# SVFormer: Semi-supervised Video Transformer for Action Recognition

arXiv: https://arxiv.org/abs/2211.13222 · HTML: https://mlsanity.com/paper/2211.13222/

## Key facts

- Cited by 68 papers in the map (data through 14 Oct 2026).
- Builds on 58 of its 73 references that are in the map.
- First posted on arXiv 23 Nov 2022.

## Builds on (most cited first, 30 of 58)

- [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)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [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)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (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)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision](https://mlsanity.com/paper/2106.01226/) (2021)
- [Masked Autoencoders As Spatiotemporal Learners](https://mlsanity.com/paper/2205.09113/) (2022)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)
- [Video Transformer Network](https://mlsanity.com/paper/2102.00719/) (2021)
- [ActBERT: Learning Global-Local Video-Text Representations](https://mlsanity.com/paper/2011.07231/) (2020)
- [Interpolation Consistency Training for Semi-Supervised Learning](https://mlsanity.com/paper/1903.03825/) (2019)
- [Adversarial Domain Adaptation with Domain Mixup](https://mlsanity.com/paper/1912.01805/) (2019)
- [A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning](https://mlsanity.com/paper/2104.14558/) (2021)
- [UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning](https://mlsanity.com/paper/2201.04676/) (2022)
- [Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition](https://mlsanity.com/paper/1708.07632/) (2017)

## Built on by (most cited first, 30 of 68)

- [A Survey on Video Diffusion Models](https://mlsanity.com/paper/2310.10647/) (2023)
- [SimDA: Simple Diffusion Adapter for Efficient Video Generation](https://mlsanity.com/paper/2308.09710/) (2023)
- [Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning](https://mlsanity.com/paper/2212.04500/) (2022)
- [CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection](https://mlsanity.com/paper/2212.05136/) (2022)
- [MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance](https://mlsanity.com/paper/2503.16421/) (2025)
- [MotionEditor: Editing Video Motion via Content-Aware Diffusion](https://mlsanity.com/paper/2311.18830/) (2023)
- [Prototypical Residual Networks for Anomaly Detection and Localization](https://mlsanity.com/paper/2212.02031/) (2022)
- [Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization](https://mlsanity.com/paper/2302.00624/) (2023)
- [Implicit Temporal Modeling with Learnable Alignment for Video Recognition](https://mlsanity.com/paper/2304.10465/) (2023)
- [vid-TLDR: Training Free Token merging for Light-weight Video Transformer](https://mlsanity.com/paper/2403.13347/) (2024)
- [Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives](https://mlsanity.com/paper/2406.05615/) (2024)
- [ResFormer: Scaling ViTs with Multi-Resolution Training](https://mlsanity.com/paper/2212.00776/) (2022)
- [ViTAR: Vision Transformer with Any Resolution](https://mlsanity.com/paper/2403.18361/) (2024)
- [Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey and Benchmark](https://mlsanity.com/paper/2402.02242/) (2024)
- [Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and Data](https://mlsanity.com/paper/2310.05010/) (2023)
- [AID: Adapting Image2Video Diffusion Models for Instruction-guided Video Prediction](https://mlsanity.com/paper/2406.06465/) (2024)
- [LabelBench: A Comprehensive Framework for Benchmarking Adaptive Label-Efficient Learning](https://mlsanity.com/paper/2306.09910/) (2023)
- [PanoSwin: a Pano-style Swin Transformer for Panorama Understanding](https://mlsanity.com/paper/2308.14726/) (2023)
- [VIDiff: Translating Videos via Multi-Modal Instructions with Diffusion Models](https://mlsanity.com/paper/2311.18837/) (2023)
- [XVO: Generalized Visual Odometry via Cross-Modal Self-Training](https://mlsanity.com/paper/2309.16772/) (2023)
- [Cross-view Action Recognition Understanding From Exocentric to Egocentric Perspective](https://mlsanity.com/paper/2305.15699/) (2023)
- [Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms](https://mlsanity.com/paper/2408.09764/) (2024)
- [VideoScan: Enabling Efficient Streaming Video Understanding via Frame-level Semantic Carriers](https://mlsanity.com/paper/2503.09387/) (2025)
- [Computer Vision for Primate Behavior Analysis in the Wild](https://mlsanity.com/paper/2401.16424/) (2024)
- [Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignment](https://mlsanity.com/paper/2402.04599/) (2024)
- [Temporal Regularization Makes Your Video Generator Stronger](https://mlsanity.com/paper/2503.15417/) (2025)
- [Roll With the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learning](https://mlsanity.com/paper/2312.12237/) (2023)
- [RadarLLM: Empowering Large Language Models to Understand Human Motion from Millimeter-Wave Point Cloud Sequence](https://mlsanity.com/paper/2504.09862/) (2025)
- [Cognition Transferring and Decoupling for Text-supervised Egocentric Semantic Segmentation](https://mlsanity.com/paper/2410.01341/) (2024)
- [Transfer Learning for Fine-grained Classification Using Semi-supervised Learning and Visual Transformers](https://mlsanity.com/paper/2305.10018/) (2023)

## Abstract (arXiv)

Semi-supervised action recognition is a challenging but critical task due to the high cost of video annotations. Existing approaches mainly use convolutional neural networks, yet current revolutionary vision transformer models have been less explored. In this paper, we investigate the use of transformer models under the SSL setting for action recognition. To this end, we introduce SVFormer, which adopts a steady pseudo-labeling framework (ie, EMA-Teacher) to cope with unlabeled video samples. While a wide range of data augmentations have been shown effective for semi-supervised image classification, they generally produce limited results for video recognition. We therefore introduce a novel augmentation strategy, Tube TokenMix, tailored for video data where video clips are mixed via a mask with consistent masked tokens over the temporal axis. In addition, we propose a temporal warping augmentation to cover the complex temporal variation in videos, which stretches selected frames to various temporal durations in the clip. Extensive experiments on three datasets Kinetics-400, UCF-101, and HMDB-51 verify the advantage of SVFormer. In particular, SVFormer outperforms the state-of-the-art by 31.5% with fewer training epochs under the 1% labeling rate of Kinetics-400. Our method can hopefully serve as a strong benchmark and encourage future search on semi-supervised action recognition with Transformer networks.