AI Paper Atlas

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

AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations

Junli Liu, Qizhi Chen, Zhigang Wang, Yiwen Tang, Yiting Zhang, Chi Yan, Dong Wang, Xuelong Li, Bin Zhao

ICCV 2025 · Vision-language and multimodal › Human and embodied modeling · approach: Visual grounding transformers · 14 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 hierarchical cross-attention (ablation)Grounding DINO · AerialVG (fine-tuned)Top-5 accuracy: 78.87 -> 82.32Improved
add hierarchical cross-attention (ablation)Grounding DINO · AerialVG (fine-tuned)Top-1 accuracy: 29.36 -> 29.78No clear effect
add relation-aware grounding (ablation)Grounding DINO · AerialVG (fine-tuned)Top-1 accuracy: 29.36 -> 45.63Improved
add relation-aware grounding (ablation)Grounding DINO · AerialVG (fine-tuned)Top-5 accuracy: 78.87 -> 79.63Improved
add hierarchical cross-attention to relation-aware model (ablation)Grounding DINO + Relation · AerialVG (fine-tuned)Top-1 accuracy: 45.63 -> 50.01Improved
add hierarchical cross-attention to relation-aware model (ablation)Grounding DINO + Relation · AerialVG (fine-tuned)Top-5 accuracy: 79.63 -> 87.00Improved
fine-tune on AerialVG instead of zero-shotGrounding DINO · AerialVGTop-1 accuracy: 11.10 -> 29.36Improved
use AerialVG model instead of Grounding DINOGrounding DINO · RefCOCOg testAccuracy: 87.02 -> 88.04Improved
use AerialVG model instead of Grounding DINOGrounding DINO · RefCOCO valAccuracy: 90.56 -> 90.58No clear effect
use AerialVG model instead of SimVGSimVG · RefCOCO+ valAccuracy: 85.36 -> 82.83Hurt

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