P
Pavel Korshunov
Researcher at Idiap Research Institute
Publications - 89
Citations - 2683
Pavel Korshunov is an academic researcher from Idiap Research Institute. The author has contributed to research in topics: JPEG & Privacy software. The author has an hindex of 30, co-authored 84 publications receiving 2009 citations. Previous affiliations of Pavel Korshunov include École Polytechnique Fédérale de Lausanne & École Normale Supérieure.
Papers
More filters
Posted Content
DeepFakes: a New Threat to Face Recognition? Assessment and Detection
Pavel Korshunov,Sébastien Marcel +1 more
TL;DR: This paper presents the first publicly available set of Deepfake videos generated from videos of VidTIMIT database, and demonstrates that GAN-generated Deep fake videos are challenging for both face recognition systems and existing detection methods.
Proceedings ArticleDOI
Pyannote.Audio: Neural Building Blocks for Speaker Diarization
Hervé Bredin,Ruiqing Yin,Juan Manuel Coria,Gregory Gelly,Pavel Korshunov,Marvin Lavechin,Diego Fustes,Hadrien Titeux,Wassim Bouaziz,Marie-Philippe Gill +9 more
TL;DR: This work introduces pyannote.audio, an open-source toolkit written in Python for speaker diarization, which provides a set of trainable end-to-end neural building blocks that can be combined and jointly optimized to build speaker darization pipelines.
Proceedings ArticleDOI
Using warping for privacy protection in video surveillance
Pavel Korshunov,Touradj Ebrahimi +1 more
TL;DR: This paper proposes an algorithm based on well-known warping techniques (common for animation and artistic purposes) to obfuscate faces in video surveillance, aiming to overcome shortcomings in tools for protection of visual privacy.
Proceedings ArticleDOI
Using face morphing to protect privacy
Pavel Korshunov,Touradj Ebrahimi +1 more
TL;DR: This paper proposes a morphing-based privacy protection method and focuses on its robustness, reversibility, and security properties and demonstrates that morphed faces retain the likeness of a face, while making them unrecognizable, which ensures the protection of privacy.
Proceedings ArticleDOI
Vulnerability assessment and detection of Deepfake videos
Pavel Korshunov,Sébastien Marcel +1 more
TL;DR: This paper presents the first publicly available set of Deepfake videos generated from videos of VidTIMIT database, and demonstrates that GAN-generated Deep fake videos are challenging for both face recognition systems and existing detection methods.