2 papers
cs.CV2026
Hyper3-CLIP: Hierarchy-Conditioned Hyperbolic Vision-Language Training
Matin Mahmood, Antonio Rueda-Toicen, Mohamed ElBassat +3
CLIP-like vision-language models (VLMs) trained with contrastive objectives learn strong global image-text representations, but their Euclidean embeddings and global pooling fail t…
cs.CV2026
Calibrated Similarity and Graph Clustering for Open-Set Animal Re-Identification
Mohamed ElBassat, Seifeldin Elkerdany, Mohamed ElBialy +5
AnimalCLEF26 addresses discovery-oriented animal re-identification, where systems must both attach query images to known individuals and discover unseen individuals by clustering t…