AI Paper Atlas

Research map / Video / Video segmentation and tracking

VIRST: Video-Instructed Reasoning Assistant for SpatioTemporal Segmentation

Jihwan Hong, Jaeyoung Do

CVPR 2026 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 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 Initial and Second ST-Fusion together (vs. removing Initial) (ablation)VIRST · MeViS validJ&F: 59.7 -> 62.9Improved
use Second ST-Fusion with cross-attention instead of an MLP (ablation)VIRST · MeViS validJ&F: 59.4 -> 62.9Improved
use dynamic anchor updating instead of first-frame anchor (ablation)VIRST · MeViS validJ&F: 57.9 -> 62.9Improved
use dynamic anchor updating instead of CLIP-guided selection (ablation)VIRST · MeViS validJ&F: 59.3 -> 62.9Improved
update anchors over time instead of fixed uniform-3 anchors (ablation)VIRST · MeViS validJ&F: 61.9 -> 62.9Improved
increase number of anchor frames from 2 to 8 (ablation)VIRST · MeViS validJ&F: 62.5 -> 63.2Improved
increase anchor frames from 3 to 4 (ablation)VIRST · MeViS validJ&F: 62.9 -> 62.9No clear effect
VIRST vs prior best on image reasoning segmentationVIRST · ReasonSegcIoU: 65.2 -> 65.0No clear effect
VIRST vs prior best on RefCOCO testBVIRST · RefCOCO testBcIoU: 84.0 -> 81.2Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 4 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