FuxiaoLiu/VisualNews-Repository
[EMNLP'21] Visual News: Benchmark and Challenges in News Image Captioning
This project helps news organizations, content creators, or media analysts automatically generate descriptive captions for news images. It takes a news image, along with its related news article, and outputs a detailed caption that highlights important people, locations, and events mentioned in the text. This is designed for researchers or practitioners who want to improve the accessibility and searchability of visual news content.
105 stars. No commits in the last 6 months.
Use this if you need to automatically create informative captions for a large volume of news images, integrating both visual content and accompanying article text.
Not ideal if you only need general image captions without specific emphasis on news entities or if your images lack associated news articles.
Stars
105
Forks
9
Language
Jupyter Notebook
License
—
Category
Last pushed
Jul 18, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/FuxiaoLiu/VisualNews-Repository"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
label-sleuth/label-sleuth
Open source no-code system for text annotation and building of text classifiers
CVHub520/X-AnyLabeling-Server
A Simple, Lightweight, and Extensible Serving Framework for X-AnyLabeling
antoninodimaggio/Hugging-Captions
Generate realistic Instagram captions using transformers 🤗
VisioSphereAI/labelvim
This is a python based standalone image annotation tool designed for tasks such as image...
hem9984/Dataset-label
This will allow you to choose your labels, and then label every image in a zip file or text line...