# Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning

arXiv: https://arxiv.org/abs/2212.03229 · HTML: https://mlsanity.com/paper/2212.03229/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- Builds on 68 of its 76 references that are in the map.
- First posted on arXiv 6 Dec 2022.

## Builds on (most cited first, 30 of 68)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](https://mlsanity.com/paper/1707.02968/) (2017)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [Segmenter: Transformer for Semantic Segmentation](https://mlsanity.com/paper/2105.05633/) (2021)
- [Florence: A New Foundation Model for Computer Vision](https://mlsanity.com/paper/2111.11432/) (2021)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (2021)

## Built on by (most cited first, 30 of 49)

- [Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution](https://mlsanity.com/paper/2307.06304/) (2023)
- [Tarsier: Recipes for Training and Evaluating Large Video Description Models](https://mlsanity.com/paper/2407.00634/) (2024)
- [Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers](https://mlsanity.com/paper/2401.11605/) (2024)
- [Memory Consolidation Enables Long-Context Video Understanding](https://mlsanity.com/paper/2402.05861/) (2024)
- [OmniVec: Learning robust representations with cross modal sharing](https://mlsanity.com/paper/2311.05709/) (2023)
- [A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames](https://mlsanity.com/paper/2312.07395/) (2023)
- [MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks](https://mlsanity.com/paper/2303.16839/) (2023)
- [Human-centric Scene Understanding for 3D Large-scale Scenarios](https://mlsanity.com/paper/2307.14392/) (2023)
- [ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation](https://mlsanity.com/paper/2412.09754/) (2024)
- [Adapting Short-Term Transformers for Action Detection in Untrimmed Videos](https://mlsanity.com/paper/2312.01897/) (2023)
- [Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities](https://mlsanity.com/paper/2311.05698/) (2023)
- [EgoSim: An Egocentric Multi-view Simulator and Real Dataset for Body-worn Cameras during Motion and Activity](https://mlsanity.com/paper/2502.18373/) (2025)
- [ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders](https://mlsanity.com/paper/2303.12001/) (2023)
- [VideoGLUE: Video General Understanding Evaluation of Foundation Models](https://mlsanity.com/paper/2307.03166/) (2023)
- [Towards a vision foundation model for comprehensive assessment of Cardiac MRI](https://mlsanity.com/paper/2410.01665/) (2024)
- [OmniVec2 -- A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning](https://mlsanity.com/paper/2507.13364/) (2025)
- [Flow Dynamics Correction for Action Recognition](https://mlsanity.com/paper/2310.10059/) (2023)
- [Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training](https://mlsanity.com/paper/2312.02914/) (2023)
- [COSA: Concatenated Sample Pretrained Vision-Language Foundation Model](https://mlsanity.com/paper/2306.09085/) (2023)
- [Learning from One Continuous Video Stream](https://mlsanity.com/paper/2312.00598/) (2023)
- [Computer Vision for Primate Behavior Analysis in the Wild](https://mlsanity.com/paper/2401.16424/) (2024)
- [Snakes and Ladders: Two Steps Up for VideoMamba](https://mlsanity.com/paper/2406.19006/) (2024)
- [C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognition](https://mlsanity.com/paper/2407.06113/) (2024)
- [Cross-Modal Learning for Anomaly Detection in Complex Industrial Process: Methodology and Benchmark](https://mlsanity.com/paper/2406.09016/) (2024)
- [Enhancing Video Transformers for Action Understanding with VLM-aided Training](https://mlsanity.com/paper/2403.16128/) (2024)
- [Skeleton-based Group Activity Recognition via Spatial-Temporal Panoramic Graph](https://mlsanity.com/paper/2407.19497/) (2024)
- [TRecViT: A Recurrent Video Transformer](https://mlsanity.com/paper/2412.14294/) (2024)
- [D'ej`a Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse](https://mlsanity.com/paper/2506.14107/) (2025)
- [Optimizing ViViT Training: Time and Memory Reduction for Action Recognition](https://mlsanity.com/paper/2306.04822/) (2023)
- [A Survey of IMU Based Cross-Modal Transfer Learning in Human Activity Recognition](https://mlsanity.com/paper/2403.15444/) (2024)

## Abstract (arXiv)

We present a simple approach which can turn a ViT encoder into an efficient video model, which can seamlessly work with both image and video inputs. By sparsely sampling the inputs, the model is able to do training and inference from both inputs. The model is easily scalable and can be adapted to large-scale pre-trained ViTs without requiring full finetuning. The model achieves SOTA results and the code will be open-sourced.