Projects
Image contextualization for fact-checking
🗒️Recap
Most research in multimodal automated fact-checking focuses on predicting the veracity of multimodal claims. However, in real-world fact-checking practices, a particular attention is also given to identifying the accurate context information about the multimodal content. For example, identifying the true location, date, and event of the image or video.
In this project, we assemble datasets and propose methods to assist human fact-checkers in predicting the true context of multimodal misinformation content.