mlsanityData to 14 Oct 2026

PyTorchVideo: A Deep Learning Library for Video Understanding

arXiv 2111.09887 ↗First posted 18 Nov 2021cs.CV cs.LGcited by 32

Not on the map. Why?

Abstract (arXiv)

We introduce PyTorchVideo, an open-source deep-learning library that provides a rich set of modular, efficient, and reproducible components for a variety of video understanding tasks, including classification, detection, self-supervised learning, and low-level processing. The library covers a full stack of video understanding tools including multimodal data loading, transformations, and models that reproduce state-of-the-art performance. PyTorchVideo further supports hardware acceleration that enables real-time inference on mobile devices. The library is based on PyTorch and can be used by any training framework; for example, PyTorchLightning, PySlowFast, or Classy Vision. PyTorchVideo is available at https://pytorchvideo.org/

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). Builds on 20 of its 27 references that are in the map. First posted on arXiv 18 Nov 2021.

Builds on

20 of 27 references.

References · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  4. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  5. 2017Non-local Neural Networkscited by 2,293
  6. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  7. 2018SlowFast Networks for Video Recognitioncited by 1,867
  8. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,143
  9. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,103
  10. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 901
  11. 2021Multiscale Vision Transformerscited by 897
  12. 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 795
8 more
  1. 2020X3D: Expanding Architectures for Efficient Video Recognitioncited by 637
  2. 2016Hollywood in Homes: Crowdsourcing Data Collection for Activity Understandingcited by 537
  3. 2017AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actionscited by 449
  4. 2019Video Classification with Channel-Separated Convolutional Networkscited by 290
  5. 2021A Large-Scale Study on Unsupervised Spatiotemporal Representation Learningcited by 214
  6. 2020Audiovisual SlowFast Networks for Video Recognitioncited by 146
  7. 2019GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processingcited by 32
  8. 2018A Weighted Sparse Sampling and Smoothing Frame Transition Approach for Semantic Fast-Forward First-Person Videoscited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 10; 2023: 5; 2024: 6; 2025: 7; 2026: 2.

32 papers.

Sort:

By area:

  1. 2021Masked Feature Prediction for Self-Supervised Visual Pre-Trainingcited by 576
  2. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 519
  3. 2022Spotting Temporally Precise, Fine-Grained Events in Videocited by 40
  4. 2022AugLy: Data Augmentations for Robustnesscited by 34
  5. 2022WOODS: Benchmarks for Out-of-Distribution Generalization in Time Seriescited by 30
  6. 2022Words are all you need? Language as an approximation for human similarity judgmentscited by 18
  7. 2022CVNets: High Performance Library for Computer Visioncited by 16
  8. 2023Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic Scenescited by 12
  9. 2023Differentially Private Video Activity Recognitioncited by 9
  10. 2024Neuro-Symbolic Evaluation of Text-to-Video Models using Formal Verificationcited by 9
  11. 2022A Multimodal German Dataset for Automatic Lip Reading Systems and Transfer Learningcited by 8
  12. 2022Know your sensORs -- A Modality Study For Surgical Action Classificationcited by 6
20 more
  1. 2023VR.net: A Real-world Dataset for Virtual Reality Motion Sickness Researchcited by 6
  2. 2022Impact of annotation modality on label quality and model performance in the automatic assessment of laughter in-the-wildcited by 4
  3. 2024Video RWKV:Video Action Recognition Based RWKVcited by 4
  4. 2025Long-VMNet: Accelerating Long-Form Video Understanding via Fixed Memorycited by 4
  5. 2025MegaScale-Data: Scaling Dataloader for Multisource Large Foundation Model Trainingcited by 4
  6. 2022Model-agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognitioncited by 3
  7. 2022Performance Evaluation of Action Recognition Models on Low Quality Videoscited by 3
  8. 2023VOCALExplore: Pay-as-You-Go Video Data Exploration and Model Building [Technical Report]cited by 2
  9. 2023Deep Video Codec Control for Vision Modelscited by 2
  10. 2025Synthetic Human Action Video Data Generation with Pose Transfercited by 2
  11. 2024Signal Processing in the Retina: Interpretable Graph Classifier to Predict Ganglion Cell Responsescited by 1
  12. 2024REWIND Dataset: Privacy-preserving Speaking Status Segmentation from Multimodal Body Movement Signals in the Wildcited by 1
  13. 2025Transfer Learning from Visual Speech Recognition to Mouthing Recognition in German Sign Languagecited by 1
  14. 2025The Importance of Facial Features in Vision-based Sign Language Recognition: Eyes, Mouth or Full Face?cited by 1
  15. 2024Video-based Exercise Classification and Activated Muscle Group Prediction with Hybrid X3D-SlowFast Networkcited by 0
  16. 2024Towards Clinical Practice in CT-Based Pulmonary Disease Screening: An Efficient and Reliable Frameworkcited by 0
  17. 2025Domain Generalization for Improved Human Activity Recognition in Office Space Videos Using Adaptive Pre-processingcited by 0
  18. 2025Spatiotemporal Analysis of Forest Machine Operations Using 3D Video Classificationcited by 0
  19. 2026Multimodal Visual Surrogate Compression for Alzheimer's Disease Classificationcited by 0
  20. 2026Action-Slot: Structured Action-Centric Representation Learning for Multi-Agent Atomic Activity Understandingcited by 0