# TAViS: Text-bridged Audio-Visual Segmentation with Foundation Models

arXiv: https://arxiv.org/abs/2506.11436 · HTML: https://mlsanity.com/paper/2506.11436/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 5 references that are in the map.
- First posted on arXiv 13 Jun 2025.

## Builds on (most cited first, 5 of 5)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [RegionCLIP: Region-based Language-Image Pretraining](https://mlsanity.com/paper/2112.09106/) (2021)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [AVSegFormer: Audio-Visual Segmentation with Transformer](https://mlsanity.com/paper/2307.01146/) (2023)
- [Annotation-free Audio-Visual Segmentation](https://mlsanity.com/paper/2305.11019/) (2023)

## Built on by (most cited first, 4 of 4)

- [Delayed Bidirectional Alignment via Disentangled Audio Semantics for Audio-Visual Segmentation](https://mlsanity.com/paper/2512.20117/) (2025)
- [Audit After Segmentation: Reference-Free Mask Quality Assessment for Language-Referred Audio-Visual Segmentation](https://mlsanity.com/paper/2602.03892/) (2026)
- [TB-AVA: Text as a Semantic Bridge for Audio-Visual Parameter Efficient Finetuning](https://mlsanity.com/paper/2605.11572/) (2026)
- [SlotAVS: Object-Centric Audio-Visual Segmentation via Bi-Modal Slot Attention](https://mlsanity.com/paper/2610.15764/) (2026)

## Abstract (arXiv)

Audio-Visual Segmentation (AVS) faces a fundamental challenge of effectively aligning audio and visual modalities. While recent approaches leverage foundation models to address data scarcity, they often rely on single-modality knowledge or combine foundation models in an off-the-shelf manner, failing to address the cross-modal alignment challenge. In this paper, we present TAViS, a novel framework that couples the knowledge of multimodal foundation models (ImageBind) for cross-modal alignment and a segmentation foundation model (SAM2) for precise segmentation. However, effectively combining these models poses two key challenges: the difficulty in transferring the knowledge between SAM2 and ImageBind due to their different feature spaces, and the insufficiency of using only segmentation loss for supervision. To address these challenges, we introduce a text-bridged design with two key components: (1) a text-bridged hybrid prompting mechanism where pseudo text provides class prototype information while retaining modality-specific details from both audio and visual inputs, and (2) an alignment supervision strategy that leverages text as a bridge to align shared semantic concepts within audio-visual modalities. Our approach achieves superior performance on single-source, multi-source, semantic datasets, and excels in zero-shot settings.