Leveraging Model Soups to Classify Intangible Cultural Heritage Images from the Mekong Delta Paper • 2603.02181 • Published 1 day ago
[dataset] embeddings-and-retrieval-learning Collection Datasets for training embeddings and retrieval models • 2 items • Updated 4 days ago
ViCLIP-OT: The First Foundation Vision-Language Model for Vietnamese Image-Text Retrieval with Optimal Transport Paper • 2602.22678 • Published 6 days ago