20 citations · 20 across the 6 of their papers we have counts for
6 papers
EMO-BOOST: Emotion-Augmented Audio-Visual Features for Improved Generalization in Deepfake Detection
Aritra Marik, Marcel Klemt, Anna Rohrbach
With every advancement in generative AI models, forensics is under increasing pressure. The constant emergence of new generation techniques makes it impossible to collect data for…
DeepFake Doctor: Diagnosing and Treating Audio-Video Fake Detection
Marcel Klemt, Carlotta Segna, Anna Rohrbach
Generative AI advances rapidly, allowing the creation of very realistic manipulated video and audio. This progress presents a significant security and ethical threat, as malicious…
ExFaceGAN: Exploring Identity Directions in GAN's Learned Latent Space for Synthetic Identity Generation
Fadi Boutros, Marcel Klemt, Meiling Fang +2
Deep generative models have recently presented impressive results in generating realistic face images of random synthetic identities. To generate multiple samples of a certain synt…
Unsupervised Face Recognition using Unlabeled Synthetic Data
Fadi Boutros, Marcel Klemt, Meiling Fang +2
Over the past years, the main research innovations in face recognition focused on training deep neural networks on large-scale identity-labeled datasets using variations of multi-c…
CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiability
Fadi Boutros, Meiling Fang, Marcel Klemt +2
The quality of face images significantly influences the performance of underlying face recognition algorithms. Face image quality assessment (FIQA) estimates the utility of the cap…
PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and Multi-Step Knowledge Distillation
Fadi Boutros, Patrick Siebke, Marcel Klemt +3
Deep neural networks have rapidly become the mainstream method for face recognition (FR). However, this limits the deployment of such models that contain an extremely large number…