mlsanityData to 7 Oct 2026

SCENIC: A JAX Library for Computer Vision Research and Beyond

arXiv 2110.11403 ↗First posted 18 Oct 2021cs.CV cs.AI cs.CLcited by 56

Not on the map. Why?

Abstract (arXiv)

Scenic is an open-source JAX library with a focus on Transformer-based models for computer vision research and beyond. The goal of this toolkit is to facilitate rapid experimentation, prototyping, and research of new vision architectures and models. Scenic supports a diverse range of vision tasks (e.g., classification, segmentation, detection)and facilitates working on multi-modal problems, along with GPU/TPU support for multi-host, multi-device large-scale training. Scenic also offers optimized implementations of state-of-the-art research models spanning a wide range of modalities. Scenic has been successfully used for numerous projects and published papers and continues serving as the library of choice for quick prototyping and publication of new research ideas.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). Builds on 16 of its 31 references that are in the map. First posted on arXiv 18 Oct 2021.

Builds on

16 of 31 references.

References · 16

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  6. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  7. 2020End-to-End Object Detection with Transformerscited by 7,384
  8. 2021ViViT: A Video Vision Transformercited by 1,610
  9. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  10. 2021How to train your ViT? Data, Augmentation, and Regularization in Vision Transformerscited by 562
  11. 2021Attention Bottlenecks for Multimodal Fusioncited by 361
  12. 2021The Benchmark Lotterycited by 133
4 more
  1. 2021TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?cited by 127
  2. 2021Scale Efficiently: Insights from Pre-training and Fine-tuning Transformerscited by 105
  3. 2021Exploring the Limits of Large Scale Pre-trainingcited by 104
  4. 2021OmniNet: Omnidirectional Representations from Transformerscited by 23

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 11; 2023: 23; 2024: 13; 2025: 4; 2026: 1.

56 papers.

Sort:

By area:

  1. 2023Scaling Vision Transformers to 22 Billion Parameterscited by 690
  2. 2023Scaling Open-Vocabulary Object Detectioncited by 335
  3. 2022Simple Open-Vocabulary Object Detection with Vision Transformerscited by 303
  4. 2023Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioningcited by 263
  5. 2023Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolutioncited by 226
  6. 2022The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformerscited by 121
  7. 2021The Efficiency Misnomercited by 98
  8. 2024Streaming Dense Video Captioningcited by 82
  9. 2023MatFormer: Nested Transformer for Elastic Inferencecited by 79
  10. 2024MoReVQA: Exploring Modular Reasoning Models for Video Question Answeringcited by 74
  11. 2022Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizescited by 72
  12. 2024BRAVE: Broadening the visual encoding of vision-language modelscited by 68
38 more
  1. 2023UnLoc: A Unified Framework for Video Localization Taskscited by 66
  2. 2021PolyViT: Co-training Vision Transformers on Images, Videos and Audiocited by 58
  3. 2024Scaling Wearable Foundation Modelscited by 57
  4. 2023On the Role of Attention in Prompt-tuningcited by 49
  5. 2022Audiovisual Masked Autoencoderscited by 47
  6. 2022Large Scale Transfer Learning for Differentially Private Image Classificationcited by 40
  7. 2021Pyramid Adversarial Training Improves ViT Performancecited by 39
  8. 2023SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understandingcited by 38
  9. 2024Infinite Limits of Multi-head Transformer Dynamicscited by 38
  10. 2023Towards Universal Image Embeddings: A Large-Scale Dataset and Challenge for Generic Image Representationscited by 28
  11. 2024Time-, Memory- and Parameter-Efficient Visual Adaptationcited by 28
  12. 2021Learned Queries for Efficient Local Attentioncited by 27
  13. 2023On Efficient Training of Large-Scale Deep Learning Models: A Literature Reviewcited by 26
  14. 2022Token Turing Machinescited by 25
  15. 2024Mixture of Nested Experts: Adaptive Processing of Visual Tokenscited by 25
  16. 2023Text-Conditioned Resampler For Long Form Video Understandingcited by 24
  17. 2023Adaptive Computation with Elastic Input Sequencecited by 22
  18. 2023Self-Supervised Learning for Endoscopic Video Analysiscited by 22
  19. 2023How can objects help action recognition?cited by 21
  20. 2022Location-Aware Self-Supervised Transformers for Semantic Segmentationcited by 20
  21. 2022M&M Mix: A Multimodal Multiview Transformer Ensemblecited by 19
  22. 2022Learning Reward Functions for Robotic Manipulation by Observing Humanscited by 14
  23. 2023Unified Visual Relationship Detection with Vision and Language Modelscited by 13
  24. 2023JaxPruner: A concise library for sparsity researchcited by 13
  25. 2024Frozen Feature Augmentation for Few-Shot Image Classificationcited by 13
  26. 2024Dual-path Collaborative Generation Network for Emotional Video Captioningcited by 13
  27. 2023Dense Video Object Captioning from Disjoint Supervisioncited by 10
  28. 2023The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Computecited by 10
  29. 2023Dual PatchNormcited by 9
  30. 2024A Generative Approach for Wikipedia-Scale Visual Entity Recognitioncited by 9
  31. 2022Beyond Transfer Learning: Co-finetuning for Action Localisationcited by 8
  32. 2024UDON: Universal Dynamic Online distillatioN for generic image representationscited by 8
  33. 2024Stepping on the Edge: Curvature Aware Learning Rate Tunerscited by 8
  34. 2023Optimizing ViViT Training: Time and Memory Reduction for Action Recognitioncited by 4
  35. 2023Towards Understanding the Effect of Pretraining Label Granularitycited by 3
  36. 2024Extending Video Masked Autoencoders to 128 framescited by 3
  37. 2025VoCap: Video Object Captioning and Segmentation from Any Promptcited by 3
  38. 2022On the Surprising Effectiveness of Transformers in Low-Labeled Video Recognitioncited by 2

50 most cited of 56 All 56 (JSON)