The growing accessibility of Generative AI based image and video manipulation tools has made the creation of deepfakes easier. This poses significant challenges for content verification and can spread misinformation. In this talk, we explore multimodal approaches that are inspired from user behavior for detecting and localizing manipulations in time. Our research draws on user studies, including those focusing on multicultural deepfakes, which provide insights into how different audiences perceive and interact with manipulated media. We discuss the findings from the ACM Multimedia 2024 One Million Deepfakes Detection benchmark. These insights give directions for future works in the area of deepfakes analysis.
Post Talk Link: Click Here
Passcode: R8&c&Mu0
Abhinav Dhall is an Associate Professor (Reader) of Computer Science at Flinders University, Australia. He has previously worked at Monash University and Indian Institute of Technology Ropar. He received a PhD in Computer Science from the Australian National University. His research focuses on affective computing and human-centered computing. His work has received several awards, including the Ten-Year Technical Impact Runner-Up at ACM ICMI 2023, NASSCOM Lab2Market 2021 winners, and best paper awards such as the Best Student Paper Honorable Mention at FG 2024, Best Doctoral Consortium Paper Award at ACM ICMR 2013, and Best Paper Nomination Award at IEEE ICME 2012. He is also an Associate Editor for IEEE Transactions on Affective Computing.
Read More
Read More