AI Paper Atlas

Research map / Video / Video segmentation and tracking

QST-SAM: Leveraging Cross-modal Instructions for Few-shot Referring Video Object Segmentation

Xin Liu, Weijia Li, Tao Chen, Hongsong Wang, Guosen Xie, Caifeng Shan, Fang Zhao

ECCV 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 Q-S-T Transformer (with Support Instruction Compressor) (ablation)QST-SAM · Ref-YouTube-VOSJ&F: 62.4 vs 60.8 (-1.6)Improved
add Multi-Priors Prompting (ablation)QST-SAM · Ref-YouTube-VOSJ&F: 62.4 vs 61.7 (-0.7)Improved
add both Q-S-T Transformer and Multi-Priors Prompting (ablation)QST-SAM · Ref-YouTube-VOSJ&F: 62.4 vs 60.4 (-2.0)Improved
increase support instructions K from 4 to 32 (ablation)QST-SAM · Ref-YouTube-VOSJ&F: 59.8 -> 62.4Improved
increase support instructions K from 32 to 64 (ablation)QST-SAM · Ref-YouTube-VOSJ&F: 62.4 -> 62.6 (+0.2), memory 42.2 -> 47.6 GBNo clear effect
add 5-shot support images to SAMWISE with simple cross-attention fusionSAMWISE · Ref-DAVIS17J&F: 65.5 -> 67.5 (+2.0)Improved
add 5-shot support images to SAMWISE with simple cross-attention fusionSAMWISE · Ref-YouTube-VOSJ&F: 59.3 -> 60.4 (+1.1)Improved
replace SAMWISE simple fusion with QST-SAMQST-SAM · Ref-DAVIS17J&F: 67.5 -> 70.3Improved
replace SAMWISE simple fusion with QST-SAMQST-SAM · Ref-YouTube-VOSJ&F: 60.4 -> 62.4Improved
drop support-side text annotations (QST-SAM vs CMA-ISM)QST-SAM · Mini-Ref-YouTube-VOS (legacy FSRVOS)J&F: 54.0 -> 59.2 (+5.2)Improved
add 5-shot support images to ReferDINOReferDINO · Ref-YouTube-VOSJ&F: 59.8 -> 60.6 (+0.8)Improved
add 5-shot support images to LoShLoSh · Ref-DAVIS17J&F: 60.4 -> 64.9 (+4.5)Improved

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