mlsanityData to 14 Oct 2026

Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching

arXiv 2308.09346 ↗First posted 18 Aug 2023cs.CVcited by 24

Not on the map. Why?

Abstract (arXiv)

Class prototype construction and matching are core aspects of few-shot action recognition. Previous methods mainly focus on designing spatiotemporal relation modeling modules or complex temporal alignment algorithms. Despite the promising results, they ignored the value of class prototype construction and matching, leading to unsatisfactory performance in recognizing similar categories in every task. In this paper, we propose GgHM, a new framework with Graph-guided Hybrid Matching. Concretely, we learn task-oriented features by the guidance of a graph neural network during class prototype construction, optimizing the intra- and inter-class feature correlation explicitly. Next, we design a hybrid matching strategy, combining frame-level and tuple-level matching to classify videos with multivariate styles. We additionally propose a learnable dense temporal modeling module to enhance the video feature temporal representation to build a more solid foundation for the matching process. GgHM shows consistent improvements over other challenging baselines on several few-shot datasets, demonstrating the effectiveness of our method. The code will be publicly available at https://github.com/jiazheng-xing/GgHM.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Builds on 34 of its 47 references that are in the map. First posted on arXiv 18 Aug 2023.

Builds on

34 of 47 references.

References · 34

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  2. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  4. 2016Matching Networks for One Shot Learningcited by 2,255
  5. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,620
  6. 2021ViViT: A Video Vision Transformercited by 1,620
  7. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,103
  8. 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 902
  9. 2021Multiscale Vision Transformerscited by 897
  10. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 379
  11. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  12. 2017Temporal Relational Reasoning in Videoscited by 324
22 more
  1. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 294
  2. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  3. 2019Few-Shot Video Classification via Temporal Alignmentcited by 125
  4. 2019Edge-labeling Graph Neural Network for Few-shot Learningcited by 114
  5. 2021VidTr: Video Transformer Without Convolutionscited by 112
  6. 2019Finding Task-Relevant Features for Few-Shot Learning by Category Traversalcited by 101
  7. 2019TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learningcited by 91
  8. 2021Temporal-Relational CrossTransformers for Few-Shot Action Recognitioncited by 84
  9. 2019TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognitioncited by 71
  10. 2021Spatio-temporal Relation Modeling for Few-shot Action Recognitioncited by 53
  11. 2020Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognitioncited by 50
  12. 2022Hybrid Relation Guided Set Matching for Few-shot Action Recognitioncited by 50
  13. 2021TA2N: Two-Stage Action Alignment Network for Few-shot Action Recognitioncited by 35
  14. 2022Compound Prototype Matching for Few-shot Action Recognitioncited by 35
  15. 2021Learning Implicit Temporal Alignment for Few-shot Video Classificationcited by 27
  16. 2022Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignmentscited by 23
  17. 2022Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognitioncited by 15
  18. 2023Revisiting the Spatial and Temporal Modeling for Few-shot Action Recognitioncited by 15
  19. 2022Multimodal Prototype-Enhanced Network for Few-Shot Action Recognitioncited by 13
  20. 2021ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-shot Learningcited by 11
  21. 2021Unsupervised Few-Shot Action Recognition via Action-Appearance Aligned Meta-Adaptationcited by 11
  22. 2022Hierarchical Compositional Representations for Few-shot Action Recognitioncited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 7; 2025: 9; 2026: 5.

24 papers.

Sort:

By area:

  1. 2024MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action Recognitioncited by 25
  2. 2023HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understandingcited by 22
  3. 2024USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelationcited by 16
  4. 2024A Comprehensive Review of Few-shot Action Recognitioncited by 11
  5. 2024Trajectory-aligned Space-time Tokens for Few-shot Action Recognitioncited by 10
  6. 2025Temporal Alignment-Free Video Matching for Few-shot Action Recognitioncited by 10
  7. 2023Few-shot Action Recognition with Captioning Foundation Modelscited by 9
  8. 2025Trokens: Semantic-Aware Relational Trajectory Tokens for Few-Shot Action Recognitioncited by 7
  9. 2024TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action Recognitioncited by 4
  10. 2026Spatio-temporal Decoupled Knowledge Compensator for Few-Shot Action Recognitioncited by 4
  11. 2025FedSC: Federated Learning with Semantic-Aware Collaborationcited by 3
  12. 2024Manta: Enhancing Mamba for Few-Shot Action Recognition of Long Sub-Sequencecited by 2
12 more
  1. 2025Joint Image-Instance Spatial-Temporal Attention for Few-shot Action Recognitioncited by 2
  2. 2025Beyond Label Semantics: Language-Guided Action Anatomy for Few-shot Action Recognitioncited by 2
  3. 2023D2ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action Recognitioncited by 1
  4. 2024SOAP: Enhancing Spatio-Temporal Relation and Motion Information Capturing for Few-Shot Action Recognitioncited by 1
  5. 2025Hierarchical Relation-augmented Representation Generalization for Few-shot Action Recognitioncited by 0
  6. 2025A2M2-Net: Adaptively Aligned Multi-Scale Moment for Few-Shot Action Recognitioncited by 0
  7. 2025Otter: Mitigating Background Distractions of Wide-Angle Few-Shot Action Recognition with Enhanced RWKVcited by 0
  8. 2025Task-Specific Distance Correlation Matching for Few-Shot Action Recognitioncited by 0
  9. 2026A Baseline Study and Benchmark for Few-Shot Open-Set Action Recognition with Feature Residual Discriminationcited by 0
  10. 2026Knowledge is Power: Advancing Few-shot Action Recognition with Multimodal Semantics from MLLMscited by 0
  11. 2026Comparison Drives Preference: Reference-Aware Modeling for AI-Generated Video Quality Assessmentcited by 0
  12. 2026Few-Shot Video Recognition via Hierarchical Metric Learningcited by 0