AI Paper Atlas

Research map / Video / Video-language understanding

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

Ming Dai, Sen Yang, Boqiang Duan, Boyuan Tong, Jiedong Zhuang, Wankou Yang, Jingdong Wang

ICML 2026 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add CoT cold-start stage on top of SFT (ablation)VideoSEG-O3-4B · Long-RVOSJ&F: 47.12 -> 51.82Improved
Add CoT cold-start stage on top of SFT (ablation)VideoSEG-O3-4B · Ref-SAVJ&F: 51.97 -> 50.11Hurt
Add RL stage after CoT cold-start (ablation)VideoSEG-O3-4B · Six RVOS benchmarks averageAvg. J&F: 57.07 -> 60.29Improved
Add RL stage after CoT cold-start (ablation)VideoSEG-O3-4B · Six RVOS benchmarks averageAvg. rounds: 2.79 -> 2.23Improved
Use standard GRPO with text-only importance ratio (ablation)Stage II cold-start model · MeViS (valu)J&F: 59.43 -> 57.92Hurt
Add SEG-aware logit calibration to GRPO (ablation)GRPO-RL baseline · Ref-SAVJ&F: 49.78 -> 51.27Improved
Add SEG-aware logit calibration to GRPO (ablation)GRPO-RL baseline · MeViS (valu)J&F: 57.92 -> 60.51Improved
Add spatial-wise auxiliary segmentation loss (ablation)GRPO + SEG calibration · MeViS (valu)J&F: 60.51 -> 60.71Improved
Add keyframe-wise auxiliary segmentation loss (ablation)GRPO + SEG calibration · MeViS (valu)J&F: 60.51 -> 61.31Improved
Use joint spatial and keyframe auxiliary loss (ablation)GRPO + SEG calibration · MeViS (valu)J&F: 60.51 -> 61.95Improved
Use joint auxiliary segmentation loss (ablation)GRPO + SEG calibration · Ref-SAVJ&F: 51.27 -> 53.22Improved
Apply RL to keyframe selection (ablation)VideoSEG-O3-4B · four RVOS benchmarkskeyframe mIoU and empty ratioImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy