collaborators

5 papers

cs.CV2025

Detecting Text Manipulation in Images using Vision Language Models

Vidit Vidit, Pavel Korshunov, Amir Mohammadi +3

Recent works have shown the effectiveness of Large Vision Language Models (VLMs or LVLMs) in image manipulation detection. However, text manipulation detection is largely missing i…

cs.CV2025

Identity-Preserving Aging and De-Aging of Faces in the StyleGAN Latent Space

Luis S. Luevano, Pavel Korshunov, Sebastien Marcel

Face aging or de-aging with generative AI has gained significant attention for its applications in such fields like forensics, security, and media. However, most state of the art m…

cs.CV2025

FantasyID: A dataset for detecting digital manipulations of ID-documents

Pavel Korshunov, Amir Mohammadi, Vidit Vidit +2

Advancements in image generation led to the availability of easy-to-use tools for malicious actors to create forged images. These tools pose a serious threat to the widespread Know…

cs.CV2025

Investigation of Accuracy and Bias in Face Recognition Trained with Synthetic Data

Pavel Korshunov, Ketan Kotwal, Christophe Ecabert +3

Synthetic data has emerged as a promising alternative for training face recognition (FR) models, offering advantages in scalability, privacy compliance, and potential for bias miti…

cs.AI2025

HintsOfTruth: A Multimodal Checkworthiness Detection Dataset with Real and Synthetic Claims

Michiel van der Meer, Pavel Korshunov, Sébastien Marcel +1

Misinformation can be countered with fact-checking, but the process is costly and slow. Identifying checkworthy claims is the first step, where automation can help scale fact-check…