paper-with-me

홈 › Papers

Reinforcing Video Reasoning Segmentation to Think Before It Segments

2025-08-15 · Sitong Gong, Lu Zhang, Yunzhi Zhuge, Xu Jia, Pingping Zhang, Huchuan Lu arxiv

Video reasoning segmentation (VRS) endeavors to delineate referred objects in videos guided by implicit instructions that encapsulate human intent and temporal logic. Previous approaches leverage large vision language models (LVLMs) to encode object semantics into <SEG> tokens for mask prediction. However, this paradigm suffers from limited interpretability during inference and suboptimal performance due to inadequate spatiotemporal reasoning. Drawing inspiration from seminal breakthroughs in reinforcement learning, we introduce Veason-R1, a specialized LVLM for VRS that emphasizes structured reasoning in segmentation. Veason-R1 is trained through Group Relative Policy Optimization (GRPO) augmented with Chain-of-Thought (CoT) initialization. To begin with, we curate high-quality CoT training data to instill structured reasoning trajectories, bridging video-level semantics and frame-level spatial grounding, yielding the supervised fine-tuned model Veason-SFT. Subsequently, GRPO fine-tuning encourages efficient exploration of the reasoning space by optimizing reasoning chains. To this end, we incorporate a holistic reward mechanism that synergistically enhances spatial alignment and temporal consistency, bolstering keyframe localization and fine-grained grounding. Comprehensive empirical evaluations demonstrate that Veason-R1 achieves state-of-the-art performance on multiple benchmarks, surpassing prior art by significant margins (e.g., +1.3 J &F in ReVOS and +10.0 J &F in ReasonVOS), while exhibiting robustness to hallucinations (+8.8 R). Our code and model weights will be available at Veason-R1.

📄 PDF Abstract BibTeX arXiv:2508.11538

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

GraphThinker: Reinforcing Temporally Grounded Video Reasoning with Event Graph Thinking

2026-02-19 · Zixu Cheng, Da Li, Jian Hu, Yuhang Zang 외 arxiv

Video reasoning requires a fine-grained understanding of the temporal dependencies and event-level relations between objects and events in videos. Current Multimodal Large Language Models (MLLMs) are prone to severe temp…

Visual Grounding

Think Before You Segment: An Object-aware Reasoning Agent for Referring Audio-Visual Segmentation

2025-08-06 · Jinxing Zhou, Yanghao Zhou, Mingfei Han, Tong Wang 외 arxiv

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 promp…

ThinkVideo: High-Quality Reasoning Video Segmentation with Chain of Thoughts

2025-05-24 · Shiu-hong Kao, Yu-Wing Tai, Chi-Keung Tang

Reasoning Video Object Segmentation is a challenging task, which generates a mask sequence from an input video and an implicit, complex text query. Existing works probe into the problem by finetuning Multimodal Large Lan…

Image SegmentationInstance SegmentationObjectReasoning Video Object Segmentation+6

Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models

2025-11-28 · Muhammad Maaz, Hanoona Rasheed, Fahad Shahbaz Khan, Salman Khan arxiv

Reasoning over dynamic visual content remains a central challenge for multimodal large language models. Recent thinking models generate explicit reasoning traces for interpretability; however, their reasoning often appea…

Reinforcement Learning

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training

2025-05-20 · Mengru Wang, Xingyu Chen, Yue Wang, Zhiwei He 외

Mixture-of-Experts (MoE) architectures within Large Reasoning Models (LRMs) have achieved impressive reasoning capabilities by selectively activating experts to facilitate structured cognitive processes. Despite notable …

AllDomain GeneralizationInstruction FollowingMixture-of-Experts