Referring Audio-Visual Segmentation (Ref-AVS) aims to segment specific objects in videos based on natural language expressions involving audio, vision, and text information. This task poses significant challenges in cross-modal reasoning and fine-grained object localization. In this paper, we propose a simple framework, SimToken, that integrates a multimodal large language model (MLLM) with the Segment Anything Model (SAM). The MLLM is guided to generate a special semantic token representing the referred object. This compact token, enriched with contextual information from all modalities, acts as a prompt to guide SAM to segment objectsacross video frames. To further improve semantic learning, we introduce a novel target-consistent semantic alignment loss that aligns token embeddings from different expressions but referring to the same object. Experiments on the Ref-AVS benchmark demonstrate that our approach achieves superior performance compared to existing methods.
@article{arxiv.2509.17537,
title = {SimToken: A Simple Baseline for Referring Audio-Visual Segmentation},
author = {Dian Jin and Yanghao Zhou and Jinxing Zhou and Jiaqi Ma and Ruohao Guo and Dan Guo},
journal= {arXiv preprint arXiv:2509.17537},
year = {2025}
}