emerisly/EDIS

Entity-Driven Image Search over Multimodal Web Content (EMNLP 2023)

27
/ 100
Experimental

This project offers a unique collection of 1 million news-related web images, each with a detailed text description, specifically designed for testing and improving image search systems. It helps researchers evaluate how well their algorithms can find relevant images from vast datasets using text queries. The primary users are researchers and developers working on advanced image retrieval and multimodal search technologies.

No commits in the last 6 months.

Use this if you are developing or evaluating advanced image search algorithms, especially for news content, and need a challenging, large-scale dataset with rich entity information.

Not ideal if you are looking for an out-of-the-box image search application, or if your focus is on general object recognition rather than complex cross-modal retrieval from news articles.

information-retrieval image-search-evaluation multimodal-data-analysis news-media-research computer-vision-benchmarking
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

26

Forks

1

Language

Python

License

Apache-2.0

Last pushed

Dec 02, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/emerisly/EDIS"

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