AI Paper Atlas

Research map / Video / Video-language understanding

InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models

Cong Wei, Yujie Zhong, Haoxian Tan, Yingsen Zeng, Yong Liu, Hongfa Wang, Yujiu Yang

ICCV 2025 · Video › Video-language understanding · approach: Long video understanding · 33 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 OVP and VMTF together (ablation)InstructSeg · RefCOCO valcIoU: 83.3 -> 85.8Improved
add OVP and VMTF together (ablation)InstructSeg · ReVOS overallJ&F: 52.9 -> 54.5Improved
add Object-aware Video Perceiver (ablation)InstructSeg without modules · ReVOS overallJ&F: 52.9 -> 54.0Improved
add Vision-guided Multi-granularity Text Fusion (ablation)InstructSeg without modules · RefCOCO valcIoU: 83.3 -> 84.8Improved
increase reference frames from 0 to 4 (ablation)InstructSeg OVP · ReVOS overallJ&F: 53.6 -> 54.5Improved
increase reference frames from 4 to 8 (ablation)InstructSeg OVP · ReVOS overallJ&F: 54.5 -> 54.6No clear effect
fuse detailed text with global text instead of global only (ablation)InstructSeg VMTF · RefCOCO valcIoU: 84.2 -> 85.8Improved
fuse global text with detailed text instead of detailed only (ablation)InstructSeg VMTF · ReVOS reasoningJ&F: 51.6 -> 51.9Improved
add video training data to image-only training (ablation)InstructSeg · ReVOS overallJ&F: 48.7 -> 54.5Improved
add image training data to video-only training (ablation)InstructSeg · RefCOCO valcIoU: 78.1 -> 85.8Improved
add referring data to reasoning-only training (ablation)InstructSeg · RefCOCO valcIoU: 74.0 -> 85.8Improved
add reasoning data to referring-only training (ablation)InstructSeg · ReVOS reasoningJ&F: 37.4 -> 51.9Improved

Later papers that compared with this method

2 later accepted papers report InstructSeg as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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