mlsanityData to 7 Oct 2026

MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action Recognition

arXiv 2405.02077 ↗First posted 3 May 2024cs.CVcited by 25

Not on the map. Why?

Abstract (arXiv)

Recent few-shot action recognition (FSAR) methods typically perform semantic matching on learned discriminative features to achieve promising performance. However, most FSAR methods focus on single-scale (e.g., frame-level, segment-level, etc) feature alignment, which ignores that human actions with the same semantic may appear at different velocities. To this end, we develop a novel Multi-Velocity Progressive-alignment (MVP-Shot) framework to progressively learn and align semantic-related action features at multi-velocity levels. Concretely, a Multi-Velocity Feature Alignment (MVFA) module is designed to measure the similarity between features from support and query videos with different velocity scales and then merge all similarity scores in a residual fashion. To avoid the multiple velocity features deviating from the underlying motion semantic, our proposed Progressive Semantic-Tailored Interaction (PSTI) module injects velocity-tailored text information into the video feature via feature interaction on channel and temporal domains at different velocities. The above two modules compensate for each other to make more accurate query sample predictions under the few-shot settings. Experimental results show our method outperforms current state-of-the-art methods on multiple standard few-shot benchmarks (i.e., HMDB51, UCF101, Kinetics, and SSv2-small).

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 47 of its 71 references that are in the map. First posted on arXiv 3 May 2024.

Builds on

47 of 71 references.

References · 47

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020Language Models are Few-Shot Learnerscited by 32,199
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  6. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  7. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  8. 2016Matching Networks for One Shot Learningcited by 2,246
  9. 2018SlowFast Networks for Video Recognitioncited by 1,862
  10. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,427
  11. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,092
  12. 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 899
35 more
  1. 2018TSM: Temporal Shift Module for Efficient Video Understandingcited by 852
  2. 2021VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understandingcited by 596
  3. 2019Meta-Learning with Implicit Gradientscited by 523
  4. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  5. 2021Prompting Visual-Language Models for Efficient Video Understandingcited by 309
  6. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  7. 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 194
  8. 2018Task-Agnostic Meta-Learning for Few-shot Learningcited by 151
  9. 2019Few-Shot Video Classification via Temporal Alignmentcited by 124
  10. 2017Few-Shot Image Recognition by Predicting Parameters from Activationscited by 122
  11. 2020Adversarial Feature Hallucination Networks for Few-Shot Learningcited by 110
  12. 2019TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learningcited by 90
  13. 2021Temporal-Relational CrossTransformers for Few-Shot Action Recognitioncited by 83
  14. 2019TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognitioncited by 71
  15. 2019Image Deformation Meta-Networks for One-Shot Learningcited by 56
  16. 2021Spatio-temporal Relation Modeling for Few-shot Action Recognitioncited by 52
  17. 2020Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognitioncited by 50
  18. 2022Hybrid Relation Guided Set Matching for Few-shot Action Recognitioncited by 49
  19. 2019Spatiotemporal Co-attention Recurrent Neural Networks for Human-Skeleton Motion Predictioncited by 46
  20. 2023CLIP-guided Prototype Modulating for Few-shot Action Recognitioncited by 41
  21. 2018Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognitioncited by 36
  22. 2023MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognitioncited by 36
  23. 2021TA2N: Two-Stage Action Alignment Network for Few-shot Action Recognitioncited by 35
  24. 2022Compound Prototype Matching for Few-shot Action Recognitioncited by 35
  25. 2022SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classificationcited by 34
  26. 2023M3Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognitioncited by 34
  27. 2019Learning Adaptive Classifiers Synthesis for Generalized Few-Shot Learningcited by 29
  28. 2022MAR: Masked Autoencoders for Efficient Action Recognitioncited by 29
  29. 2023Semantic Prompt for Few-Shot Image Recognitioncited by 29
  30. 2021Learning Implicit Temporal Alignment for Few-shot Video Classificationcited by 27
  31. 2023Boosting Few-shot Action Recognition with Graph-guided Hybrid Matchingcited by 24
  32. 2021CoCo-BERT: Improving Video-Language Pre-training with Contrastive Cross-modal Matching and Denoisingcited by 17
  33. 2023Revisiting the Spatial and Temporal Modeling for Few-shot Action Recognitioncited by 15
  34. 2020TAEN: Temporal Aware Embedding Network for Few-Shot Action Recognitioncited by 12
  35. 2022Hierarchical Compositional Representations for Few-shot Action Recognitioncited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 14; 2026: 7.

25 papers.

Sort:

By area:

  1. 2025Vision-centric Token Compression in Large Language Modelcited by 21
  2. 2024A Comprehensive Review of Few-shot Action Recognitioncited by 11
  3. 2024Locality-aware Cross-modal Correspondence Learning for Dense Audio-Visual Events Localizationcited by 10
  4. 2025FiLo++: Zero-/Few-Shot Anomaly Detection by Fused Fine-Grained Descriptions and Deformable Localizationcited by 7
  5. 2025OutDreamer: Video Outpainting with a Diffusion Transformercited by 4
  6. 2025OmniGaze: Reward-inspired Generalizable Gaze Estimation In The Wildcited by 4
  7. 2026Spatio-temporal Decoupled Knowledge Compensator for Few-Shot Action Recognitioncited by 4
  8. 2025EVA02-AT: Egocentric Video-Language Understanding with Spatial-Temporal Rotary Positional Embeddings and Symmetric Optimizationcited by 3
  9. 2024SSPA: Split-and-Synthesize Prompting with Gated Alignments for Multi-Label Image Recognitioncited by 2
  10. 2025Beyond Label Semantics: Language-Guided Action Anatomy for Few-shot Action Recognitioncited by 2
  11. 2025VIKSER: Visual Knowledge-Driven Self-Reinforcing Reasoning Frameworkcited by 1
  12. 2026SRENet: Spectral Re-Entry Network for Point Cloud Action Recognitioncited by 1
13 more
  1. 2024Video-to-Task Learning via Motion-Guided Attention for Few-Shot Action Recognitioncited by 0
  2. 2025Hierarchical Relation-augmented Representation Generalization for Few-shot Action Recognitioncited by 0
  3. 2025Diffusion Disambiguation Models for Partial Label Learningcited by 0
  4. 2025Harnessing Group-Oriented Consistency Constraints for Semi-Supervised Semantic Segmentation in CdZnTe Semiconductorscited by 0
  5. 2025FedMGP: Personalized Federated Learning with Multi-Group Text-Visual Promptscited by 0
  6. 2025H3Former: Hypergraph-based Semantic-Aware Aggregation via Hyperbolic Hierarchical Contrastive Loss for Fine-Grained Visual Classificationcited by 0
  7. 2025Label-Efficient Skeleton-based Recognition with Stable-Invertible Graph Convolutional Networkscited by 0
  8. 2025Active Learning for GCN-based Action Recognitioncited by 0
  9. 2026Knowledge is Power: Advancing Few-shot Action Recognition with Multimodal Semantics from MLLMscited by 0
  10. 2026STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognitioncited by 0
  11. 2026DREAM: Extending Vision-Language Models with Dual-Objective Encoding for Cross-Modal Retrievalcited by 0
  12. 2026Forbid Your Attention: Fooling Multimodal Large Language Models by Selectively Removing Intrinsic Focus in Spectral Domaincited by 0
  13. 2026Few-Shot Video Recognition via Hierarchical Metric Learningcited by 0