mlsanityData to 14 Oct 2026

One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching

arXiv 2307.07286 ↗First posted 14 Jul 2023cs.CV cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

One-shot skeleton action recognition, which aims to learn a skeleton action recognition model with a single training sample, has attracted increasing interest due to the challenge of collecting and annotating large-scale skeleton action data. However, most existing studies match skeleton sequences by comparing their feature vectors directly which neglects spatial structures and temporal orders of skeleton data. This paper presents a novel one-shot skeleton action recognition technique that handles skeleton action recognition via multi-scale spatial-temporal feature matching. We represent skeleton data at multiple spatial and temporal scales and achieve optimal feature matching from two perspectives. The first is multi-scale matching which captures the scale-wise semantic relevance of skeleton data at multiple spatial and temporal scales simultaneously. The second is cross-scale matching which handles different motion magnitudes and speeds by capturing sample-wise relevance across multiple scales. Extensive experiments over three large-scale datasets (NTU RGB+D, NTU RGB+D 120, and PKU-MMD) show that our method achieves superior one-shot skeleton action recognition, and it outperforms the state-of-the-art consistently by large margins.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 40 of its 70 references that are in the map. First posted on arXiv 14 Jul 2023.

Builds on

40 of 70 references.

References · 40

  1. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  2. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  3. 2016Matching Networks for One Shot Learningcited by 2,255
  4. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,620
  5. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
  6. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  7. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 686
  8. 2019A Closer Look at Few-shot Classificationcited by 684
  9. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 533
  10. 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 343
  11. 2021Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognitioncited by 322
  12. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 294
28 more
  1. 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
  2. 2016Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognitioncited by 143
  3. 2016An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Datacited by 126
  4. 2017A New Representation of Skeleton Sequences for 3D Action Recognitioncited by 126
  5. 2019Few-Shot Video Classification via Temporal Alignmentcited by 125
  6. 2018Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregationcited by 106
  7. 2017View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Datacited by 105
  8. 2020Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognitioncited by 91
  9. 2018View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognitioncited by 84
  10. 2019TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognitioncited by 71
  11. 2022Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognitioncited by 71
  12. 2019Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searchingcited by 70
  13. 2017Skeleton-based Action Recognition with Convolutional Neural Networkscited by 54
  14. 2017Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gatescited by 54
  15. 2021Spatio-temporal Relation Modeling for Few-shot Action Recognitioncited by 53
  16. 2022Hybrid Relation Guided Set Matching for Few-shot Action Recognitioncited by 50
  17. 2022STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognitioncited by 43
  18. 2021Learning Dynamic Alignment via Meta-filter for Few-shot Learningcited by 41
  19. 20233Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognitioncited by 40
  20. 2020Skeleton-DML: Deep Metric Learning for Skeleton-Based One-Shot Action Recognitioncited by 23
  21. 2022Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognitioncited by 22
  22. 2022Uncertainty-DTW for Time Series and Sequencescited by 21
  23. 2017Scene Flow to Action Map: A New Representation for RGB-D based Action Recognition with Convolutional Neural Networkscited by 20
  24. 2020SL-DML: Signal Level Deep Metric Learning for Multimodal One-Shot Action Recognitioncited by 18
  25. 2023Self-Supervised 3D Action Representation Learning with Skeleton Cloud Colorizationcited by 16
  26. 2021One-shot action recognition in challenging therapy scenarioscited by 15
  27. 2018Ensemble One-dimensional Convolution Neural Networks for Skeleton-based Action Recognitioncited by 10
  28. 2022Adaptive Local-Component-aware Graph Convolutional Network for One-shot Skeleton-based Action Recognitioncited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 4; 2026: 4.

12 papers.

  1. 2024CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Mannercited by 11
  2. 2024A Comprehensive Review of Few-shot Action Recognitioncited by 11
  3. 2024Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignmentcited by 10
  4. 2024Towards Physical World Backdoor Attacks against Skeleton Action Recognitioncited by 7
  5. 2025MoFM: A Large-Scale Human Motion Foundation Modelcited by 5
  6. 2025Zero-Shot Skeleton-Based Action Recognition With Prototype-Guided Feature Alignmentcited by 4
  7. 2025SkeletonX: Data-Efficient Skeleton-based Action Recognition via Cross-sample Feature Aggregationcited by 3
  8. 2026SkeletonContext: Skeleton-side Context Prompt Learning for Zero-Shot Skeleton-based Action Recognitioncited by 3
  9. 2025Heatmap Pooling Network for Action Recognition from RGB Videoscited by 1
  10. 2026Skarimva: Skeleton-based Action Recognition is a Multi-view Applicationcited by 0
  11. 2026SkelHCC: A Hyperbolic CLIP-Driven Cache Adaptation Framework for Skeleton-based One-Shot Action Recognitioncited by 0
  12. 2026STAR: Skeletal Token Alignment and Rearrangement for Interaction Recognitioncited by 0