kuanghuei/SCAN

PyTorch source code for "Stacked Cross Attention for Image-Text Matching" (ECCV 2018)

50
/ 100
Established

This project helps researchers and practitioners in computer vision and natural language processing to match images with relevant text descriptions, or vice versa. It takes a collection of images and corresponding text captions as input, and outputs models capable of accurately retrieving descriptions for a given image, or images for a given description. It is designed for those working with large datasets of multimedia content.

579 stars. No commits in the last 6 months.

Use this if you need to develop or evaluate state-of-the-art models for finding the most relevant images for a text query or the most relevant text description for an image.

Not ideal if you are looking for an out-of-the-box solution without deep learning expertise or are working with non-image/text data.

computer-vision natural-language-processing image-retrieval text-retrieval multimedia-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

579

Forks

118

Language

Python

License

Apache-2.0

Last pushed

May 18, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kuanghuei/SCAN"

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