Score: 1

ReVSeg: Incentivizing the Reasoning Chain for Video Segmentation with Reinforcement Learning

Published: December 2, 2025 | arXiv ID: 2512.02835v1

By: Yifan Li , Yingda Yin , Lingting Zhu and more

Potential Business Impact:

Helps computers understand moving objects in videos.

Business Areas:
Image Recognition Data and Analytics, Software

Reasoning-centric video object segmentation is an inherently complex task: the query often refers to dynamics, causality, and temporal interactions, rather than static appearances. Yet existing solutions generally collapse these factors into simplified reasoning with latent embeddings, rendering the reasoning chain opaque and essentially intractable. We therefore adopt an explicit decomposition perspective and introduce ReVSeg, which executes reasoning as sequential decisions in the native interface of pretrained vision language models (VLMs). Rather than folding all reasoning into a single-step prediction, ReVSeg executes three explicit operations -- semantics interpretation, temporal evidence selection, and spatial grounding -- aligning pretrained capabilities. We further employ reinforcement learning to optimize the multi-step reasoning chain, enabling the model to self-refine its decision quality from outcome-driven signals. Experimental results demonstrate that ReVSeg attains state-of-the-art performances on standard video object segmentation benchmarks and yields interpretable reasoning trajectories. Project page is available at https://clementine24.github.io/ReVSeg/ .

Page Count
15 pages

Category
Computer Science:
CV and Pattern Recognition