# Bridging Audio and Vision: Zero-Shot Audiovisual Segmentation by Connecting Pretrained Models

arXiv: https://arxiv.org/abs/2506.06537 · HTML: https://mlsanity.com/paper/2506.06537/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 30 references that are in the map.
- First posted on arXiv 6 Jun 2025.

## Builds on (most cited first, 23 of 23)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [VGGSound: A Large-scale Audio-Visual Dataset](https://mlsanity.com/paper/2004.14368/) (2020)
- [BEATs: Audio Pre-Training with Acoustic Tokenizers](https://mlsanity.com/paper/2212.09058/) (2022)
- [CRIS: CLIP-Driven Referring Image Segmentation](https://mlsanity.com/paper/2111.15174/) (2021)
- [WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research](https://mlsanity.com/paper/2303.17395/) (2023)
- [Localizing Visual Sounds the Hard Way](https://mlsanity.com/paper/2104.02691/) (2021)
- [Audio-Visual Segmentation](https://mlsanity.com/paper/2207.05042/) (2022)
- [Localizing Visual Sounds the Easy Way](https://mlsanity.com/paper/2203.09324/) (2022)
- [A Closer Look at Weakly-Supervised Audio-Visual Source Localization](https://mlsanity.com/paper/2209.09634/) (2022)
- [Natural Language Supervision for General-Purpose Audio Representations](https://mlsanity.com/paper/2309.05767/) (2023)
- [Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning](https://mlsanity.com/paper/2303.11302/) (2023)
- [Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation](https://mlsanity.com/paper/2206.12772/) (2022)
- [Improving Audio-Visual Segmentation with Bidirectional Generation](https://mlsanity.com/paper/2308.08288/) (2023)
- [Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation](https://mlsanity.com/paper/2304.02970/) (2023)
- [BAVS: Bootstrapping Audio-Visual Segmentation by Integrating Foundation Knowledge](https://mlsanity.com/paper/2308.10175/) (2023)
- [Learning to Localize Sound Sources in Visual Scenes: Analysis and Applications](https://mlsanity.com/paper/1911.09649/) (2019)
- [MarginNCE: Robust Sound Localization with a Negative Margin](https://mlsanity.com/paper/2211.01966/) (2022)
- [Learning to Visually Localize Sound Sources from Mixtures without Prior Source Knowledge](https://mlsanity.com/paper/2403.17420/) (2024)
- [Aligning Sight and Sound: Advanced Sound Source Localization Through Audio-Visual Alignment](https://mlsanity.com/paper/2407.13676/) (2024)

## Built on by (most cited first, 1 of 1)

- [Acoustic Field Video for Multimodal Scene Understanding](https://mlsanity.com/paper/2601.17123/) (2026)

## Abstract (arXiv)

Audiovisual segmentation (AVS) aims to identify visual regions corresponding to sound sources, playing a vital role in video understanding, surveillance, and human-computer interaction. Traditional AVS methods depend on large-scale pixel-level annotations, which are costly and time-consuming to obtain. To address this, we propose a novel zero-shot AVS framework that eliminates task-specific training by leveraging multiple pretrained models. Our approach integrates audio, vision, and text representations to bridge modality gaps, enabling precise sound source segmentation without AVS-specific annotations. We systematically explore different strategies for connecting pretrained models and evaluate their efficacy across multiple datasets. Experimental results demonstrate that our framework achieves state-of-the-art zero-shot AVS performance, highlighting the effectiveness of multimodal model integration for finegrained audiovisual segmentation.