mlsanityData to 14 Oct 2026

Long-Term Feature Banks for Detailed Video Understanding

arXiv 1812.05038 ↗First posted 12 Dec 2018cs.CVcited by 239

Not on the map. Why?

Abstract (arXiv)

To understand the world, we humans constantly need to relate the present to the past, and put events in context. In this paper, we enable existing video models to do the same. We propose a long-term feature bank---supportive information extracted over the entire span of a video---to augment state-of-the-art video models that otherwise would only view short clips of 2-5 seconds. Our experiments demonstrate that augmenting 3D convolutional networks with a long-term feature bank yields state-of-the-art results on three challenging video datasets: AVA, EPIC-Kitchens, and Charades.

Key facts. Cited by 239 papers in the map (data through 14 Oct 2026). First posted on arXiv 12 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 69; 2022: 67; 2023: 46; 2024: 32; 2025: 18; 2026: 7.

239 papers.

Sort:

By area:

  1. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,620
  2. 2021ViViT: A Video Vision Transformercited by 1,620
  3. 2021Multiscale Vision Transformerscited by 897
  4. 2023MovieChat: From Dense Token to Sparse Memory for Long Video Understandingcited by 542
  5. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 519
  6. 2024Titans: Learning to Memorize at Test Timecited by 328
  7. 2021ActionCLIP: A New Paradigm for Video Action Recognitioncited by 320
  8. 2021Video Transformer Networkcited by 272
  9. 2021H2O: Two Hands Manipulating Objects for First Person Interaction Recognitioncited by 254
  10. 2024MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understandingcited by 229
  11. 2021Keeping Your Eye on the Ball: Trajectory Attention in Video Transformerscited by 224
  12. 2021Anticipative Video Transformercited by 200
38 more
  1. 2022MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognitioncited by 189
  2. 2023A Simple LLM Framework for Long-Range Video Question-Answeringcited by 178
  3. 2022Revisiting the "Video" in Video-Language Understandingcited by 169
  4. 2024Streaming Long Video Understanding with Large Language Modelscited by 167
  5. 2022Multiview Transformers for Video Recognitioncited by 148
  6. 2024LongVLM: Efficient Long Video Understanding via Large Language Modelscited by 147
  7. 2021Towards Long-Form Video Understandingcited by 146
  8. 2021Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Timecited by 141
  9. 2021TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?cited by 127
  10. 2025Streaming Video Question-Answering with In-context Video KV-Cache Retrievalcited by 117
  11. 2022MeMOT: Multi-Object Tracking with Memorycited by 114
  12. 2024HourVideo: 1-Hour Video-Language Understandingcited by 113
  13. 2021Temporal Context Aggregation Network for Temporal Action Proposal Refinementcited by 112
  14. 2021VidTr: Video Transformer Without Convolutionscited by 112
  15. 2022Global Tracking Transformerscited by 110
  16. 2024Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understandingcited by 108
  17. 2021Context-aware Biaffine Localizing Network for Temporal Sentence Groundingcited by 107
  18. 2021Long Short-Term Transformer for Online Action Detectioncited by 88
  19. 2021MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actionscited by 84
  20. 2024Streaming Dense Video Captioningcited by 82
  21. 2022TALLFormer: Temporal Action Localization with a Long-memory Transformercited by 79
  22. 2023Verbs in Action: Improving verb understanding in video-language modelscited by 76
  23. 2021Object-Region Video Transformerscited by 73
  24. 2024MovieChat+: Question-aware Sparse Memory for Long Video Question Answeringcited by 73
  25. 2021Temporal Query Networks for Fine-grained Video Understandingcited by 68
  26. 2021Temporal Memory Relation Network for Workflow Recognition from Surgical Videocited by 66
  27. 2023HierVL: Learning Hierarchical Video-Language Embeddingscited by 66
  28. 2022Video Transformers: A Surveycited by 63
  29. 2021Visual Semantic Role Labeling for Video Understandingcited by 60
  30. 2022Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learningcited by 59
  31. 2022A CLIP-Hitchhiker's Guide to Long Video Retrievalcited by 57
  32. 2021TubeR: Tubelet Transformer for Video Action Detectioncited by 55
  33. 2024Language Repository for Long Video Understandingcited by 55
  34. 2021ROAD: The ROad event Awareness Dataset for Autonomous Drivingcited by 54
  35. 2021Mining Contextual Information Beyond Image for Semantic Segmentationcited by 48
  36. 2022Retrieval-Enhanced Machine Learningcited by 47
  37. 2022Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detectioncited by 47
  38. 2024Memory Consolidation Enables Long-Context Video Understandingcited by 45

50 most cited of 239 All 239 (JSON)