Supporting Visual Misinformation Detection Tasks with Similarity Matching

Data Science Bond Israel
Data Science Bond Israel
Public group
Location image of event venue

Details

Join us to a seminar by Hana Matatov sharing her PhD work.
Talk will be held in Hebrew.

10:45 > Gathering
11:00 > Talk starts
12:00 > Estimated finish

Abstract: The increasing spread of misinformation is one of the major problems facing society. In particular, misinformation poses a significant challenge to journalists, as their work increasingly depends on information from web sources and social media. In our work, we focus on the problem of supporting journalists in identifying visual misinformation, for example, images that have been manipulated or taken out of context. Based on informal interviews with journalists, we identified an opportunity to support them in collaboratively detecting visual misinformation.
To this end, we develop computer vision similarity matching process that aims to retrieve previously published versions of a query image, which may have been manipulated. An empirical evaluation of the matching process on a large-scale dataset collected from various sources including social media and news, shows that this process can successfully retrieve a wide range of image manipulations, but that some manipulations remain difficult to detect.

Bio: Hana is a PhD candidate at the Technion- Israel Institute of Technology, under the guidance of Dr. Ofra Amir (Technion) and Dr. Mor Naaman (Cornell Tech). Her main research topics are data science & image retrieval. Her current research focuses on visual misinformation detection, near-duplicates and manipulations detection, image indexing and retrieval, computer vision, social media sources, and collaborative systems.

IMPORTANT
To avoid waiting for your name tag to be prepared, please fill the form below with your name.
https://forms.office.com/Pages/ResponsePage.aspx?id=v4j5cvGGr0GRqy180BHbRzyEYuSGv1NGocFgT5HJhZ5UNDcwR0tDSVQxQ1E5MlpFMUNZSEpMSzlHWi4u