37 citations · 160 across the 27 of their papers we have counts for
3 papers · 1 filter
RUMPL: Ray-Based Transformers for Universal Multi-View 2D to 3D Human Pose Lifting
Seyed Abolfazl Ghasemzadeh, Alexandre Alahi, Christophe De Vleeschouwer
Estimating 3D human poses from 2D images remains challenging due to occlusions and projective ambiguity. Multi-view learning-based approaches mitigate these issues but often fail t…
Few-Shot Adaptation Benchmark for Remote Sensing Vision-Language Models
Karim El Khoury, Maxime Zanella, Christophe De Vleeschouwer +1
Remote Sensing Vision-Language Models (RSVLMs) have shown remarkable potential thanks to large-scale pretraining, achieving strong zero-shot performance on various tasks. However,…
Data-Efficient Stream-Based Active Distillation for Scalable Edge Model Deployment
Dani Manjah, Tim Bary, Benoît Gérin +2
Edge camera-based systems are continuously expanding, facing ever-evolving environments that require regular model updates. In practice, complex teacher models are run on a central…