shivangi-aneja/COSMOS
[AAAI 2023] COSMOS: Catching Out-of-Context Misinformation using Self Supervised Learning
COSMOS is a comprehensive dataset designed to help identify when images are used with misleading or "out-of-context" captions. It provides a vast collection of images paired with their original and modified news article captions, alongside object detection data. This resource is invaluable for researchers and data scientists focused on developing and evaluating AI models for misinformation detection.
No commits in the last 6 months.
Use this if you are developing or testing machine learning models that need to accurately detect if an image's caption is misleading or taken out of its original context.
Not ideal if you are looking for a pre-built, ready-to-use tool to flag misinformation directly, as this project provides a dataset for model training and evaluation rather than an end-user application.
Stars
44
Forks
14
Language
Python
License
MIT
Category
Last pushed
Dec 16, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/shivangi-aneja/COSMOS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
aaronchong888/DeepFake-Detect
Open-source deepfake detection: train your own model with TensorFlow, Keras & EfficientNet
dessa-oss/DeepFake-Detection
Towards deepfake detection that actually works
abhijithjadhav/Deepfake_detection_using_deep_learning
This projects aims in detection of video deepfakes using deep learning techniques like RestNext...
afsalashyana/FakeImageDetection
Fake Image Detection Using Machine Learning
agusgun/FakeImageDetector
Image Tampering Detection using ELA and CNN