Patrick Le Callet

UFFM achieves superior pseudo-label quality by harmonizing labeled and unlabeled data training, challenging the dominance of manual labeling in semi-supervised learning.

GAFIC achieves unprecedented accuracy in image cropping by fusing local and global features, outperforming traditional methods that compromise pixel integrity.

A new benchmark reveals that existing defect detection methods falter in novel production scenarios, highlighting the urgent need for severity-aware assessments in manufacturing.

Mapping MOS to JND for high-quality video is harder than expected: confidence intervals overlap, and statistical power is low.