mlsanityData to 7 Oct 2026

MASTAF: A Model-Agnostic Spatio-Temporal Attention Fusion Network for Few-shot Video Classification

arXiv 2112.04585 ↗First posted 8 Dec 2021cs.CV cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

We propose MASTAF, a Model-Agnostic Spatio-Temporal Attention Fusion network for few-shot video classification. MASTAF takes input from a general video spatial and temporal representation,e.g., using 2D CNN, 3D CNN, and Video Transformer. Then, to make the most of such representations, we use self- and cross-attention models to highlight the critical spatio-temporal region to increase the inter-class variations and decrease the intra-class variations. Last, MASTAF applies a lightweight fusion network and a nearest neighbor classifier to classify each query video. We demonstrate that MASTAF improves the state-of-the-art performance on three few-shot video classification benchmarks(UCF101, HMDB51, and Something-Something-V2), e.g., by up to 91.6%, 69.5%, and 60.7% for five-way one-shot video classification, respectively.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 29 of its 40 references that are in the map. First posted on arXiv 8 Dec 2021.

Builds on

29 of 40 references.

References · 29

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  5. 2016Matching Networks for One Shot Learningcited by 2,246
  6. 2021ViViT: A Video Vision Transformercited by 1,610
  7. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,092
  8. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
  9. 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 899
  10. 2019A Closer Look at Few-shot Classificationcited by 679
  11. 2017Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?cited by 551
  12. 2017Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classificationcited by 521
17 more
  1. 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
  2. 2017Temporal Relational Reasoning in Videoscited by 324
  3. 2019A Short Note on the Kinetics-700 Human Action Datasetcited by 308
  4. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  5. 2017Meta Networkscited by 268
  6. 2019Cross Attention Network for Few-shot Classificationcited by 218
  7. 2018Moments in Time Dataset: one million videos for event understandingcited by 215
  8. 2017Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognitioncited by 178
  9. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  10. 2019Few-Shot Video Classification via Temporal Alignmentcited by 124
  11. 2021VidTr: Video Transformer Without Convolutionscited by 112
  12. 2021Temporal-Relational CrossTransformers for Few-Shot Action Recognitioncited by 83
  13. 2019TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognitioncited by 71
  14. 2016One-shot Learning with Memory-Augmented Neural Networkscited by 60
  15. 2019ProtoGAN: Towards Few Shot Learning for Action Recognitioncited by 41
  16. 2021Few-shot Action Recognition with Prototype-centered Attentive Learningcited by 28
  17. 2018STAIR Actions: A Video Dataset of Everyday Home Actionscited by 6

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 5; 2025: 2.

8 papers.

  1. 2024A Comprehensive Review of Few-shot Action Recognitioncited by 11
  2. 2024SpikMamba: When SNN meets Mamba in Event-based Human Action Recognitioncited by 10
  3. 2024Task-Adapter: Task-specific Adaptation of Image Models for Few-shot Action Recognitioncited by 8
  4. 2023Semantic-aware Video Representation for Few-shot Action Recognitioncited by 7
  5. 2024TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action Recognitioncited by 3
  6. 2024MU-MAE: Multimodal Masked Autoencoders-Based One-Shot Learningcited by 0
  7. 2025Task-Adapter++: Task-specific Adaptation with Order-aware Alignment for Few-shot Action Recognitioncited by 0
  8. 2025A2M2-Net: Adaptively Aligned Multi-Scale Moment for Few-Shot Action Recognitioncited by 0