AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Region-aware Anchoring Mechanism for Efficient Referring Visual Grounding

Shuyi Ouyang, Ziwei Niu, Hongyi Wang, Yen-Wei Chen, Lanfen Lin

ICCV 2025 · Vision-language and multimodal › Human and embodied modeling · approach: Visual grounding transformers · 2 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
replace direct interaction (LAVT design) with RaAM (ablation)RaAM-RVG · gRefCOCO val (GRES)cIoU: 64.77 -> 67.35Improved
replace direct interaction (LAVT design) with RaAM (ablation)RaAM-RVG · gRefCOCO val (GRES)gIoU: 67.62 -> 70.02Improved
add L2V gate (ablation)RaAM-RVG · gRefCOCO val (GRES)cIoU: 65.74 -> 67.35Improved
add L2V gate (ablation)RaAM-RVG · gRefCOCO val (GRES)Pr@0.9: 25.86 -> 27.43Improved
add learnable coefficients and linear transform flow control components (ablation)RaAM-RVG · gRefCOCO val (GRES)cIoU: 63.87 -> 67.35Improved
generate anchors in 2 stages instead of 1 (ablation)RaAM-RVG · gRefCOCO val (GRES)cIoU: 66.38 -> 67.35Improved
generate anchors in 3 stages instead of 2 (ablation)RaAM-RVG · gRefCOCO val (GRES)cIoU: 67.35 -> 64.58Hurt
generate anchors in 4 stages instead of 2 (ablation)RaAM-RVG · gRefCOCO val (GRES)cIoU: 67.35 -> 60.22Hurt
add region loss Lr and pixel loss Lseg_p (ablation)RaAM-RVG · gRefCOCO val (GRES)cIoU: 65.09 -> 67.35Improved
integrate RaAM into LAVTLAVT · gRefCOCO val (GRES)cIoU: 57.64 -> 61.45Improved
integrate RaAM into PolyFormerPolyFormer · gRefCOCO val (GRES)cIoU: 59.35 -> 63.79Improved
integrate RaAM into HyperSegHyperSeg · gRefCOCO val (GRES)cIoU: 62.75 -> 66.68Improved

Earlier methods this paper compares with

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