Human inspired and implicit signal based approaches for deepfake detection

Title: Human inspired and implicit signal based approaches for deepfake detection
Presented by Dr. Abhinav Dhall, Monash University
Date: February 17, 13.00 to 13.50 AEDT

Recording link for those who missed it: link

Abstract: Availability of image and video manipulation software have made it easier to create deepfake videos. In this work, we analyse the effectiveness of human implicit signals for aiding deepfake content analysis. We will present user-centric and content-centric approaches for detecting fake videos based on user gaze, audio and video signals. Furthermore, we will show how to localisatise the manipulation in time.

Bio: Dr. Abhinav Dhall is a Lecturer at Monash University. He is also an Assistant Professor (on leave) at IIT Ropar. His research interests are computer vision, affective computing and deep learning. He received a PhD in computer science from the Australian National University. Later, he pursued Postdoc fellowships at the University of Waterloo, Canada and the University of Canberra, Australia. His research has been recognized by awards such as the best student paper honorable mention award at IEEE AFGR 2013 and the best doctoral consortium paper award at ACM ICMR 2013.