8 papers
Le MuMo JEPA: Multi-Modal Self-Supervised Representation Learning with Learnable Fusion Tokens
Ciem Cornelissen, Sam Leroux, Pieter Simoens
Self-supervised learning has emerged as a powerful paradigm for learning visual representations without manual annotations, yet most methods still operate on a single modality and…
Efficient On-Board Processing of Oblique UAV Video for Rapid Flood Extent Mapping
Vishisht Sharma, Sam Leroux, Lisa Landuyt +2
Effective disaster response relies on rapid disaster response, where oblique aerial video is the primary modality for initial scouting due to its ability to maximize spatial covera…
Privacy-Preserving Computer Vision for Industry: Three Case Studies in Human-Centric Manufacturing
Sander De Coninck, Emilio Gamba, Bart Van Doninck +3
The adoption of AI-powered computer vision in industry is often constrained by the need to balance operational utility with worker privacy. Building on our previously proposed priv…
In-Field Mapping of Grape Yield and Quality with Illumination-Invariant Deep Learning
Ciem Cornelissen, Sander De Coninck, Axel Willekens +2
This paper presents an end-to-end, IoT-enabled robotic system for the non-destructive, real-time, and spatially-resolved mapping of grape yield and quality (Brix, Acidity) in viney…
Mitigating Bias Using Model-Agnostic Data Attribution
Sander De Coninck, Sam Leroux, Pieter Simoens
Mitigating bias in machine learning models is a critical endeavor for ensuring fairness and equity. In this paper, we propose a novel approach to address bias by leveraging pixel i…
Enabling Privacy-Aware AI-Based Ergonomic Analysis
Sander De Coninck, Emilio Gamba, Bart Van Doninck +3
Musculoskeletal disorders (MSDs) are a leading cause of injury and productivity loss in the manufacturing industry, incurring substantial economic costs. Ergonomic assessments can…