aimagelab/ReT

[CVPR 2025] Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval

28
/ 100
Experimental

This project helps you find specific documents from a large collection by understanding both text and images. You provide a question or description, possibly with an image, and it returns relevant documents that match your query, even if the information is spread across text and visuals. This is ideal for researchers, analysts, or anyone who needs to accurately retrieve information from complex, multimodal datasets.

No commits in the last 6 months.

Use this if you need to perform highly accurate searches on documents that contain both written text and images, and traditional text-only search engines aren't precise enough.

Not ideal if your retrieval needs are purely text-based or if you are looking for a simple keyword search solution.

multimodal-search document-intelligence information-retrieval research-assist data-mining
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 3 / 25

How are scores calculated?

Stars

34

Forks

1

Language

Python

License

Apache-2.0

Last pushed

Sep 12, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/aimagelab/ReT"

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