P. Korshunov

Most-cited papers

DeepFakes: a New Threat to Face Recognition? Assessment and Detection
P. Korshunov, S. Marcel
2018arXiv.org834 citations
Semantic Scholar
Pyannote.Audio: Neural Building Blocks for Speaker Diarization
H. Bredin, Ruiqing Yin, Juan Manuel Coria, G. Gelly +6 more
2019IEEE International Conference on Acoustics, Speech, and Signal Processing535 citations Open access
Semantic Scholar
Vulnerability assessment and detection of Deepfake videos
P. Korshunov, S. Marcel
2019International Conference on Biometrics141 citations Open access
Semantic Scholar
Using face morphing to protect privacy
P. Korshunov, T. Ebrahimi
20132013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance109 citations Open access
Semantic Scholar
Privacy in mini-drone based video surveillance
Margherita Bonetto, P. Korshunov, G. Ramponi, T. Ebrahimi
2015IEEE International Conference on Automatic Face & Gesture Recognition104 citations Open access
Semantic Scholar
Using warping for privacy protection in video surveillance
P. Korshunov, T. Ebrahimi
2013International Conference on Digital Signal Processing102 citations Open access
Semantic Scholar
Speaker Inconsistency Detection in Tampered Video
P. Korshunov, S. Marcel
2018European Signal Processing Conference90 citations Open access
Semantic Scholar
Overview of BTAS 2016 speaker anti-spoofing competition
P. Korshunov, S. Marcel, H. Muckenhirn, A. Gonçalves +12 more
20162016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems (BTAS)83 citations Open access
Semantic Scholar
Overview and evaluation of the JPEG XT HDR image compression standard
A. Artusi, Rafał K. Mantiuk, T. Richter, Philippe Hanhart +4 more
2019Journal of Real-Time Image Processing81 citations Open access
Semantic Scholar
Visual attention in LDR and HDR images
Hiromi Nemoto, P. Korshunov, Philippe Hanhart, T. Ebrahimi
201580 citations
Semantic Scholar
Best Practices and Recommendations for Crowdsourced QoE - Lessons learned from the Qualinet Task Force Crowdsourcing
T. Hossfeld, Matthias Hirth, J. Redi, F. Mazza +6 more
201477 citations
Semantic Scholar
Deepfake detection: humans vs. machines
P. Korshunov, S. Marcel
2020arXiv.org75 citations
Semantic Scholar
Continuously Reproducing Toolchains in Pattern Recognition and Machine Learning Experiments
A. Anjos, Manuel Günther, Tiago de Freitas Pereira, P. Korshunov +2 more
2017International Conference on Machine Learning72 citations
Semantic Scholar
Vulnerability Analysis of Face Morphing Attacks from Landmarks and Generative Adversarial Networks
Eklavya Sarkar, P. Korshunov, Laurent Colbois, S. Marcel
2020arXiv.org71 citations
Semantic Scholar
Video quality for face detection, recognition, and tracking
P. Korshunov, Wei Tsang Ooi
2011TOMCCAP71 citations Open access
Semantic Scholar
Crowdsourcing-based multimedia subjective evaluations: a case study on image recognizability and aesthetic appeal
J. Redi, T. Hossfeld, P. Korshunov, F. Mazza +2 more
2013CrowdMM '1368 citations Open access
Semantic Scholar
Are GAN-based morphs threatening face recognition?
Eklavya Sarkar, P. Korshunov, Laurent Colbois, S. Marcel
2022IEEE International Conference on Acoustics, Speech, and Signal Processing64 citations Open access
Semantic Scholar
Subjective quality assessment database of HDR images compressed with JPEG XT
P. Korshunov, Philippe Hanhart, T. Richter, A. Artusi +2 more
2015International Workshop on Quality of Multimedia Experience64 citations Open access
Semantic Scholar
Privacy-preserving photo sharing based on a secure JPEG
Lin Yuan, P. Korshunov, T. Ebrahimi
2015Conference on Computer Communications Workshops59 citations Open access
Semantic Scholar
Subjective study of privacy filters in video surveillance
P. Korshunov, Claudia Araimo, Francesca De Simone, Carmelo Velardo +2 more
2012IEEE International Workshop on Multimedia Signal Processing57 citations Open access
Semantic Scholar
Crowdsourcing approach for evaluation of privacy filters in video surveillance
P. Korshunov, Shuting Cai, T. Ebrahimi
2012CrowdMM '1256 citations Open access
Semantic Scholar
Secure JPEG scrambling enabling privacy in photo sharing
Lin Yuan, P. Korshunov, T. Ebrahimi
2015IEEE International Conference on Automatic Face & Gesture Recognition54 citations Open access
Semantic Scholar
Framework for objective evaluation of privacy filters
P. Korshunov, A. Melle, J. Dugelay, T. Ebrahimi
2013Optics & Photonics - Optical Engineering + Applications51 citations Open access
Semantic Scholar
Critical video quality for distributed automated video surveillance
P. Korshunov, Wei Tsang Ooi
2005ACM Multimedia48 citations Open access
Semantic Scholar
Survey of web-based crowdsourcing frameworks for subjective quality assessment
Tobias Hoβfeld, Matthias Hirth, P. Korshunov, Philippe Hanhart +3 more
2014IEEE International Workshop on Multimedia Signal Processing47 citations Open access
Semantic Scholar
Cross-Database Evaluation of Audio-Based Spoofing Detection Systems
P. Korshunov, S. Marcel
2016Interspeech46 citations Open access
Semantic Scholar
Long-Term Spectral Statistics for Voice Presentation Attack Detection
Hannah Muckenhirn, P. Korshunov, M. Magimai.-Doss, S. Marcel
2017IEEE/ACM Transactions on Audio Speech and Language Processing45 citations Open access
Semantic Scholar
JPEG XT: A Compression Standard for HDR and WCG Images [Standards in a Nutshell]
A. Artusi, Rafał K. Mantiuk, T. Richter, P. Korshunov +3 more
2016IEEE Signal Processing Magazine44 citations Open access
Semantic Scholar
PEViD: privacy evaluation video dataset
P. Korshunov, T. Ebrahimi
2013Optics & Photonics - Optical Engineering + Applications43 citations Open access
Semantic Scholar
Improving Generalization of Deepfake Detection With Data Farming and Few-Shot Learning
P. Korshunov, S. Marcel
2022IEEE Transactions on Biometrics Behavior and Identity Science40 citations Open access
Semantic Scholar
Quality evaluation of HEVC and VP9 video compression in real-time applications
M. Rerábek, Philippe Hanhart, P. Korshunov, T. Ebrahimi
2015International Workshop on Quality of Multimedia Experience40 citations Open access
Semantic Scholar
Crowdsourcing-based evaluation of privacy in HDR images
P. Korshunov, Hiromi Nemoto, A. Skodras, T. Ebrahimi
2014Photonics Europe39 citations Open access
Semantic Scholar
[JCT-VC contribution] AhG4: Subjective evaluation of HEVC intra coding for still image compression
Philippe Hanhart, M. Rerábek, P. Korshunov, T. Ebrahimi
201336 citations
Semantic Scholar
Impact of Score Fusion on Voice Biometrics and Presentation Attack Detection in Cross-Database Evaluations
P. Korshunov, S. Marcel
2017IEEE Journal on Selected Topics in Signal Processing34 citations Open access
Semantic Scholar
HDR image compression: A new challenge for objective quality metrics
Philippe Hanhart, Marco V. Bernardo, P. Korshunov, Manuela Pereira +2 more
2014International Workshop on Quality of Multimedia Experience34 citations Open access
Semantic Scholar
Subjective and Objective Evaluation of Deepfake Videos
P. Korshunov, S. Marcel
2021IEEE International Conference on Acoustics, Speech, and Signal Processing32 citations Open access
Semantic Scholar
Subjective evaluation of higher dynamic range video
Philippe Hanhart, P. Korshunov, T. Ebrahimi
2014Optics & Photonics - Optical Engineering + Applications31 citations Open access
Semantic Scholar
Benchmarking of quality metrics on ultra-high definition video sequences
Philippe Hanhart, P. Korshunov, T. Ebrahimi
2013International Conference on Digital Signal Processing31 citations Open access
Semantic Scholar
Subjective and objective evaluation of HDR video compression
M. Rerábek, Philippe Hanhart, P. Korshunov, T. Ebrahimi
201530 citations
Semantic Scholar
Overview of the MediaEval 2013 Visual Privacy Task
A. Badii, T. Ebrahimi, Christian Fedorczak, P. Korshunov +3 more
2013MediaEval Benchmarking Initiative for Multimedia Evaluation28 citations
Semantic Scholar
Improving Generalization of Deepfake Detection by Training for Attribution
Anubhav Jain, P. Korshunov, S. Marcel
2021IEEE International Workshop on Multimedia Signal Processing26 citations Open access
Semantic Scholar
Tampered Speaker Inconsistency Detection with Phonetically Aware Audio-visual Features
P. Korshunov, Michael Halstead, Diego Castán, M. Graciarena +4 more
2019International Conference on Machine Learning26 citations
Semantic Scholar
Subjective Quality Evaluation Of High Dynamic Range Video And Display For Future TV
Philippe Hanhart, P. Korshunov, T. Ebrahimi, Yvonne Thomas +1 more
201425 citations Open access
Semantic Scholar
Performance evaluation of the emerging JPEG XT image compression standard
A. Pinheiro, K. Fliegel, P. Korshunov, Lukáš Krasula +3 more
2014IEEE International Workshop on Multimedia Signal Processing24 citations Open access
Semantic Scholar
Towards optimal distortion-based visual privacy filters
P. Korshunov, T. Ebrahimi
2014International Conference on Information Photonics23 citations Open access
Semantic Scholar
Scrambling-based tool for secure protection of JPEG images
P. Korshunov, T. Ebrahimi
2014International Conference on Information Photonics21 citations Open access
Semantic Scholar
The Speed Submission to DIHARD II: Contributions & Lessons Learned
Md Sahidullah, J. Patino, Samuele Cornell, Ruiqing Yin +10 more
2019arXiv.org19 citations
Semantic Scholar
On the use of convolutional neural networks for speech presentation attack detection
P. Korshunov, A. Gonçalves, R. Violato, F. Simões +1 more
2018International Conference on Identity, Security and Behavior Analysis19 citations Open access
Semantic Scholar
Ultra-eye: UHD and HD images eye tracking dataset
Hiromi Nemoto, Philippe Hanhart, P. Korshunov, T. Ebrahimi
2014International Workshop on Quality of Multimedia Experience19 citations Open access
Semantic Scholar
Context-dependent JPEG backward-compatible high-dynamic range image compression
P. Korshunov, T. Ebrahimi
201319 citations Open access
Semantic Scholar