cene555/ruCLIP-SB

RuCLIP-SB (Russian Contrastive Language–Image Pretraining SWIN-BERT) is a multimodal model for obtaining images and text similarities and rearranging captions and pictures. Unlike other versions of the model we use BERT for text encoder and SWIN transformer for image encoder.

35
/ 100
Emerging

This tool helps you analyze and organize visual content with accompanying text descriptions in Russian. You provide images and their Russian captions, and it calculates how similar each image is to a given text, or how well captions match pictures. This is useful for anyone working with large collections of Russian-language images and descriptions, such as content managers, archivists, or e-commerce specialists.

No commits in the last 6 months.

Use this if you need to quickly find Russian images based on text descriptions or sort Russian image-caption pairs by relevance.

Not ideal if your primary need is for non-Russian language content analysis or if you require fine-grained object detection within images.

content-management image-search russian-language-processing media-asset-management data-organization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

14

Forks

3

Language

Jupyter Notebook

License

MIT

Last pushed

Jan 25, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/cene555/ruCLIP-SB"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.