Raphaël Delécluse
PulseAugur coverage of Raphaël Delécluse — every cluster mentioning Raphaël Delécluse across labs, papers, and developer communities, ranked by signal.
-
Privacy-preserving person re-identification uses depth images and Transformers
Researchers have developed a novel person re-identification system that prioritizes privacy by utilizing depth images instead of traditional RGB data. This method employs a Transformer encoder to process temporal sequen…
-
New Transformer Model Enhances Multi-Pedestrian Trajectory Prediction
Researchers have developed a novel Three-Step Hierarchical Transformer model designed to improve multi-pedestrian trajectory prediction. This new architecture effectively separates temporal encoding, multimodal fusion, …
-
ICPR 2026 competition launches privacy-preserving person re-identification benchmark
A new competition, the ICPR 2026 TVRID, has been introduced for privacy-preserving person re-identification using top-view RGB-Depth cameras. The competition features a dataset with 86 identities captured by four synchr…