# Make Skeleton-based Action Recognition Model Smaller, Faster and Better

arXiv: https://arxiv.org/abs/1907.09658 · HTML: https://mlsanity.com/paper/1907.09658/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jul 2019.

## Built on by (most cited first, 22 of 22)

- [Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition](https://mlsanity.com/paper/2106.15125/) (2021)
- [One-shot action recognition in challenging therapy scenarios](https://mlsanity.com/paper/2102.08997/) (2021)
- [PSUMNet: Unified Modality Part Streams are All You Need for Efficient Pose-based Action Recognition](https://mlsanity.com/paper/2208.05775/) (2022)
- [TrouSPI-Net: Spatio-temporal attention on parallel atrous convolutions and U-GRUs for skeletal pedestrian crossing prediction](https://mlsanity.com/paper/2109.00953/) (2021)
- [AugmentGest: Can Random Data Cropping Augmentation Boost Gesture Recognition Performance?](https://mlsanity.com/paper/2506.07216/) (2025)
- [The Imaginative Generative Adversarial Network: Automatic Data Augmentation for Dynamic Skeleton-Based Hand Gesture and Human Action Recognition](https://mlsanity.com/paper/2105.13061/) (2021)
- [Domain and View-point Agnostic Hand Action Recognition](https://mlsanity.com/paper/2103.02303/) (2021)
- [OO-dMVMT: A Deep Multi-view Multi-task Classification Framework for Real-time 3D Hand Gesture Classification and Segmentation](https://mlsanity.com/paper/2304.05956/) (2023)
- [Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions](https://mlsanity.com/paper/2108.13055/) (2021)
- [SHREC 2022 Track on Online Detection of Heterogeneous Gestures](https://mlsanity.com/paper/2207.06706/) (2022)
- [Real-Time Hand Gesture Recognition: Integrating Skeleton-Based Data Fusion and Multi-Stream CNN](https://mlsanity.com/paper/2406.15003/) (2024)
- [UAV (Unmanned Aerial Vehicles): Diverse Applications of UAV Datasets in Segmentation, Classification, Detection, and Tracking](https://mlsanity.com/paper/2409.03245/) (2024)
- [Fine-grained Hand Gesture Recognition in Multi-viewpoint Hand Hygiene](https://mlsanity.com/paper/2109.02917/) (2021)
- [ReL-SAR: Representation Learning for Skeleton Action Recognition with Convolutional Transformers and BYOL](https://mlsanity.com/paper/2409.05749/) (2024)
- [Evolving Skeletons: Motion Dynamics in Action Recognition](https://mlsanity.com/paper/2501.02593/) (2025)
- [SHREC 2021: Track on Skeleton-based Hand Gesture Recognition in the Wild](https://mlsanity.com/paper/2106.10980/) (2021)
- [A New Adjacency Matrix Configuration in GCN-based Models for Skeleton-based Action Recognition](https://mlsanity.com/paper/2206.14344/) (2022)
- [Real-Time Elderly Monitoring for Senior Safety by Lightweight Human Action Recognition](https://mlsanity.com/paper/2207.10519/) (2022)
- [Actor-identified Spatiotemporal Action Detection -- Detecting Who Is Doing What in Videos](https://mlsanity.com/paper/2208.12940/) (2022)
- [Evaluating Temporal Patterns in Applied Infant Affect Recognition](https://mlsanity.com/paper/2209.03496/) (2022)
- [Unsupervised Discovery of Long-Term Spatiotemporal Periodic Workflows in Human Activities](https://mlsanity.com/paper/2511.14945/) (2025)
- [OMG-Bench: A New Challenging Benchmark for Skeleton-based Online Micro Hand Gesture Recognition](https://mlsanity.com/paper/2512.16727/) (2025)

## Abstract (arXiv)

Although skeleton-based action recognition has achieved great success in recent years, most of the existing methods may suffer from a large model size and slow execution speed. To alleviate this issue, we analyze skeleton sequence properties to propose a Double-feature Double-motion Network (DD-Net) for skeleton-based action recognition. By using a lightweight network structure (i.e., 0.15 million parameters), DD-Net can reach a super fast speed, as 3,500 FPS on one GPU, or, 2,000 FPS on one CPU. By employing robust features, DD-Net achieves the state-of-the-art performance on our experimental datasets: SHREC (i.e., hand actions) and JHMDB (i.e., body actions). Our code will be released with this paper later.