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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add hierarchical cross-attention (ablation) | Grounding DINO · AerialVG (fine-tuned) | Top-5 accuracy: 78.87 -> 82.32 | Improved |
| add hierarchical cross-attention (ablation) | Grounding DINO · AerialVG (fine-tuned) | Top-1 accuracy: 29.36 -> 29.78 | No clear effect |
| add relation-aware grounding (ablation) | Grounding DINO · AerialVG (fine-tuned) | Top-1 accuracy: 29.36 -> 45.63 | Improved |
| add relation-aware grounding (ablation) | Grounding DINO · AerialVG (fine-tuned) | Top-5 accuracy: 78.87 -> 79.63 | Improved |
| add hierarchical cross-attention to relation-aware model (ablation) | Grounding DINO + Relation · AerialVG (fine-tuned) | Top-1 accuracy: 45.63 -> 50.01 | Improved |
| add hierarchical cross-attention to relation-aware model (ablation) | Grounding DINO + Relation · AerialVG (fine-tuned) | Top-5 accuracy: 79.63 -> 87.00 | Improved |
| fine-tune on AerialVG instead of zero-shot | Grounding DINO · AerialVG | Top-1 accuracy: 11.10 -> 29.36 | Improved |
| use AerialVG model instead of Grounding DINO | Grounding DINO · RefCOCOg test | Accuracy: 87.02 -> 88.04 | Improved |
| use AerialVG model instead of Grounding DINO | Grounding DINO · RefCOCO val | Accuracy: 90.56 -> 90.58 | No clear effect |
| use AerialVG model instead of SimVG | SimVG · RefCOCO+ val | Accuracy: 85.36 -> 82.83 | Hurt |
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.
- Dynamic-MDETR — Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding (TPAMI 2023) · better on 2 of 2 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
- GroundVLP: Harnessing Zero-Shot Visual Grounding from Vision-Language Pre-training and Open-Vocabulary Object Detection (AAAI 2024 · similarity 0.88)
- From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes (NeurIPS 2025 · similarity 0.88)
- GeoViS: Geospatially Rewarded Visual Search for Remote Sensing Visual Grounding (CVPR 2026 · similarity 0.87)
- SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding (NeurIPS 2025 · similarity 0.87)
- SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding (CVPR 2025 · similarity 0.87)
- Investigating Compositional Challenges in Vision-Language Models for Visual Grounding (CVPR 2024 · similarity 0.87)
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.
