Research map / Vision-language and multimodal / Human and embodied modeling
Open-Text Aerial Detection: A Unified Framework For Aerial Visual Grounding And Detection
Guoting Wei, Xia Yuan, Yang Zhou, Haizhao Jing, Yu Liu, Xianbiao Qi, Chunxia Zhao, Haokui Zhang, Rong Xiao
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 attribute-level dense alignment (ablation) | OTA-Det-M · AerialVG | Attr-Align tau=0.5: 14.36 -> 44.23 | Improved |
| add attribute-level dense alignment (ablation) | OTA-Det-M · AerialVG | Attr-Align tau=0.7: 0.47 -> 21.96 | Improved |
| add attribute-level dense alignment (ablation) | OTA-Det-M · AerialVG | Acc@0.5: 54.67 -> 54.94 | No clear effect |
| add decoupled multi-granular head (ablation) | OTA-Det-M · AerialVG | Attr-Align tau=0.5: 39.55 -> 44.23 | Improved |
| add decoupled multi-granular head (ablation) | OTA-Det-M · AerialVG | Attr-Align tau=0.7: 14.88 -> 21.96 | Improved |
| add decoupled multi-granular head (ablation) | OTA-Det-M · AerialVG | Acc@0.5: 54.16 -> 54.94 | Improved |
| add image-level annotation aggregation (ablation) | OTA-Det-M · AerialVG | Attr-Align tau=0.5: 43.21 -> 44.23 | Improved |
| add image-level annotation aggregation (ablation) | OTA-Det-M · AerialVG | Attr-Align tau=0.7: 22.74 -> 21.96 | Hurt |
| add image-level annotation aggregation (ablation) | OTA-Det-M · AerialVG | Acc@0.5: 54.56 -> 54.94 | Improved |
| train LAE-DINO jointly on OTA-Mix with Naive Reformulation | LAE-DINO · DOTA | mAP: 46.8 -> 46.2 | Hurt |
| replace LAE-DINO with OTA-Det-M under task-specific LAE-1M training | OVAD · LAE-80C | mAP: +11.0 mAP | Improved |
| replace AerialVG method with OTA-Det-M | RSVG · AerialVG | Acc@0.5: 50.0 -> 54.9 | Improved |
Closest papers by meaning
- VK-Det: Visual Knowledge Guided Prototype Learning for Open-Vocabulary Aerial Object Detection (AAAI 2026 · similarity 0.91)
- AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations (ICCV 2025 · similarity 0.90)
- GeoViS: Geospatially Rewarded Visual Search for Remote Sensing Visual Grounding (CVPR 2026 · similarity 0.88)
- GroundVLP: Harnessing Zero-Shot Visual Grounding from Vision-Language Pre-training and Open-Vocabulary Object Detection (AAAI 2024 · similarity 0.87)
- SkySense-O: Towards Open-World Remote Sensing Interpretation with Vision-Centric Visual-Language Modeling (CVPR 2025 · similarity 0.86)
- Zero-Shot Aerial Object Detection with Visual Description Regularization (AAAI 2024 · similarity 0.86)
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.
