subho406/OmniNet
Official Pytorch implementation of "OmniNet: A unified architecture for multi-modal multi-task learning" | Authors: Subhojeet Pramanik, Priyanka Agrawal, Aman Hussain
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.
Stars
513
Forks
59
Language
Python
License
—
Category
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.
Higher-rated alternatives
open-mmlab/mmpretrain
OpenMMLab Pre-training Toolbox and Benchmark
facebookresearch/mmf
A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
HuaizhengZhang/Awsome-Deep-Learning-for-Video-Analysis
Papers, code and datasets about deep learning and multi-modal learning for video analysis
KaiyangZhou/pytorch-vsumm-reinforce
Unsupervised video summarization with deep reinforcement learning (AAAI'18)
adambielski/siamese-triplet
Siamese and triplet networks with online pair/triplet mining in PyTorch