Schedule
Invited Speakers
- Alexei A. Efros, University of California Berkeley
- Matt Turek, DARPA
- Luisa Verdoliva, University Federico II Naples [Slides]
- Tom Van de Weghe, JSK Stanford Fellow & VRT Correspondent [Slides]
- Pawel Korus, New York University [Slides]
- Aviv Ovadya, Thoughtful Technology Project [Slides]
- Scott McCloseky [Slides]
Time-Table
Saturday 15th June @ Room 104C
9:00-9:10 Welcome remarks
9:10-9:40 Invited talk: Alexei Efros (University of California Berkeley)
9:40-10:10 Invited Talk: Matt Turek (DARPA)
10:10-10:30 Contributed Talk: Limits of Deepfake Detection: A Robust Estimation Viewpoint
10:30-11:30 Poster session 1 / Coffee break
11:30-12:00 Invited Talk: Pawel Korus (New York University)
12:00-12:15 Contributed Talk: We Need No Pixels: Video Manipulation Detection Using Stream Descriptors
12:15-12:30: Contributed Talk: A Utility-Preserving GAN for Face Obscuration
12:30-14:00 Lunch break
14:00-14:30 Invited Talk: Luisa Verdoliva (University Federico II Naples)
14:30-14:45 Contributed Talk: Tampered Speaker Inconsistency Detection with Phonetically Aware Audio-visual Features
14:45-15:00 Contributed Talk: Measuring the Effectiveness of Voice Conversion on Speaker Identification and Automatic Speech Recognition Systems
15:00-15:45 Poster session 2 / Coffee break
15:45-16:15 CVPR MediaForensics Workshop Preview
16:15-16:45 Invited Talk: Tom Van de Weghe (JSK Stanford Fellow & VRT Correspondent)
16:45-17:00 Invited Talk: Aviv Ovadya (Thoughtful Technology Project)
17:00-18:00 Panel Discussion. Moderator: Delip Rao (AI Foundation).
Panel: Luisa Verdoliva, Pawel Korus, Tom Van de Weghe, Aviv Ovadya
Accepted Papers
- Limits of Deepfake Detection: A Robust Estimation Viewpoint, Sakshi Agarwal, Lav R. Varshney [Paper] [Slides] [Poster]
- We Need No Pixels: Video Manipulation Detection Using Stream Descriptors, David Güera, Sriram Baireddy, Paolo Bestagini, Stefano Tubaro,Edward J. Delp [Paper] [Slides] [Poster]
- A Utility-Preserving GAN for Face Obscuration, Hanxiang Hao, David Güera, Amy R. Reibman, Edward J. Delp [Paper] [Slides] [Poster]
- Tampered Speaker Inconsistency Detection with Phonetically Aware Audio-visual Features, Pavel Korshunov, Michael Halstead, Diego Castan, Martin Graciarena, Mitchell McLaren, Brian Burns, Aaron Lawson, Sebastien Marcel [Paper] [Slides] [Poster]
- Measuring the Effectiveness of Voice Conversion on Speaker Identification and Automatic Speech Recognition Systems, Gokce Keskin, Tyler Lee, Cory Stephenson, Oguz H. Elibol [Paper] [Slides] [Poster]
Recordings
- The recordings can be found here: https://slideslive.com/icml/icml-2019-room-104-c-live
- Also checkout the live tweets by Giorgio Patrini (https://twitter.com/GiorgioPatrini)