mlsanityData to 7 Oct 2026

Revisiting 3D ResNets for Video Recognition

arXiv 2109.01696 ↗First posted 3 Sep 2021cs.CV cs.LG eess.IVcited by 10

Not on the map. Why?

Abstract (arXiv)

A recent work from Bello shows that training and scaling strategies may be more significant than model architectures for visual recognition. This short note studies effective training and scaling strategies for video recognition models. We propose a simple scaling strategy for 3D ResNets, in combination with improved training strategies and minor architectural changes. The resulting models, termed 3D ResNet-RS, attain competitive performance of 81.0 on Kinetics-400 and 83.8 on Kinetics-600 without pre-training. When pre-trained on a large Web Video Text dataset, our best model achieves 83.5 and 84.3 on Kinetics-400 and Kinetics-600. The proposed scaling rule is further evaluated in a self-supervised setup using contrastive learning, demonstrating improved performance. Code is available at: https://github.com/tensorflow/models/tree/master/official.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 31 of its 37 references that are in the map. First posted on arXiv 3 Sep 2021.

Builds on

31 of 37 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2017Squeeze-and-Excitation Networkscited by 4,763
  5. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  6. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  7. 2017The Kinetics Human Action Video Datasetcited by 1,894
  8. 2018SlowFast Networks for Video Recognitioncited by 1,862
  9. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  10. 2021ViViT: A Video Vision Transformercited by 1,610
  11. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,609
  12. 2017Random Erasing Data Augmentationcited by 1,235
19 more
  1. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,139
  2. 2016Deep Networks with Stochastic Depthcited by 973
  3. 2021Multiscale Vision Transformerscited by 896
  4. 2019Big Transfer (BiT): General Visual Representation Learningcited by 766
  5. 2020X3D: Expanding Architectures for Efficient Video Recognitioncited by 635
  6. 2017In-Datacenter Performance Analysis of a Tensor Processing Unitcited by 610
  7. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  8. 2017Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classificationcited by 521
  9. 2018Bag of Tricks for Image Classification with Convolutional Neural Networkscited by 430
  10. 2020Spatiotemporal Contrastive Video Representation Learningcited by 372
  11. 2019Attention Augmented Convolutional Networkscited by 363
  12. 2018A Short Note about Kinetics-600cited by 331
  13. 2019Video Classification with Channel-Separated Convolutional Networkscited by 290
  14. 2021Video Transformer Networkcited by 271
  15. 2018DropBlock: A regularization method for convolutional networkscited by 261
  16. 2021Revisiting ResNets: Improved Training and Scaling Strategiescited by 158
  17. 2021LambdaNetworks: Modeling Long-Range Interactions Without Attentioncited by 107
  18. 2020Learning Video Representations from Textual Web Supervisioncited by 39
  19. 2021Simple Training Strategies and Model Scaling for Object Detectioncited by 25

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 1; 2024: 1; 2025: 3; 2026: 2.

10 papers.

  1. 2022Multiview Transformers for Video Recognitioncited by 148
  2. 2022Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learningcited by 49
  3. 2023Revisiting pre-trained remote sensing model benchmarks: resizing and normalization matterscited by 27
  4. 2024A Change Detection Reality Checkcited by 13
  5. 2022Automatic Diagnosis of Myocarditis Disease in Cardiac MRI Modality using Deep Transformers and Explainable Artificial Intelligencecited by 2
  6. 2025Few-Shot Learning in Video and 3D Object Detection: A Surveycited by 2
  7. 2026ColoDiff: Integrating Dynamic Consistency With Content Awareness for Colonoscopy Video Generationcited by 2
  8. 2025BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inferencecited by 1
  9. 2025Segment-and-Classify: ROI-Guided Generalizable Contrast Phase Classification in CT Using XGBoostcited by 0
  10. 2026Compressed Video Aggregator: Content-driven Module for Efficient Micro-Video Recommendationcited by 0