dinhanhx's picture

dinhanhx

dinhanhx

·

dinhanhx

AI & ML interests

Vision Language

Recent Activity

upvoted a paper about 9 hours ago

NV-Retriever: Improving text embedding models with effective hard-negative mining

upvoted a collection 7 days ago

liked a model 8 days ago

nvidia/llama-nemotron-rerank-1b-v2

View all activity

Organizations

Collections 2

spaces 3

TorchCAM

Class activation maps for your PyTorch models (CAM, Grad-CAM

Nemoretriever Page Elements

Identify and extract elements from document pages

Velvet

Generate captions and answers based on images and text

models 0

None public yet

datasets 10

dinhanhx/google-wit-vi

Updated Nov 29, 2023 • 214 • 6

dinhanhx/coco-2017-vi

Preview • Updated Nov 9, 2023 • 85

dinhanhx/OK-VQA-multilang

Viewer • Updated Sep 21, 2023 • 19.7k • 154

dinhanhx/TextVQA-vi

Viewer • Updated Sep 21, 2023 • 55.5k • 149

dinhanhx/VQAv2-vi

Preview • Updated Sep 21, 2023 • 75

dinhanhx/evjvqa

Viewer • Updated Jun 24, 2023 • 3.77k • 69

dinhanhx/TextCaps-vi

Preview • Updated Jun 17, 2023 • 34

dinhanhx/cc_sbu_align_multilang

Viewer • Updated Jun 7, 2023 • 3.44k • 622

dinhanhx/crossmodal-3600

Viewer • Updated Jun 6, 2023 • 3.6k • 1.12k • 6

dinhanhx/gcc-vi

Preview • Updated Jun 6, 2023 • 35 • 1