02 / PUBLICATIONS
Peer-reviewed work on multimodal detection and efficient computer vision, alongside my doctoral thesis.
5 publications
ICMV 2025 · SPIE / Conference paper
MEFA-MS revisits early fusion with a U-Net architecture and spatial and channel attention. It aims to preserve detection quality while reducing inference cost.
Key contribution : An attention-based encoder-decoder, evaluated against MEFA on DENSE with RT-DETR.
Université Grenoble Alpes / Doctoral thesis
My doctoral research investigates early multimodal image fusion for pedestrian and vehicle detection, within a CIFRE collaboration between Orange and LIG.
Key contribution : Connecting multimodal perception, attention mechanisms and object detection.
ICCV Workshops 2025 · MIRA / Conference paper
FMCAF combines frequency-domain filtering and cross-attention to fuse RGB and infrared images. It is evaluated on low-light pedestrian detection and aerial vehicle detection.
Key contribution : Fusion studied in two different settings: LLVIP and VEDAI.
VISAPP 2025 / Conference paper
MEFA uses attention to fuse visible, infrared and LiDAR images before detection. It is studied with YOLOv8 and RT-DETR, including rainy and foggy conditions.
Key contribution : An upstream fusion module that works with existing single-modality detectors.
EGC 2024 / Conference paper
This conference contribution focuses on the energy footprint of YOLOv8 for pedestrian and vehicle detection.
Key contribution : Bringing energy use into the evaluation of object detectors.
No publications match your search. Try another term or year.
LET’S CONNECT
For scientific and technical discussions about computer vision and multimodal perception.
Send me an email