ViCLIP-OT - a minhnguyent546 Collection

minhnguyent546 's Collections

cotu-legal-retriever

[model] Machine Translation Models

[dataset] image-text datasets

[dataset] embeddings-and-retrieval-learning

[dataset] text-generation

[model] embeddings

ViCLIP-OT

updated Mar 1

ViCLIP-OT: The First Foundation Vision-Language Model for Vietnamese Image–Text Retrieval with Optimal Transport

minhnguyent546/ViCLIP-OT

Feature Extraction • 0.2B • Updated Mar 2 • 10 • 2

Note Model trained with CLIP + SIGROT objective
minhnguyent546/ViSigLIP-OT

Feature Extraction • 0.2B • Updated Mar 2 • 4 • 1

Note Model trained with SigLIP + SIGROT objective
minhnguyent546/ViCLIP-OT-checkpoints

Feature Extraction • Updated Mar 16

Note Checkpoints and other artifacts for ViCLIP-OT