mlsanityData to 14 Oct 2026

SlowFast Networks for Video Recognition

arXiv 1812.03982 ↗First posted 10 Dec 2018cs.CVcited by 1,867

Not on the map. Why?

Cited by 71 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present SlowFast networks for video recognition. Our model involves (i) a Slow pathway, operating at low frame rate, to capture spatial semantics, and (ii) a Fast pathway, operating at high frame rate, to capture motion at fine temporal resolution. The Fast pathway can be made very lightweight by reducing its channel capacity, yet can learn useful temporal information for video recognition. Our models achieve strong performance for both action classification and detection in video, and large improvements are pin-pointed as contributions by our SlowFast concept. We report state-of-the-art accuracy on major video recognition benchmarks, Kinetics, Charades and AVA. Code has been made available at: https://github.com/facebookresearch/SlowFast

Key facts. Cited by 1,867 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 294; 2022: 358; 2023: 375; 2024: 345; 2025: 305; 2026: 190.

1,867 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. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,556
  4. 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,322
  5. 2021Video Swin Transformercited by 1,091
  6. 2021Multiscale Vision Transformerscited by 897
  7. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  8. 2021CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrievalcited by 651
  9. 2021CLIPort: What and Where Pathways for Robotic Manipulationcited by 622
  10. 2021VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understandingcited by 602
  11. 2024LLaVA-Video: Video Instruction Tuning With Synthetic Datacited by 583
  12. 2021Masked Feature Prediction for Self-Supervised Visual Pre-Trainingcited by 576
38 more
  1. 2023VideoMAE V2: Scaling Video Masked Autoencoders with Dual Maskingcited by 528
  2. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 519
  3. 2021Less is More: ClipBERT for Video-and-Language Learning via Sparse Samplingcited by 484
  4. 2022InternVideo: General Video Foundation Models via Generative and Discriminative Learningcited by 447
  5. 2021VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Textcited by 429
  6. 2022Masked Autoencoders As Spatiotemporal Learnerscited by 429
  7. 2021Attention Bottlenecks for Multimodal Fusioncited by 361
  8. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 350
  9. 2024VideoMamba: State Space Model for Efficient Video Understandingcited by 328
  10. 2022Expanding Language-Image Pretrained Models for General Video Recognitioncited by 321
  11. 2021ActionCLIP: A New Paradigm for Video Action Recognitioncited by 320
  12. 2024InternVideo2: Scaling Foundation Models for Multimodal Video Understandingcited by 317
  13. 2022ActionFormer: Localizing Moments of Actions with Transformerscited by 311
  14. 2021Prompting Visual-Language Models for Efficient Video Understandingcited by 310
  15. 2023LMDrive: Closed-Loop End-to-End Driving with Large Language Modelscited by 305
  16. 2023Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistlescited by 290
  17. 2022Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activitiescited by 287
  18. 2021Video Transformer Networkcited by 272
  19. 2022Balanced Multimodal Learning via On-the-fly Gradient Modulationcited by 264
  20. 2021Revisiting Skeleton-based Action Recognitioncited by 257
  21. 2021H2O: Two Hands Manipulating Objects for First Person Interaction Recognitioncited by 254
  22. 2022Egocentric Video-Language Pretrainingcited by 232
  23. 2024MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understandingcited by 229
  24. 2021Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptionscited by 226
  25. 2021CLIP2Video: Mastering Video-Text Retrieval via Image CLIPcited by 225
  26. 2021Keeping Your Eye on the Ball: Trajectory Attention in Video Transformerscited by 224
  27. 2022Omnivore: A Single Model for Many Visual Modalitiescited by 215
  28. 2021A Large-Scale Study on Unsupervised Spatiotemporal Representation Learningcited by 214
  29. 2022UniFormer: Unifying Convolution and Self-attention for Visual Recognitioncited by 206
  30. 2023Video Understanding with Large Language Models: A Surveycited by 206
  31. 2021Anticipative Video Transformercited by 200
  32. 2023Unmasked Teacher: Towards Training-Efficient Video Foundation Modelscited by 199
  33. 2022ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learningcited by 193
  34. 2023UniVTG: Towards Unified Video-Language Temporal Groundingcited by 190
  35. 2022MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognitioncited by 189
  36. 2021VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modelingcited by 188
  37. 2022UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learningcited by 184
  38. 2021Adaptive Token Sampling For Efficient Vision Transformerscited by 183

50 most cited of 1,867 All 1,867 (JSON)