subho406/OmniNet

Official Pytorch implementation of "OmniNet: A unified architecture for multi-modal multi-task learning" | Authors: Subhojeet Pramanik, Priyanka Agrawal, Aman Hussain

36
/ 100
Emerging

This project offers a single solution for processing various types of real-world information like text, images, and videos. It can analyze different data inputs and provide outputs for tasks such as describing images, answering questions about visuals, and recognizing activities in videos. Anyone working with diverse media content for analysis or intelligent system development would find this tool useful.

513 stars. No commits in the last 6 months.

Use this if you need a single system to analyze different types of data like text, images, and videos, and perform multiple related tasks simultaneously.

Not ideal if you only work with a single data type (e.g., only text) or only need to perform one specific analysis task.

multi-modal analysis content understanding visual question answering video activity recognition image captioning
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 18 / 25

How are scores calculated?

Stars

513

Forks

59

Language

Python

License

Last pushed

Oct 31, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/subho406/OmniNet"

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