AI Paper Atlas

Research map / Video / Video-language understanding

CoT-RVS: Zero-Shot Chain-of-Thought Reasoning Segmentation for Videos

Shiu-hong Kao, Yu-Wing Tai, Chi-Keung Tang

ICLR 2026 · Video › Video-language understanding · approach: Long video understanding · 17 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
use zero-shot CoT-RVS with GPT-4o instead of best finetuned baselinereasoning VOS · MeViSJ&F: 51.3 -> 52.2Improved
use CoT-RVS-GPT-4o instead of GLUSReasonVOS · ReasonVOSJ&F: 49.9 -> 65.5Improved
use CoT-RVS-GPT-4o instead of HyperSegReVOS · ReVOSJ&F: 55.7 -> 55.9Improved
use CoT-RVS-Gemma3-12B instead of best finetuned baselineMeViS · MeViSJ&F: 51.3 -> 44.2Hurt
use GPT-4o instead of Gemma3-12B as keyframe selector (ablation)CoT-RVS · ReasonVOSJ&F: 50.7 -> 65.5Improved
use CoT-RVS-GPT-4o on temporally sensitive queriesCoT-RVS · T-ReasonVOSJ&F: 37.4 -> 55.5Improved
use 8 keyframe candidates instead of 16 (ablation)CoT-RVS (GPT-4o) · ReasonVOSJ&F: 60.0 -> 65.5Improved
use 4 keyframe candidates instead of 8 (ablation)CoT-RVS (GPT-4o) · ReasonVOSJ&F: 65.5 -> 66.2No clear effect
add chain-of-thought prompting for keyframe selection (ablation)CoT-RVS · ReasonVOS / onlineJ&FImproved
use online CoT-RVS (LLaVA1.5-7B) instead of offline GPT-4oCoT-RVS · Refer-DAVIS-17J&F: 79.1 -> 73.9Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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