (2023)
- [Local Spherical Harmonics Improve Skeleton-Based Hand Action Recognition](https://mlsanity.com/paper/2308.10557/) (2023)
- [Self-supervised Extraction of Human Motion Structures via Frame-wise Discrete Features](https://mlsanity.com/paper/2309.05972/) (2023)

## Abstract (arXiv)

Existing methods for skeleton-based action recognition mainly focus on improving the recognition accuracy, whereas the efficiency of the model is rarely considered. Recently, there are some works trying to speed up the skeleton modeling by designing light-weight modules. However, in addition to the model size, the amount of the data involved in the calculation is also an important factor for the running speed, especially for the skeleton data where most of the joints are redundant or non-informative to identify a specific skeleton. Besides, previous works usually employ one fix-sized model for all the samples regardless of the difficulty of recognition, which wastes computations for easy samples. To address these limitations, a novel approach, called AdaSGN, is proposed in this paper, which can reduce the computational cost of the inference process by adaptively controlling the input number of the joints of the skeleton on-the-fly. Moreover, it can also adaptively select the optimal model size for each sample to achieve a better trade-off between accuracy and efficiency. We conduct extensive experiments on three challenging datasets, namely, NTU-60, NTU-120 and SHREC, to verify the superiority of the proposed approach, where AdaSGN achieves comparable or even higher performance with much lower GFLOPs compared with the baseline method.