mlsanityData to 7 Oct 2026

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

arXiv 1907.09658 ↗First posted 23 Jul 2019cs.CVcited by 22

Not on the map. Why?

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.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 8; 2022: 6; 2023: 1; 2024: 3; 2025: 4.

22 papers.

Sort:

  1. 2021Constructing Stronger and Faster Baselines for Skeleton-based Action Recognitioncited by 87
  2. 2021One-shot action recognition in challenging therapy scenarioscited by 15
  3. 2022PSUMNet: Unified Modality Part Streams are All You Need for Efficient Pose-based Action Recognitioncited by 14
  4. 2021TrouSPI-Net: Spatio-temporal attention on parallel atrous convolutions and U-GRUs for skeletal pedestrian crossing predictioncited by 13
  5. 2025AugmentGest: Can Random Data Cropping Augmentation Boost Gesture Recognition Performance?cited by 10
  6. 2021The Imaginative Generative Adversarial Network: Automatic Data Augmentation for Dynamic Skeleton-Based Hand Gesture and Human Action Recognitioncited by 8
  7. 2021Domain and View-point Agnostic Hand Action Recognitioncited by 5
  8. 2023OO-dMVMT: A Deep Multi-view Multi-task Classification Framework for Real-time 3D Hand Gesture Classification and Segmentationcited by 3
  9. 2021Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directionscited by 2
  10. 2022SHREC 2022 Track on Online Detection of Heterogeneous Gesturescited by 2
  11. 2024Real-Time Hand Gesture Recognition: Integrating Skeleton-Based Data Fusion and Multi-Stream CNNcited by 2
  12. 2024UAV (Unmanned Aerial Vehicles): Diverse Applications of UAV Datasets in Segmentation, Classification, Detection, and Trackingcited by 2
10 more
  1. 2021Fine-grained Hand Gesture Recognition in Multi-viewpoint Hand Hygienecited by 1
  2. 2024ReL-SAR: Representation Learning for Skeleton Action Recognition with Convolutional Transformers and BYOLcited by 1
  3. 2025Evolving Skeletons: Motion Dynamics in Action Recognitioncited by 1
  4. 2021SHREC 2021: Track on Skeleton-based Hand Gesture Recognition in the Wildcited by 0
  5. 2022A New Adjacency Matrix Configuration in GCN-based Models for Skeleton-based Action Recognitioncited by 0
  6. 2022Real-Time Elderly Monitoring for Senior Safety by Lightweight Human Action Recognitioncited by 0
  7. 2022Actor-identified Spatiotemporal Action Detection -- Detecting Who Is Doing What in Videoscited by 0
  8. 2022Evaluating Temporal Patterns in Applied Infant Affect Recognitioncited by 0
  9. 2025Unsupervised Discovery of Long-Term Spatiotemporal Periodic Workflows in Human Activitiescited by 0
  10. 2025OMG-Bench: A New Challenging Benchmark for Skeleton-based Online Micro Hand Gesture Recognitioncited by 0