mlsanityData to 7 Oct 2026

Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition

arXiv 2210.16820 ↗First posted 30 Oct 2022cs.CV cs.AI cs.LGcited by 22

Not on the map. Why?

Abstract (arXiv)

We propose a Few-shot Learning pipeline for 3D skeleton-based action recognition by Joint tEmporal and cAmera viewpoiNt alIgnmEnt (JEANIE). To factor out misalignment between query and support sequences of 3D body joints, we propose an advanced variant of Dynamic Time Warping which jointly models each smooth path between the query and support frames to achieve simultaneously the best alignment in the temporal and simulated camera viewpoint spaces for end-to-end learning under the limited few-shot training data. Sequences are encoded with a temporal block encoder based on Simple Spectral Graph Convolution, a lightweight linear Graph Neural Network backbone. We also include a setting with a transformer. Finally, we propose a similarity-based loss which encourages the alignment of sequences of the same class while preventing the alignment of unrelated sequences. We show state-of-the-art results on NTU-60, NTU-120, Kinetics-skeleton and UWA3D Multiview Activity II.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 52 of its 97 references that are in the map. First posted on arXiv 30 Oct 2022.

Builds on

52 of 97 references.

References · 52

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2016Matching Networks for One Shot Learningcited by 2,246
  7. 2017The Kinetics Human Action Video Datasetcited by 1,894
  8. 2019Simplifying Graph Convolutional Networkscited by 1,470
  9. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  10. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  11. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  12. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
38 more
  1. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 683
  2. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 530
  3. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  4. 2016Convolutional Two-Stream Network Fusion for Video Action Recognitioncited by 384
  5. 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 339
  6. 2017Temporal Segment Networks for Action Recognition in Videoscited by 279
  7. 2017Soft-DTW: a Differentiable Loss Function for Time-Seriescited by 265
  8. 2019Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 228
  9. 2017A New Representation of Skeleton Sequences for 3D Action Recognitioncited by 125
  10. 2019Few-Shot Video Classification via Temporal Alignmentcited by 124
  11. 2020Adversarial Feature Hallucination Networks for Few-Shot Learningcited by 110
  12. 2017View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Datacited by 105
  13. 2021On Learning the Geodesic Path for Incremental Learningcited by 85
  14. 2018View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognitioncited by 84
  15. 2019Meta-Learning of Neural Architectures for Few-Shot Learningcited by 73
  16. 2019ProtoGAN: Towards Few Shot Learning for Action Recognitioncited by 41
  17. 2018A Generative Approach to Zero-Shot and Few-Shot Action Recognitioncited by 39
  18. 2019Spatiotemporal Pyramid Network for Video Action Recognitioncited by 37
  19. 2020Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learningcited by 31
  20. 2020TAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classificationcited by 30
  21. 2020Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognitioncited by 30
  22. 2019A Comparative Review of Recent Kinect-based Action Recognition Algorithmscited by 29
  23. 2020Tensor Representations for Action Recognitioncited by 28
  24. 2014Histogram of Oriented Principal Components for Cross-View Action Recognitioncited by 27
  25. 2020Power Normalizations in Fine-grained Image, Few-shot Image and Graph Classificationcited by 27
  26. 2021Few-shot Keypoint Detection with Uncertainty Learning for Unseen Speciescited by 27
  27. 2020Self-supervising Action Recognition by Statistical Moment and Subspace Descriptorscited by 24
  28. 2022Contrastive Laplacian Eigenmapscited by 24
  29. 2020Skeleton-DML: Deep Metric Learning for Skeleton-Based One-Shot Action Recognitioncited by 23
  30. 2021Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognitioncited by 22
  31. 2019Fisher-Bures Adversary Graph Convolutional Networkscited by 18
  32. 2020SL-DML: Signal Level Deep Metric Learning for Multimodal One-Shot Action Recognitioncited by 18
  33. 2014HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognitioncited by 15
  34. 2019Loss Switching Fusion with Similarity Search for Video Classificationcited by 15
  35. 2021High-order Tensor Pooling with Attention for Action Recognitioncited by 14
  36. 2018CNN-based Action Recognition and Supervised Domain Adaptation on 3D Body Skeletons via Kernel Feature Mapscited by 13
  37. 2018Power Normalizing Second-order Similarity Network for Few-shot Learningcited by 13
  38. 2022Multi-level Second-order Few-shot Learningcited by 12

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 5; 2025: 6; 2026: 3.

22 papers.

Sort:

  1. 2024Advancing Video Anomaly Detection: A Concise Review and a New Datasetcited by 48
  2. 20233Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognitioncited by 40
  3. 2023Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinementcited by 30
  4. 2023Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentationcited by 24
  5. 2024Learnable Expansion of Graph Operators for Multi-Modal Feature Fusioncited by 22
  6. 2024Do Language Models Understand Time?cited by 14
  7. 2023One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matchingcited by 12
  8. 2023Flow Dynamics Correction for Action Recognitioncited by 12
  9. 2023Traffic Forecasting on New Roads Using Spatial Contrastive Pre-Training (SCPT)cited by 11
  10. 2024A Comprehensive Review of Few-shot Action Recognitioncited by 11
  11. 2024Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignmentcited by 10
  12. 20253D Skeleton-Based Action Recognition: A Reviewcited by 6
10 more
  1. 2025MoFM: A Large-Scale Human Motion Foundation Modelcited by 5
  2. 2025SkeletonX: Data-Efficient Skeleton-based Action Recognition via Cross-sample Feature Aggregationcited by 3
  3. 2025Feature Hallucination for Self-supervised Action Recognitioncited by 3
  4. 2023Exploiting Field Dependencies for Learning on Categorical Datacited by 2
  5. 2025Few-Shot Learning in Video and 3D Object Detection: A Surveycited by 2
  6. 2025Learning Time in Static Classifierscited by 2
  7. 2023Position and Orientation-Aware One-Shot Learning for Medical Action Recognition from Signal Datacited by 1
  8. 2026Cross-Domain Human Action Recognition from Multiview Motion and Textual Descriptionscited by 0
  9. 2026Uncertainty-DTW for Sequences and Visual Tokenscited by 0
  10. 2026SkelHCC: A Hyperbolic CLIP-Driven Cache Adaptation Framework for Skeleton-based One-Shot Action Recognitioncited by 0