mlsanityData to 14 Oct 2026

Joint Image-Instance Spatial-Temporal Attention for Few-shot Action Recognition

arXiv 2503.14430 ↗First posted 11 Mar 2025cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Few-shot Action Recognition (FSAR) constitutes a crucial challenge in computer vision, entailing the recognition of actions from a limited set of examples. Recent approaches mainly focus on employing image-level features to construct temporal dependencies and generate prototypes for each action category. However, a considerable number of these methods utilize mainly image-level features that incorporate background noise and focus insufficiently on real foreground (action-related instances), thereby compromising the recognition capability, particularly in the few-shot scenario. To tackle this issue, we propose a novel joint Image-Instance level Spatial-temporal attention approach (I2ST) for Few-shot Action Recognition. The core concept of I2ST is to perceive the action-related instances and integrate them with image features via spatial-temporal attention. Specifically, I2ST consists of two key components: Action-related Instance Perception and Joint Image-Instance Spatial-temporal Attention. Given the basic representations from the feature extractor, the Action-related Instance Perception is introduced to perceive action-related instances under the guidance of a text-guided segmentation model. Subsequently, the Joint Image-Instance Spatial-temporal Attention is used to construct the feature dependency between instances and images...

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 45 of its 78 references that are in the map. First posted on arXiv 11 Mar 2025.

Builds on

45 of 78 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  6. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  7. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  9. 2016Matching Networks for One Shot Learningcited by 2,255
  10. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  11. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,103
  12. 2023Segment Everything Everywhere All at Oncecited by 548
33 more
  1. 2019Meta-Learning with Implicit Gradientscited by 525
  2. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  3. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  4. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 379
  5. 2018Low-Shot Learning from Imaginary Datacited by 181
  6. 2018Task-Agnostic Meta-Learning for Few-shot Learningcited by 151
  7. 2019Few-Shot Video Classification via Temporal Alignmentcited by 125
  8. 2017Few-Shot Image Recognition by Predicting Parameters from Activationscited by 122
  9. 2020Adversarial Feature Hallucination Networks for Few-Shot Learningcited by 110
  10. 2018Delta-encoder: an effective sample synthesis method for few-shot object recognitioncited by 89
  11. 2021Temporal-Relational CrossTransformers for Few-Shot Action Recognitioncited by 84
  12. 2019TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognitioncited by 71
  13. 2019Image Deformation Meta-Networks for One-Shot Learningcited by 56
  14. 2020Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognitioncited by 50
  15. 2022Hybrid Relation Guided Set Matching for Few-shot Action Recognitioncited by 50
  16. 2023CLIP-guided Prototype Modulating for Few-shot Action Recognitioncited by 41
  17. 2021TA2N: Two-Stage Action Alignment Network for Few-shot Action Recognitioncited by 35
  18. 2022Compound Prototype Matching for Few-shot Action Recognitioncited by 35
  19. 2018Pairwise Body-Part Attention for Recognizing Human-Object Interactionscited by 34
  20. 2021Few-shot Action Recognition with Prototype-centered Attentive Learningcited by 28
  21. 2023Boosting Few-shot Action Recognition with Graph-guided Hybrid Matchingcited by 24
  22. 2023How can objects help action recognition?cited by 21
  23. 2020Few-shot Action Recognition with Implicit Temporal Alignment and Pair Similarity Optimizationcited by 18
  24. 2020Cooperative Bi-path Metric for Few-shot Learningcited by 15
  25. 2023Revisiting the Spatial and Temporal Modeling for Few-shot Action Recognitioncited by 15
  26. 2023HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognitioncited by 12
  27. 2023Video Action Recognition with Attentive Semantic Unitscited by 12
  28. 2023On the Importance of Spatial Relations for Few-shot Action Recognitioncited by 11
  29. 2022Hierarchical Compositional Representations for Few-shot Action Recognitioncited by 10
  30. 2021Few-Shot Fine-Grained Action Recognition via Bidirectional Attention and Contrastive Meta-Learningcited by 7
  31. 2023Few-shot Action Recognition via Intra- and Inter-Video Information Maximizationcited by 7
  32. 2023Consistency Prototype Module and Motion Compensation for Few-Shot Action Recognition (CLIP-CPM2C)cited by 4
  33. 2023Task-Specific Alignment and Multiple Level Transformer for Few-Shot Action Recognitioncited by 2

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Beyond Label Semantics: Language-Guided Action Anatomy for Few-shot Action Recognitioncited by 2
  2. 2025Distinguishing Visually Similar Actions: Prompt-Guided Semantic Prototype Modulation for Few-Shot Action Recognitioncited by 0