Saved in:
Bibliographic Details
Main Authors: Zhao, Yuan, Jia, Zhenqi, Zhang, Yongqiang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.27706
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917366301982720
author Zhao, Yuan
Jia, Zhenqi
Zhang, Yongqiang
author_facet Zhao, Yuan
Jia, Zhenqi
Zhang, Yongqiang
contents Reference Audio-Visual Segmentation (Ref-AVS) aims to segment objects in audible videos based on multimodal cues in reference expressions. Previous methods overlook the explicit recognition of expression difficulty and dominant modality in multimodal cues, over-rely on the quality of the instruction-tuning dataset for object reasoning, and lack reflective validation of segmentation results, leading to erroneous mask predictions. To address these issues, in this paper, we propose a novel training-free Multi-Agent Recognition, Reasoning, and Reflection framework to achieve high-quality Reference Audio-Visual Segmentation, termed MAR3. Incorporating the sociological Delphi theory to achieve robust analysis, a Consensus Multimodal Recognition mechanism is proposed that enables LLM agents to explicitly recognize the difficulty of reference expressions and the dominant modality of multimodal cues. Based on our modality-dominant difficulty rule, we propose an adaptive Collaborative Object Reasoning strategy to reliably reason about the referred object. To further ensure precise mask prediction, we develop a Reflective Learning Segmentation mechanism, in which a check agent examines intermediate segmentation results and iteratively corrects the object text prompt of the segment agent. Experiments demonstrate that MAR3 achieves superior performance (69.2% in J&F) on the Ref-AVSBench dataset, outperforming SOTA by 3.4% absolutely.
format Preprint
id arxiv_https___arxiv_org_abs_2603_27706
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MAR3: Multi-Agent Recognition, Reasoning, and Reflection for Reference Audio-Visual Segmentation
Zhao, Yuan
Jia, Zhenqi
Zhang, Yongqiang
Multimedia
Reference Audio-Visual Segmentation (Ref-AVS) aims to segment objects in audible videos based on multimodal cues in reference expressions. Previous methods overlook the explicit recognition of expression difficulty and dominant modality in multimodal cues, over-rely on the quality of the instruction-tuning dataset for object reasoning, and lack reflective validation of segmentation results, leading to erroneous mask predictions. To address these issues, in this paper, we propose a novel training-free Multi-Agent Recognition, Reasoning, and Reflection framework to achieve high-quality Reference Audio-Visual Segmentation, termed MAR3. Incorporating the sociological Delphi theory to achieve robust analysis, a Consensus Multimodal Recognition mechanism is proposed that enables LLM agents to explicitly recognize the difficulty of reference expressions and the dominant modality of multimodal cues. Based on our modality-dominant difficulty rule, we propose an adaptive Collaborative Object Reasoning strategy to reliably reason about the referred object. To further ensure precise mask prediction, we develop a Reflective Learning Segmentation mechanism, in which a check agent examines intermediate segmentation results and iteratively corrects the object text prompt of the segment agent. Experiments demonstrate that MAR3 achieves superior performance (69.2% in J&F) on the Ref-AVSBench dataset, outperforming SOTA by 3.4% absolutely.
title MAR3: Multi-Agent Recognition, Reasoning, and Reflection for Reference Audio-Visual Segmentation
topic Multimedia
url https://arxiv.org/abs/2603.27706