mlsanityData to 14 Oct 2026

ActionVLAD: Learning spatio-temporal aggregation for action classification

arXiv 1704.02895 ↗First posted 10 Apr 2017cs.CVcited by 73

Not on the map. Why?

Abstract (arXiv)

In this work, we introduce a new video representation for action classification that aggregates local convolutional features across the entire spatio-temporal extent of the video. We do so by integrating state-of-the-art two-stream networks with learnable spatio-temporal feature aggregation. The resulting architecture is end-to-end trainable for whole-video classification. We investigate different strategies for pooling across space and time and combining signals from the different streams. We find that: (i) it is important to pool jointly across space and time, but (ii) appearance and motion streams are best aggregated into their own separate representations. Finally, we show that our representation outperforms the two-stream base architecture by a large margin (13% relative) as well as out-performs other baselines with comparable base architectures on HMDB51, UCF101, and Charades video classification benchmarks.

Key facts. Cited by 73 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 29; 2022: 18; 2023: 12; 2024: 7; 2025: 4; 2026: 3.

73 papers.

Sort:

By area:

  1. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,620
  2. 2021Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrievalcited by 1,177
  3. 2024MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understandingcited by 229
  4. 2021Anticipative Video Transformercited by 200
  5. 2022MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognitioncited by 189
  6. 2021Towards Long-Form Video Understandingcited by 146
  7. 2021VidTr: Video Transformer Without Convolutionscited by 112
  8. 2021T2VLAD: Global-Local Sequence Alignment for Text-Video Retrievalcited by 103
  9. 2023AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?cited by 81
  10. 2023HierVL: Learning Hierarchical Video-Language Embeddingscited by 66
  11. 2021SeqNet: Learning Descriptors for Sequence-based Hierarchical Place Recognitioncited by 57
  12. 2022Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videoscited by 50
38 more
  1. 2021Video Contrastive Learning with Global Contextcited by 41
  2. 2022Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipationcited by 41
  3. 2023Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphscited by 39
  4. 2021Space-Time Crop & Attend: Improving Cross-modal Video Representation Learningcited by 31
  5. 2022Rethinking Learning Approaches for Long-Term Action Anticipationcited by 29
  6. 2023PALM: Predicting Actions through Language Modelscited by 29
  7. 2021Coarse to Fine Multi-Resolution Temporal Convolutional Networkcited by 28
  8. 2021No frame left behind: Full Video Action Recognitioncited by 24
  9. 2022C2F-TCN: A Framework for Semi and Fully Supervised Temporal Action Segmentationcited by 23
  10. 2021Social Fabric: Tubelet Compositions for Video Relation Detectioncited by 18
  11. 2023AutoLabel: CLIP-based framework for Open-set Video Domain Adaptationcited by 18
  12. 2021TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge Devicecited by 17
  13. 2022Gate-Shift-Fuse for Video Action Recognitioncited by 15
  14. 2021Coarse Temporal Attention Network (CTA-Net) for Driver's Activity Recognitioncited by 14
  15. 2022PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Datacited by 14
  16. 2021DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learningcited by 13
  17. 2022Surgical Skill Assessment via Video Semantic Aggregationcited by 13
  18. 2021CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognitioncited by 12
  19. 2024Spatio-Temporal Attention and Gaussian Processes for Personalized Video Gaze Estimationcited by 12
  20. 2021Unsupervised Few-Shot Action Recognition via Action-Appearance Aligned Meta-Adaptationcited by 11
  21. 2021Temporal-attentive Covariance Pooling Networks for Video Recognitioncited by 11
  22. 2023DiffAnt: Diffusion Models for Action Anticipationcited by 9
  23. 2024Language Model Guided Interpretable Video Action Reasoningcited by 8
  24. 2021Delta Sampling R-BERT for limited data and low-light action recognitioncited by 7
  25. 2022VLAD-VSA: Cross-Domain Face Presentation Attack Detection with Vocabulary Separation and Adaptationcited by 7
  26. 2021Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionariescited by 6
  27. 2021Higher Order Recurrent Space-Time Transformer for Video Action Predictioncited by 6
  28. 2021AirObject: A Temporally Evolving Graph Embedding for Object Identificationcited by 5
  29. 2021Federated Action Recognition on Heterogeneous Embedded Devicescited by 4
  30. 2022ViGAT: Bottom-up event recognition and explanation in video using factorized graph attention networkcited by 4
  31. 2024Situational Scene Graph for Structured Human-centric Situation Understandingcited by 4
  32. 2021Joint Learning On The Hierarchy Representation for Fine-Grained Human Action Recognitioncited by 3
  33. 2022MAiVAR: Multimodal Audio-Image and Video Action Recognizercited by 3
  34. 2022Transformers in Action Recognition: A Review on Temporal Modelingcited by 3
  35. 2024Hierarchical Augmentation and Distillation for Class Incremental Audio-Visual Video Recognitioncited by 3
  36. 2026CliPPER: Contextual Video-Language Pretraining on Long-form Intraoperative Surgical Procedures for Event Recognitioncited by 3
  37. 2021Event and Activity Recognition in Video Surveillance for Cyber-Physical Systemscited by 2
  38. 2022Robotic Detection of a Human-Comprehensible Gestural Language for Underwater Multi-Human-Robot Collaborationcited by 2

50 most cited of 73 All 73 (JSON)