10 papers
Are In-Context Images Worth 10 Dimensions?
Adhemar de Senneville, Xavier Bou, Jérémy Anger +2
There has been significant work on understanding the In-Context Learning capabilities of Large Language Models, especially on the induction circuit. For a few-shot classification t…
Robust RPC Bundle Adjustment for Multi-Date Satellite Imagery with Season-Invariant Correspondences
Roger Marí, Elías Masquil, Xavier Bou +2
Accurate refinement of Rational Polynomial Camera (RPC) models is essential for high-quality satellite image geolocation. In ground control point (GCP)-free multi-view pipelines, t…
Towards Athlete Fatigue Assessment from Association Football Videos
Xavier Bou, Nathan Correger, Alexandre Cloots +7
Fatigue monitoring is central in association football due to its links with injury risk and tactical performance. However, objective fatigue-related indicators are commonly derived…
Unlocking Few-Shot Capabilities in LVLMs via Prompt Conditioning and Head Selection
Adhemar de Senneville, Xavier Bou, Jérémy Anger +2
Current Large Vision Language Models (LVLMs) excel at many zero-shot tasks like image captioning, visual question answering and OCR. However, these same models suffer from poor per…
Remote Sensing Change Detection via Weak Temporal Supervision
Xavier Bou, Elliot Vincent, Gabriele Facciolo +3
Semantic change detection in remote sensing aims to identify land cover changes between bi-temporal image pairs. Progress in this area has been limited by the scarcity of annotated…
Towards Large Scale Geostatistical Methane Monitoring with Part-based Object Detection
Adhemar de Senneville, Xavier Bou, Thibaud Ehret +5
Object detection is one of the main applications of computer vision in remote sensing imagery. Despite its increasing availability, the sheer volume of remote sensing data poses a…
Structure Tensor Representation for Robust Oriented Object Detection
Xavier Bou, Gabriele Facciolo, Rafael Grompone von Gioi +2
Oriented object detection predicts orientation in addition to object location and bounding box. Precisely predicting orientation remains challenging due to angular periodicity, whi…
Exploring Robust Features for Few-Shot Object Detection in Satellite Imagery
Xavier Bou, Gabriele Facciolo, Rafael Grompone von Gioi +2
The goal of this paper is to perform object detection in satellite imagery with only a few examples, thus enabling users to specify any object class with minimal annotation. To thi…
Portraying the Need for Temporal Data in Flood Detection via Sentinel-1
Xavier Bou, Thibaud Ehret, Rafael Grompone von Gioi +1
Identifying flood affected areas in remote sensing data is a critical problem in earth observation to analyze flood impact and drive responses. While a number of methods have been…
Reducing False Alarms in Video Surveillance by Deep Feature Statistical Modeling
Xavier Bou, Aitor Artola, Thibaud Ehret +3
Detecting relevant changes is a fundamental problem of video surveillance. Because of the high variability of data and the difficulty of properly annotating changes, unsupervised m…