Think Before You Segment: An Object-aware Reasoning Agent for Referring Audio-Visual Segmentation
Abstract
Referring Audio-Visual Segmentation (Ref-AVS) aims to segment target objects in audible videos based on given reference expressions. Prior works typically rely on learning latent embeddings via multimodal fusion to prompt a tunable SAM/SAM2 decoder for segmentation, which requires strong pixel-level supervision and lacks interpretability. From a novel perspective of explicit reference understanding, we propose TGS-Agent, which decomposes the task into a Think-Ground-Segment process, mimicking the human reasoning procedure by first identifying the referred object through multimodal analysis, followed by coarse-grained grounding and precise segmentation. To this end, we first propose Ref-Thinker, a multimodal language model capable of reasoning over textual, visual, and auditory cues. We construct an instruction-tuning dataset with explicit object-aware think-answer chains for Ref-Thinker fine-tuning. The object description inferred by Ref-Thinker is used as an explicit prompt for Grounding-DINO and SAM2, which perform grounding and segmentation without relying on pixel-level supervision. Additionally, we introduce R\textsuperscript{2}-AVSBench, a new benchmark with linguistically diverse and reasoning-intensive references for better evaluating model generalization. Our approach achieves state-of-the-art results on both standard Ref-AVSBench and proposed R\textsuperscript{2}-AVSBench. Code will be available at https://github.com/jasongief/TGS-Agent.
Cite
@article{arxiv.2508.04418,
title = {Think Before You Segment: An Object-aware Reasoning Agent for Referring Audio-Visual Segmentation},
author = {Jinxing Zhou and Yanghao Zhou and Mingfei Han and Tong Wang and Xiaojun Chang and Hisham Cholakkal and Rao Muhammad Anwer},
journal= {arXiv preprint arXiv:2508.04418},
year = {2025}
}
Comments
Project page: https://github.com/jasongief/TGS-Agent