3 papers
cs.LG2025
From Theory to Throughput: CUDA-Optimized APML for Large-Batch 3D Learning
Sasan Sharifipour, Constantino Álvarez Casado, Manuel Lage Cañellas +1
Loss functions are fundamental to learning accurate 3D point cloud models, yet common choices trade geometric fidelity for computational cost. Chamfer Distance is efficient but per…
cs.CV2025
Quality-Aware Framework for Video-Derived Respiratory Signals
Nhi Nguyen, Constantino Álvarez Casado, Le Nguyen +2
Video-based respiratory rate (RR) estimation is often unreliable due to inconsistent signal quality across extraction methods. We present a predictive, quality-aware framework that…
cs.CV2025
LiDAR-based Human Activity Recognition through Laplacian Spectral Analysis
Sasan Sharifipour, Constantino Álvarez Casado, Le Nguyen +4
Human Activity Recognition supports applications in healthcare, manufacturing, and human-machine interaction. LiDAR point clouds offer a privacy-preserving alternative to cameras a…