# MAViL: Masked Audio-Video Learners

arXiv: https://arxiv.org/abs/2212.08071 · HTML: https://mlsanity.com/paper/2212.08071/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- Builds on 83 of its 108 references that are in the map.
- First posted on arXiv 15 Dec 2022.

## Builds on (most cited first, 30 of 83)

- [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)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [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)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [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)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language](https://mlsanity.com/paper/2202.03555/) (2022)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)

## Built on by (most cited first, 30 of 59)

- [CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders](https://mlsanity.com/paper/2311.00566/) (2023)
- [OmniSat: Self-Supervised Modality Fusion for Earth Observation](https://mlsanity.com/paper/2404.08351/) (2024)
- [Self-Supervised Multimodal Learning: A Survey](https://mlsanity.com/paper/2304.01008/) (2023)
- [Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matching](https://mlsanity.com/paper/2406.00320/) (2024)
- [Masked Autoencoders for Microscopy are Scalable Learners of Cellular Biology](https://mlsanity.com/paper/2404.10242/) (2024)
- [CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities](https://mlsanity.com/paper/2312.14556/) (2023)
- [OmniVec: Learning robust representations with cross modal sharing](https://mlsanity.com/paper/2311.05709/) (2023)
- [An Unbiased Look at Datasets for Visuo-Motor Pre-Training](https://mlsanity.com/paper/2310.09289/) (2023)
- [Foundation Models for Music: A Survey](https://mlsanity.com/paper/2408.14340/) (2024)
- [CED: Consistent ensemble distillation for audio tagging](https://mlsanity.com/paper/2308.11957/) (2023)
- [Masked Image Modeling: A Survey](https://mlsanity.com/paper/2408.06687/) (2024)
- [VicTR: Video-conditioned Text Representations for Activity Recognition](https://mlsanity.com/paper/2304.02560/) (2023)
- [Unveiling the Power of Audio-Visual Early Fusion Transformers with Dense Interactions through Masked Modeling](https://mlsanity.com/paper/2312.01017/) (2023)
- [From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation](https://mlsanity.com/paper/2409.19132/) (2024)
- [Listen to Look into the Future: Audio-Visual Egocentric Gaze Anticipation](https://mlsanity.com/paper/2305.03907/) (2023)
- [AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models](https://mlsanity.com/paper/2309.10787/) (2023)
- [Improved Baselines for Data-efficient Perceptual Augmentation of LLMs](https://mlsanity.com/paper/2403.13499/) (2024)
- [Seeing Sound, Hearing Sight: Uncovering Modality Bias and Conflict of AI models in Sound Localization](https://mlsanity.com/paper/2505.11217/) (2025)
- [CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment](https://mlsanity.com/paper/2505.01237/) (2025)
- [Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities](https://mlsanity.com/paper/2311.05698/) (2023)
- [Siamese Vision Transformers are Scalable Audio-visual Learners](https://mlsanity.com/paper/2403.19638/) (2024)
- [Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Large Models](https://mlsanity.com/paper/2407.11717/) (2024)
- [Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning](https://mlsanity.com/paper/2512.19687/) (2025)
- [Spiking Tucker Fusion Transformer for Audio-Visual Zero-Shot Learning](https://mlsanity.com/paper/2407.08130/) (2024)
- [Masked Autoencoders are Scalable Learners of Cellular Morphology](https://mlsanity.com/paper/2309.16064/) (2023)
- [Learning Spatial Features from Audio-Visual Correspondence in Egocentric Videos](https://mlsanity.com/paper/2307.04760/) (2023)
- [Exploring Missing Modality in Multimodal Egocentric Datasets](https://mlsanity.com/paper/2401.11470/) (2024)
- [Unsupervised Audio-Visual Segmentation with Modality Alignment](https://mlsanity.com/paper/2403.14203/) (2024)
- [AVCap: Leveraging Audio-Visual Features as Text Tokens for Captioning](https://mlsanity.com/paper/2407.07801/) (2024)
- [FLAP: Fast Language-Audio Pre-training](https://mlsanity.com/paper/2311.01615/) (2023)

## Abstract (arXiv)

We present Masked Audio-Video Learners (MAViL) to train audio-visual representations. Our approach learns with three complementary forms of self-supervision: (1) reconstruction of masked audio and video input data, (2) intra- and inter-modal contrastive learning with masking, and (3) self-training by reconstructing joint audio-video contextualized features learned from the first two objectives. Pre-training with MAViL not only enables the model to perform well in audio-visual classification and retrieval tasks but also improves representations of each modality in isolation, without using information from the other modality for fine-tuning or inference. Empirically, MAViL sets a new state-of-the-art on AudioSet (53.1 mAP) and VGGSound (67.1% accuracy). For the first time, a self-supervised audio-visual model outperforms ones that use external supervision on these benchmarks.