jshilong/GPT4RoI
(ECCVW 2025)GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest
This project helps anyone who needs to understand specific details within images by allowing you to point out regions of interest and ask questions about them. You input an image and highlight specific areas, then ask questions using natural language. The output is a descriptive answer focusing solely on the selected region(s), making it ideal for visual content analysis. This is for professionals like image analysts, researchers, or content moderators.
551 stars. No commits in the last 6 months.
Use this if you need to ask precise, natural language questions about specific parts of an image and get targeted answers.
Not ideal if you need a general image caption or overall scene description without specifying regions of interest.
Stars
551
Forks
28
Language
Python
License
—
Category
Last pushed
Jun 03, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/jshilong/GPT4RoI"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
KimMeen/Time-LLM
[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming...
om-ai-lab/VLM-R1
Solve Visual Understanding with Reinforced VLMs
bytedance/SALMONN
SALMONN family: A suite of advanced multi-modal LLMs
NVlabs/OmniVinci
OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.
fixie-ai/ultravox
A fast multimodal LLM for real-time voice