# VidTr: Video Transformer Without Convolutions

arXiv: https://arxiv.org/abs/2104.11746 · HTML: https://mlsanity.com/paper/2104.11746/

## Key facts

- Cited by 112 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 65 references that are in the map.
- First posted on arXiv 23 Apr 2021.

## Builds on (most cited first, 30 of 49)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (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)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (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)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?](https://mlsanity.com/paper/1711.09577/) (2017)
- [Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding](https://mlsanity.com/paper/1604.01753/) (2016)
- [Multi-modal Transformer for Video Retrieval](https://mlsanity.com/paper/2007.10639/) (2020)
- [Temporal Relational Reasoning in Videos](https://mlsanity.com/paper/1711.08496/) (2017)
- [Video Action Transformer Network](https://mlsanity.com/paper/1812.02707/) (2018)
- [A Short Note on the Kinetics-700 Human Action Dataset](https://mlsanity.com/paper/1907.06987/) (2019)
- [Video Classification with Channel-Separated Convolutional Networks](https://mlsanity.com/paper/1904.02811/) (2019)

## Built on by (most cited first, 30 of 112)

- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [AdaViT: Adaptive Vision Transformers for Efficient Image Recognition](https://mlsanity.com/paper/2111.15668/) (2021)
- [Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers](https://mlsanity.com/paper/2106.05392/) (2021)
- [UniFormer: Unifying Convolution and Self-attention for Visual Recognition](https://mlsanity.com/paper/2201.09450/) (2022)
- [Video Understanding with Large Language Models: A Survey](https://mlsanity.com/paper/2312.17432/) (2023)
- [Anticipative Video Transformer](https://mlsanity.com/paper/2106.02036/) (2021)
- [UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning](https://mlsanity.com/paper/2201.04676/) (2022)
- [Earthformer: Exploring Space-Time Transformers for Earth System Forecasting](https://mlsanity.com/paper/2207.05833/) (2022)
- [Multiview Transformers for Video Recognition](https://mlsanity.com/paper/2201.04288/) (2022)
- [AIM: Adapting Image Models for Efficient Video Action Recognition](https://mlsanity.com/paper/2302.03024/) (2023)
- [Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks](https://mlsanity.com/paper/2112.01522/) (2021)
- [UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer](https://mlsanity.com/paper/2211.09552/) (2022)
- [TALL: Thumbnail Layout for Deepfake Video Detection](https://mlsanity.com/paper/2307.07494/) (2023)
- [TubeDETR: Spatio-Temporal Video Grounding with Transformers](https://mlsanity.com/paper/2203.16434/) (2022)
- [Long Short-Term Transformer for Online Action Detection](https://mlsanity.com/paper/2107.03377/) (2021)
- [Video Transformers: A Survey](https://mlsanity.com/paper/2201.05991/) (2022)
- [Future Transformer for Long-term Action Anticipation](https://mlsanity.com/paper/2205.14022/) (2022)
- [Temporally Efficient Vision Transformer for Video Instance Segmentation](https://mlsanity.com/paper/2204.08412/) (2022)
- [Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?](https://mlsanity.com/paper/2203.08392/) (2022)
- [Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning](https://mlsanity.com/paper/2212.03229/) (2022)
- [InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges](https://mlsanity.com/paper/2211.09529/) (2022)
- [Video Contrastive Learning with Global Context](https://mlsanity.com/paper/2108.02722/) (2021)
- [Co-training Transformer with Videos and Images Improves Action Recognition](https://mlsanity.com/paper/2112.07175/) (2021)
- [Delving into Sequential Patches for Deepfake Detection](https://mlsanity.com/paper/2207.02803/) (2022)
- [Dual-path Adaptation from Image to Video Transformers](https://mlsanity.com/paper/2303.09857/) (2023)
- [SODFormer: Streaming Object Detection with Transformer Using Events and Frames](https://mlsanity.com/paper/2308.04047/) (2023)
- [Memory-and-Anticipation Transformer for Online Action Understanding](https://mlsanity.com/paper/2308.07893/) (2023)
- [How Much Temporal Long-Term Context is Needed for Action Segmentation?](https://mlsanity.com/paper/2308.11358/) (2023)
- [DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition](https://mlsanity.com/paper/2203.10233/) (2022)
- [Motion-Guided Masking for Spatiotemporal Representation Learning](https://mlsanity.com/paper/2308.12962/) (2023)

## Abstract (arXiv)

We introduce Video Transformer (VidTr) with separable-attention for video classification. Comparing with commonly used 3D networks, VidTr is able to aggregate spatio-temporal information via stacked attentions and provide better performance with higher efficiency. We first introduce the vanilla video transformer and show that transformer module is able to perform spatio-temporal modeling from raw pixels, but with heavy memory usage. We then present VidTr which reduces the memory cost by 3.3× while keeping the same performance. To further optimize the model, we propose the standard deviation based topK pooling for attention (pooltopKstd), which reduces the computation by dropping non-informative features along temporal dimension. VidTr achieves state-of-the-art performance on five commonly used datasets with lower computational requirement, showing both the efficiency and effectiveness of our design. Finally, error analysis and visualization show that VidTr is especially good at predicting actions that require long-term temporal reasoning.