AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Multimodal Referring Segmentation: A Survey

IJCV 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation

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
modern fully-supervised transformer vs early LSTM-CNNOneRef-L · RefCOCOg val (UMD)mIoU: 34.06 -> 75.68Improved
MLLM-based SAM4MLLM vs conventional OneRef-L on testSAM4MLLM-8B · RefCOCOg test (UMD)mIoU: 76.82 -> 76.40No clear effect
weak/semi-supervision (ADDP) vs full supervisionADDP · RefCOCOg val (UMD)mIoU: 59.05 -> 75.68Mixed
recent RVOS method vs URVOSVRS-HQ · Ref-YouTube-VOSJ&F: 47.23 -> 71.00Improved
GLUS vs VRS-HQ on MeViSGLUS · MeViSJ&F: 50.90 -> 51.30No clear effect
recent AVS method vs original AVSBench baselineDDESeg · AVSBench S4J: 78.74 -> 92.40Improved
DDESeg on harder AVSS benchmarkDDESeg · AVSBench-Semantic AVSSJ: 29.77 -> 63.40Improved
weakly-supervised WS-AVS vs fully-supervised RAVSWS-AVS · AVSBench S4J: 34.13 -> 93.10Hurt
OISA-1B vs LISA-13B on OmniAVSOISA-1B · OmniAVS (All)J&F: 36.1 -> 41.1Improved
larger LISA modelLISA · OmniAVS (All)J&F: 33.6 -> 36.1Improved
OISA-1B on Ref-AVS seen vs unseen subsetsOISA-1B · Ref-AVSJ: 51.7 -> 58.3Mixed

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