# AV-Unified: A Unified Framework for Audio-visual Scene Understanding

arXiv: https://arxiv.org/abs/2603.06530 · HTML: https://mlsanity.com/paper/2603.06530/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 62 of its 94 references that are in the map.
- First posted on arXiv 6 Mar 2026.

## Builds on (most cited first, 30 of 62)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks](https://mlsanity.com/paper/2206.08916/) (2022)
- [Deep Modular Co-Attention Networks for Visual Question Answering](https://mlsanity.com/paper/1906.10770/) (2019)
- [Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action](https://mlsanity.com/paper/2312.17172/) (2023)
- [Hierarchical Question-Image Co-Attention for Visual Question Answering](https://mlsanity.com/paper/1606.00061/) (2016)
- [VTimeLLM: Empower LLM to Grasp Video Moments](https://mlsanity.com/paper/2311.18445/) (2023)
- [Learning to Answer Questions in Dynamic Audio-Visual Scenarios](https://mlsanity.com/paper/2203.14072/) (2022)
- [Learning to Localize Sound Source in Visual Scenes](https://mlsanity.com/paper/1803.03849/) (2018)
- [Self-Supervised Learning of Audio-Visual Objects from Video](https://mlsanity.com/paper/2008.04237/) (2020)
- [Localizing Visual Sounds the Hard Way](https://mlsanity.com/paper/2104.02691/) (2021)
- [Hierarchical Conditional Relation Networks for Video Question Answering](https://mlsanity.com/paper/2002.10698/) (2020)
- [A Unified Sequence Interface for Vision Tasks](https://mlsanity.com/paper/2206.07669/) (2022)
- [Audio-Visual Segmentation](https://mlsanity.com/paper/2207.05042/) (2022)
- [Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering](https://mlsanity.com/paper/1904.04357/) (2019)
- [Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing](https://mlsanity.com/paper/2007.10558/) (2020)
- [UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling](https://mlsanity.com/paper/2111.12085/) (2021)
- [Multiple Sound Sources Localization from Coarse to Fine](https://mlsanity.com/paper/2007.06355/) (2020)
- [SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation](https://mlsanity.com/paper/2101.08833/) (2021)
- [Pano-AVQA: Grounded Audio-Visual Question Answering on 360^circ Videos](https://mlsanity.com/paper/2110.05122/) (2021)
- [Localizing Visual Sounds the Easy Way](https://mlsanity.com/paper/2203.09324/) (2022)
- [Audio-Visual Segmentation with Semantics](https://mlsanity.com/paper/2301.13190/) (2023)
- [Dual-modality seq2seq network for audio-visual event localization](https://mlsanity.com/paper/1902.07473/) (2019)
- [Positive Sample Propagation along the Audio-Visual Event Line](https://mlsanity.com/paper/2104.00239/) (2021)
- [AVSegFormer: Audio-Visual Segmentation with Transformer](https://mlsanity.com/paper/2307.01146/) (2023)
- [Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction](https://mlsanity.com/paper/2112.13528/) (2021)
- [Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation](https://mlsanity.com/paper/2305.16318/) (2023)
- [CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video Segmentation](https://mlsanity.com/paper/2309.09709/) (2023)
- [A Simple Baseline for Audio-Visual Scene-Aware Dialog](https://mlsanity.com/paper/1904.05876/) (2019)

## Abstract (arXiv)

When humans perceive the world, they naturally integrate multiple audio-visual tasks within dynamic, real-world scenes. However, current works such as event localization, parsing, segmentation and question answering are mostly explored individually, making it challenging to comprehensively understand complex audio-visual scenes and explore inter-task relationships. Hence, we propose AV-Unified, a unified framework that enables joint learning across a wide range of audio-visual scene understanding tasks. AV-Unified standardizes the diverse input-output formats of each task and incorporates a multi-scale spatiotemporal perception network to effectively capture audio-visual associations. Specifically, we unify the inputs and outputs of all supported tasks by converting them into sequences of discrete tokens, establishing a shared representation that allows a single architecture to be trained jointly across heterogeneous varied datasets. Considering the varying temporal granularity of audio-visual events, a multi-scale temporal perception module is designed to capture key cues. Meanwhile, to overcome the lack of auditory supervision in the visual domain, we design a cross-modal guidance-based spatial perception module that models spatial audio-visual associations. Furthermore, task-specific text prompts are employed to enhance the model's adaptability and task-awareness. Extensive experiments on benchmark datasets (e.g., AVE, LLP, MUSIC-AVQA, VGG-SS and AVS) demonstrate the effectiveness of AV-Unified across temporal, spatial, and spatiotemporal tasks.