zhuang-li/FactualSceneGraph

[ACL 2023 Findings] FACTUAL dataset, the textual scene graph parser trained on FACTUAL.

37
/ 100
Emerging

This tool helps convert descriptive text into a structured list of objects, their attributes, and how they relate to each other, known as a 'scene graph'. You provide sentences or longer descriptions, and it outputs a concise summary of the key elements and their connections. This is ideal for anyone working with image or video descriptions, content analysis, or generating structured data from natural language.

127 stars.

Use this if you need to extract structured relationships and attributes from textual descriptions, especially for images, videos, or complex narratives.

Not ideal if you're looking for a general-purpose text summarization tool or if your main goal is sentiment analysis.

content-analysis image-captioning video-description data-extraction knowledge-graph-generation
No License No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

127

Forks

12

Language

Python

License

Last pushed

Nov 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/zhuang-li/FactualSceneGraph"

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