2 papers
cs.CV2025
From Words to Wavelengths: VLMs for Few-Shot Multispectral Object Detection
Manuel Nkegoum, Minh-Tan Pham, Élisa Fromont +2
Multispectral object detection is critical for safety-sensitive applications such as autonomous driving and surveillance, where robust perception under diverse illumination conditi…
cs.CV2025
FSMODNet: A Closer Look at Few-Shot Detection in Multispectral Data
Manuel Nkegoum, Minh-Tan Pham, Élisa Fromont +2
Few-shot multispectral object detection (FSMOD) addresses the challenge of detecting objects across visible and thermal modalities with minimal annotated data. In this paper, we ex…