cs.CVOct 30, 2026

ReVEAL: Eliciting Role-Aware Latent Visual Evidence from MLLMs for Reasoning Video Object Segmentation

Authors: Zhongyuan Bao, Cunjie He, Lejun Zhang, Zenglin Xu, Yanwei Fu

Organizations: Fudan University · New York University

Abstract

Reasoning video object segmentation (ReVOS) requires segmenting the target specified by an implicit query throughout a video. Existing MLLM-based methods typically require costly cross-model alignment, tying MLLM training to a downstream segmentation model. We present ReVEAL, a decoupled thinking-with-video framework for ReVOS that elicits role-aware latent visual evidence from MLLM reasoning to directly guide segmentation. ReVEAL introduces Visual Evidence Tokens (VETs) into video reasoning to associate necessary visual regions or entities with target, background, or distractor roles, while a Dynamic Attention Layer Router adaptively aggregates VET-to-video attention across layers into role-specific grounding evidence. We train the MLLM to perform VET-augmented reasoning on our constructed ReVEAL-47K dataset, with a Contrastive Attention Grounding Loss as auxiliary supervision to apply role-specific constraints to VET attention and optimize layer routing for reliable latent grounding. At inference, ReVEAL identifies the target through this thinking-with-video process and fuses the resulting role-specific evidence to guide a frozen SAM2 in predicting target masks. Experiments on five benchmarks show that ReVEAL outperforms alignment-free baselines and remains competitive with alignment-based methods.

Figures & tables

Appendix figures & tables15 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Beyond Token Representations: Explicit Visual Object Grounding for Video Reasoning Segmentation

    Nov 3, 2026Jun Huang, Junyang Zhang, Zijie Yue +3Video ReasoningVideo Object Segmentation

  2. RCoT-Seg: Reinforced Chain-of-Thought for Video Reasoning and Segmentation

    May 8, 2026Junwei Wen, Deshui Miao, Guangming Lu +2Video Object SegmentationVideo Reasoning

  3. VideoSEG-O3: A Multi-turn Reinforcement Learning Framework for Reasoning Video Object Segmentation

    Jun 5, 2026Ming Dai, Sen Yang, Boqiang Duan +4Video Object SegmentationReferring Video Object Segmentation