mlsanityData to 7 Oct 2026

X3D: Expanding Architectures for Efficient Video Recognition

arXiv 2004.04730 ↗First posted 9 Apr 2020cs.CVcited by 635

Not on the map. Why?

Abstract (arXiv)

This paper presents X3D, a family of efficient video networks that progressively expand a tiny 2D image classification architecture along multiple network axes, in space, time, width and depth. Inspired by feature selection methods in machine learning, a simple stepwise network expansion approach is employed that expands a single axis in each step, such that good accuracy to complexity trade-off is achieved. To expand X3D to a specific target complexity, we perform progressive forward expansion followed by backward contraction. X3D achieves state-of-the-art performance while requiring 4.8x and 5.5x fewer multiply-adds and parameters for similar accuracy as previous work. Our most surprising finding is that networks with high spatiotemporal resolution can perform well, while being extremely light in terms of network width and parameters. We report competitive accuracy at unprecedented efficiency on video classification and detection benchmarks. Code will be available at: https://github.com/facebookresearch/SlowFast

Key facts. Cited by 635 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 107; 2022: 149; 2023: 133; 2024: 106; 2025: 87; 2026: 53.

635 papers.

Sort:

By area:

  1. 2021ViViT: A Video Vision Transformercited by 1,610
  2. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,609
  3. 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,305
  4. 2021Video Swin Transformercited by 1,090
  5. 2021Multiscale Vision Transformerscited by 896
  6. 2021Masked Feature Prediction for Self-Supervised Visual Pre-Trainingcited by 573
  7. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 516
  8. 2021Less is More: ClipBERT for Video-and-Language Learning via Sparse Samplingcited by 484
  9. 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 477
  10. 2022Masked Autoencoders As Spatiotemporal Learnerscited by 428
  11. 2021VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Textcited by 427
  12. 2024VideoMamba: State Space Model for Efficient Video Understandingcited by 325
38 more
  1. 2021ActionCLIP: A New Paradigm for Video Action Recognitioncited by 317
  2. 2025Perception Encoder: The best visual embeddings are not at the output of the networkcited by 315
  3. 2021Prompting Visual-Language Models for Efficient Video Understandingcited by 309
  4. 2021Video Transformer Networkcited by 271
  5. 2021Revisiting Skeleton-based Action Recognitioncited by 256
  6. 2021H2O: Two Hands Manipulating Objects for First Person Interaction Recognitioncited by 251
  7. 2022TinyViT: Fast Pretraining Distillation for Small Vision Transformerscited by 232
  8. 2021Keeping Your Eye on the Ball: Trajectory Attention in Video Transformerscited by 224
  9. 2022UniFormer: Unifying Convolution and Self-attention for Visual Recognitioncited by 206
  10. 2023Video Understanding with Large Language Models: A Surveycited by 203
  11. 2022ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learningcited by 192
  12. 2022MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognitioncited by 189
  13. 2022UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learningcited by 182
  14. 2021Adaptive Token Sampling For Efficient Vision Transformerscited by 181
  15. 2022Frozen CLIP Models are Efficient Video Learnerscited by 181
  16. 2021BEVT: BERT Pretraining of Video Transformerscited by 169
  17. 2022Revisiting the "Video" in Video-Language Understandingcited by 167
  18. 2021Revisiting ResNets: Improved Training and Scaling Strategiescited by 158
  19. 2022Multiview Transformers for Video Recognitioncited by 148
  20. 2021Towards Long-Form Video Understandingcited by 146
  21. 2021MoViNets: Mobile Video Networks for Efficient Video Recognitioncited by 135
  22. 2021TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?cited by 127
  23. 2021ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysiscited by 124
  24. 2022UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormercited by 116
  25. 2022HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modelingcited by 115
  26. 2021VidTr: Video Transformer Without Convolutionscited by 112
  27. 2024Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyondcited by 111
  28. 2022Long Movie Clip Classification with State-Space Video Modelscited by 106
  29. 2024Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understandingcited by 106
  30. 2022Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understandingcited by 102
  31. 2022Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learningcited by 90
  32. 2023Vita-CLIP: Video and text adaptive CLIP via Multimodal Promptingcited by 90
  33. 2021An Image is Worth 16x16 Words, What is a Video Worth?cited by 87
  34. 2022VindLU: A Recipe for Effective Video-and-Language Pretrainingcited by 87
  35. 2021Space-time Mixing Attention for Video Transformercited by 84
  36. 2022PYSKL: Towards Good Practices for Skeleton Action Recognitioncited by 83
  37. 2021MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matchingcited by 82
  38. 2022A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translationcited by 80

50 most cited of 635 All 635 (JSON)