# It Takes Two: Masked Appearance-Motion Modeling for Self-supervised Video Transformer Pre-training

arXiv: https://arxiv.org/abs/2210.05234 · HTML: https://mlsanity.com/paper/2210.05234/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 60 of its 70 references that are in the map.
- First posted on arXiv 11 Oct 2022.

## Builds on (most cited first, 30 of 60)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [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)
- [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)
- [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)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (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)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding](https://mlsanity.com/paper/2109.14084/) (2021)

## Built on by (most cited first, 10 of 10)

- [MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition](https://mlsanity.com/paper/2307.02227/) (2023)
- [Masked Motion Predictors are Strong 3D Action Representation Learners](https://mlsanity.com/paper/2308.07092/) (2023)
- [Motion-Guided Masking for Spatiotemporal Representation Learning](https://mlsanity.com/paper/2308.12962/) (2023)
- [Masked Modeling for Self-supervised Representation Learning on Vision and Beyond](https://mlsanity.com/paper/2401.00897/) (2023)
- [SMC++: Masked Learning of Unsupervised Video Semantic Compression](https://mlsanity.com/paper/2406.04765/) (2024)
- [SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing](https://mlsanity.com/paper/2603.19228/) (2026)
- [TESPEC: Temporally-Enhanced Self-Supervised Pretraining for Event Cameras](https://mlsanity.com/paper/2508.00913/) (2025)
- [Aerial Image Object Detection With Vision Transformer Detector (ViTDet)](https://mlsanity.com/paper/2301.12058/) (2023)
- [Remote Sensing Scene Classification with Masked Image Modeling (MIM)](https://mlsanity.com/paper/2302.14256/) (2023)
- [Foundational Models for Pathology and Endoscopy Images: Application for Gastric Inflammation](https://mlsanity.com/paper/2406.18249/) (2024)

## Abstract (arXiv)

Self-supervised video transformer pre-training has recently benefited from the mask-and-predict pipeline. They have demonstrated outstanding effectiveness on downstream video tasks and superior data efficiency on small datasets. However, temporal relation is not fully exploited by these methods. In this work, we explicitly investigate motion cues in videos as extra prediction target and propose our Masked Appearance-Motion Modeling (MAM2) framework. Specifically, we design an encoder-regressor-decoder pipeline for this task. The regressor separates feature encoding and pretext tasks completion, such that the feature extraction process is completed adequately by the encoder. In order to guide the encoder to fully excavate spatial-temporal features, two separate decoders are used for two pretext tasks of disentangled appearance and motion prediction. We explore various motion prediction targets and figure out RGB-difference is simple yet effective. As for appearance prediction, VQGAN codes are leveraged as prediction target. With our pre-training pipeline, convergence can be remarkably speed up, e.g., we only require half of epochs than state-of-the-art VideoMAE (400 v.s. 800) to achieve the competitive performance. Extensive experimental results prove that our method learns generalized video representations. Notably, our MAM2 with ViT-B achieves 82.3% on Kinects-400, 71.3% on Something-Something V2, 91.5% on UCF101, and 62.5% on HMDB51.