Research map / Vision-language and multimodal / Cross-modal learning
MMVIP: A Visible-infrared Paired Dataset for Multi-weather Marine Vision
Yunpeng Yin, Lihan Wang, Zhaoshen He, Xinqiang He, Xingming Liao, Zhuowei Wang, Lianglun Cheng
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 |
|---|---|---|---|
| use fine-tuned MINIMA with RoMa (dense matching) instead of sparse or semi-dense matchers | visible-infrared registration · MMVIP registration | MSE / SSIM: MSE 0.0039, SSIM 0.8822 (best of nine methods) | Improved |
| use dense matching instead of sparse matching in terms of runtime | registration time · MMVIP registration | time (ms): MINIMA_LG 480.8 -> RoMa 5042.6 | Hurt |
| switch from visible to infrared images for ship detection | YOLO11 · MMVIP ship detection | mAP@0.5:0.95: 0.754 -> 0.590 | Hurt |
| switch from visible to infrared images for buoy detection | YOLO11 · MMVIP buoy detection | mAP@0.5: 0.795 -> 0.599 | Hurt |
| switch from visible to infrared images for buoy precision | YOLO11 · MMVIP buoy detection | precision: 0.874 -> 0.889 | Improved |
| low-light, night and foggy conditions for registration | registration algorithms · MMVIP registration | qualitative registration quality | Hurt |
| rainy weather for infrared detection | YOLO11 infrared · MMVIP detection | qualitative detection | Hurt |
Closest papers by meaning
- Neptune-X: Active X-to-Maritime Generation for Universal Maritime Object Detection (NeurIPS 2025 · similarity 0.83)
- NAUTILUS: A Large Multimodal Model for Underwater Scene Understanding (NeurIPS 2025 · similarity 0.82)
- MFogHub: Bridging Multi-Regional and Multi-Satellite Data for Global Marine Fog Detection and Forecasting (CVPR 2025 · similarity 0.82)
- DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Response (NeurIPS 2025 · similarity 0.81)
- WeatherPrompt: Multi-modality Representation Learning for All-Weather Drone Visual Geo-Localization (NeurIPS 2025 · similarity 0.81)
- Bridging Remote Sensors with Multisensor Geospatial Foundation Models (CVPR 2024 · similarity 0.81)
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.
