Research map / Vision-language and multimodal / Cross-modal learning
Learning Better UAV-Based Cross-View Object Geo-Localization from Multi-Modal Prompts: MoP-UAV Benchmark and MoPT Framework
Xiaohan Zhang, Zhangkai Shen, Si-Yuan Cao, Xiaokai Bai, Yiming Li, Zheheng Han, Zhe Wu, Qi Ming, Hui-Liang Shen
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 |
|---|---|---|---|
| train with multi-modal prompts instead of single-modal (ablation) | MoPT · MoP-UAV test (box inference) | Acc@50: 0.2082 -> 0.4074 | Improved |
| train with multi-modal prompts instead of text only (ablation) | MoPT · MoP-UAV test (text inference) | Acc@25 vs Acc@50: Acc@25 0.6203 -> 0.6106; Acc@50 0.3574 -> 0.4052 | Mixed |
| add RefCOCOg pre-training (ablation) | MoPT · MoP-UAV test (text inference) | Acc@50: 0.2854 -> 0.4052 | Improved |
| add cross-view contrastive loss LToken (ablation) | MoPT · MoP-UAV test (box+point inference) | Acc@50: 0.2945 -> 0.4051 | Improved |
| add LToken (ablation) | MoPT · MoP-UAV test (single-modality inference) | Acc@50: text 0.4189 -> 0.4052 | Mixed |
| combine all three prompt modalities at inference (ablation) | MoPT · MoP-UAV test | Acc@50: 0.4052 (text) -> 0.4436 | Improved |
| use MoPT instead of DetGeo/OCGNet with point prompts | point-prompt localization · MoP-UAV test (point prompt only) | Acc@50: 0.3349 -> 0.4051 | Improved |
Closest papers by meaning
- Weather-Robust Cross-View Geo-Localization via Prototype-Based Semantic Part Discovery (NeurIPS 2026 · similarity 0.86)
- WeatherPrompt: Multi-modality Representation Learning for All-Weather Drone Visual Geo-Localization (NeurIPS 2025 · similarity 0.86)
- Game4Loc: A UAV Geo-Localization Benchmark from Game Data (AAAI 2025 · similarity 0.86)
- Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology (ICLR 2025 · similarity 0.85)
- SatNav: A Scalable Benchmark for Long-Horizon UAV Vision-Language Navigation from Satellite Imagery (NeurIPS 2026 · similarity 0.85)
- GOMAA-Geo: GOal Modality Agnostic Active Geo-localization (NeurIPS 2024 · similarity 0.84)
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.
