# Multimodal Variational Auto-encoder based Audio-Visual Segmentation

arXiv: https://arxiv.org/abs/2310.08303 · HTML: https://mlsanity.com/paper/2310.08303/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Builds on 63 of its 91 references that are in the map.
- First posted on arXiv 12 Oct 2023.

## Builds on (most cited first, 30 of 63)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [PVT v2: Improved Baselines with Pyramid Vision Transformer](https://mlsanity.com/paper/2106.13797/) (2021)
- [Learning Representations by Maximizing Mutual Information Across Views](https://mlsanity.com/paper/1906.00910/) (2019)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [Panoptic Feature Pyramid Networks](https://mlsanity.com/paper/1901.02446/) (2019)
- [Multimodal Transformer for Unaligned Multimodal Language Sequences](https://mlsanity.com/paper/1906.00295/) (2019)
- [Score-based Generative Modeling in Latent Space](https://mlsanity.com/paper/2106.05931/) (2021)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [On Variational Bounds of Mutual Information](https://mlsanity.com/paper/1905.06922/) (2019)
- [Look, Listen and Learn](https://mlsanity.com/paper/1705.08168/) (2017)
- [Importance Weighted Autoencoders](https://mlsanity.com/paper/1509.00519/) (2015)
- [Attention Bottlenecks for Multimodal Fusion](https://mlsanity.com/paper/2107.00135/) (2021)
- [Domain Separation Networks](https://mlsanity.com/paper/1608.06019/) (2016)
- [On Mutual Information Maximization for Representation Learning](https://mlsanity.com/paper/1907.13625/) (2019)
- [Objects that Sound](https://mlsanity.com/paper/1712.06651/) (2017)
- [SMIL: Multimodal Learning with Severely Missing Modality](https://mlsanity.com/paper/2103.05677/) (2021)
- [CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information](https://mlsanity.com/paper/2006.12013/) (2020)
- [Multimodal Generative Models for Scalable Weakly-Supervised Learning](https://mlsanity.com/paper/1802.05335/) (2018)
- [Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis](https://mlsanity.com/paper/2102.04830/) (2021)

## Built on by (most cited first, 30 of 38)

- [Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models](https://mlsanity.com/paper/2401.04658/) (2024)
- [Audio-Visual Segmentation via Unlabeled Frame Exploitation](https://mlsanity.com/paper/2403.11074/) (2024)
- [Cooperation Does Matter: Exploring Multi-Order Bilateral Relations for Audio-Visual Segmentation](https://mlsanity.com/paper/2312.06462/) (2023)
- [Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time](https://mlsanity.com/paper/2407.01851/) (2024)
- [Towards Open-Vocabulary Audio-Visual Event Localization](https://mlsanity.com/paper/2411.11278/) (2024)
- [Label-anticipated Event Disentanglement for Audio-Visual Video Parsing](https://mlsanity.com/paper/2407.08126/) (2024)
- [Unveiling the Power of Audio-Visual Early Fusion Transformers with Dense Interactions through Masked Modeling](https://mlsanity.com/paper/2312.01017/) (2023)
- [Stepping Stones: A Progressive Training Strategy for Audio-Visual Semantic Segmentation](https://mlsanity.com/paper/2407.11820/) (2024)
- [Multimodal Referring Segmentation: A Survey](https://mlsanity.com/paper/2508.00265/) (2025)
- [Audio-Visual Instance Segmentation](https://mlsanity.com/paper/2310.18709/) (2023)
- [Object-aware Adaptive-Positivity Learning for Audio-Visual Question Answering](https://mlsanity.com/paper/2312.12816/) (2023)
- [EchoTrack: Auditory Referring Multi-Object Tracking for Autonomous Driving](https://mlsanity.com/paper/2402.18302/) (2024)
- [AVS-Mamba: Exploring Temporal and Multi-modal Mamba for Audio-Visual Segmentation](https://mlsanity.com/paper/2501.07810/) (2025)
- [Detecting Misinformation in Multimedia Content through Cross-Modal Entity Consistency: A Dual Learning Approach](https://mlsanity.com/paper/2409.00022/) (2024)
- [CPM: Class-conditional Prompting Machine for Audio-visual Segmentation](https://mlsanity.com/paper/2407.05358/) (2024)
- [Dynamic Derivation and Elimination: Audio Visual Segmentation with Enhanced Audio Semantics](https://mlsanity.com/paper/2503.12840/) (2025)
- [Robust Audio-Visual Segmentation via Audio-Guided Visual Convergent Alignment](https://mlsanity.com/paper/2503.12847/) (2025)
- [AVESFormer: Efficient Transformer Design for Real-Time Audio-Visual Segmentation](https://mlsanity.com/paper/2408.01708/) (2024)
- [Revisiting Audio-Visual Segmentation with Vision-Centric Transformer](https://mlsanity.com/paper/2506.23623/) (2025)
- [Extending Segment Anything Model into Auditory and Temporal Dimensions for Audio-Visual Segmentation](https://mlsanity.com/paper/2406.06163/) (2024)
- [Implicit Counterfactual Learning for Audio-Visual Segmentation](https://mlsanity.com/paper/2507.20740/) (2025)
- [Complementary and Contrastive Learning for Audio-Visual Segmentation](https://mlsanity.com/paper/2510.10051/) (2025)
- [SAVE: Segment Audio-Visual Easy way using Segment Anything Model](https://mlsanity.com/paper/2407.02004/) (2024)
- [From Waveforms to Pixels: A Survey on Audio-Visual Segmentation](https://mlsanity.com/paper/2508.03724/) (2025)
- [Delayed Bidirectional Alignment via Disentangled Audio Semantics for Audio-Visual Segmentation](https://mlsanity.com/paper/2512.20117/) (2025)
- [UWAV: Uncertainty-weighted Weakly-supervised Audio-Visual Video Parsing](https://mlsanity.com/paper/2505.09615/) (2025)
- [AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting](https://mlsanity.com/paper/2506.01015/) (2025)
- [Audit After Segmentation: Reference-Free Mask Quality Assessment for Language-Referred Audio-Visual Segmentation](https://mlsanity.com/paper/2602.03892/) (2026)
- [Multi-View Oriented GPLVM: Expressiveness and Efficiency](https://mlsanity.com/paper/2502.08253/) (2025)
- [HAVT-IVD: Heterogeneity-Aware Cross-Modal Network for Audio-Visual Surveillance: Idling Vehicles Detection With Multichannel Audio and Multiscale Visual Cues](https://mlsanity.com/paper/2504.16102/) (2025)

## Abstract (arXiv)

We propose an Explicit Conditional Multimodal Variational Auto-Encoder (ECMVAE) for audio-visual segmentation (AVS), aiming to segment sound sources in the video sequence. Existing AVS methods focus on implicit feature fusion strategies, where models are trained to fit the discrete samples in the dataset. With a limited and less diverse dataset, the resulting performance is usually unsatisfactory. In contrast, we address this problem from an effective representation learning perspective, aiming to model the contribution of each modality explicitly. Specifically, we find that audio contains critical category information of the sound producers, and visual data provides candidate sound producer(s). Their shared information corresponds to the target sound producer(s) shown in the visual data. In this case, cross-modal shared representation learning is especially important for AVS. To achieve this, our ECMVAE factorizes the representations of each modality with a modality-shared representation and a modality-specific representation. An orthogonality constraint is applied between the shared and specific representations to maintain the exclusive attribute of the factorized latent code. Further, a mutual information maximization regularizer is introduced to achieve extensive exploration of each modality. Quantitative and qualitative evaluations on the AVSBench demonstrate the effectiveness of our approach, leading to a new state-of-the-art for AVS, with a 3.84 mIOU performance leap on the challenging MS3 subset for multiple sound source segmentation.