AI Paper Atlas

Research map / Video / Video segmentation and tracking

ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations

Tianming Liang, Kun-Yu Lin, Chaolei Tan, Jianguo Zhang, Wei-Shi Zheng, Jian-Fang Hu

ICCV 2025 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 28 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 cross-modal attention to the mask decoder (ablation)ReferDINO (Swin-T) · MeViSJ&F: 47.6 -> 48.0Improved
add deformable cross-attention to the mask decoder (ablation)ReferDINO (Swin-T) · MeViSJ&F: 45.3 -> 48.0Improved
add memory-augmented tracker to the temporal enhancer (ablation)ReferDINO (Swin-T) · MeViSJ&F: 47.6 -> 48.0Improved
add cross-modal temporal decoder (ablation)ReferDINO (Swin-T) · MeViSJ&F: 45.8 -> 48.0Improved
prune 50% of queries with confidence-aware strategy (ablation)ReferDINO · Ref-YouTube-VOSJ&F: 67.6 -> 67.5No clear effect
prune 50% of queries with confidence-aware strategy (ablation)ReferDINO · Ref-YouTube-VOSFPS: 4.9 -> 51.0Improved
prune 50% of queries with confidence-aware strategy (ablation)ReferDINO · Ref-YouTube-VOSFLOPs: 840.3G -> 499.3GImproved
prune 50% of queries with confidence-aware strategy (ablation)ReferDINO · Ref-YouTube-VOSGPU memory: 24.0G -> 14.1GImproved
replace confidence-aware pruning with random pruning of 50% queries (ablation)ReferDINO · Ref-YouTube-VOSJ&F: 67.5 -> 38.3Hurt
use ReferDINO decoder and enhancer instead of dynamic mask head baselineG-DINO+DH (Swin-T) · Ref-YouTube-VOSJ&F: 64.2 -> 67.5Improved
use ReferDINO instead of dynamic mask head baselineG-DINO-DH (Swin-T) · MeViSJ&F: 45.4 -> 48.0Improved
use grounding-guided mask decoder instead of dynamic mask headG-DINO+DH · Ref-YouTube-VOStraining memory: 25.3G -> 14.1GImproved

Later papers that compared with this method

5 later accepted papers report ReferDINO as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

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