Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
[Re] Boosting the Visual Interpretability of CLIP via Adversarial Fine-Tuning
Anton Nuzhdin, Andrei Gruzitski, Balázs Egyed +1
This paper presents a reproducibility study of ``Boosting the Visual Interpretability of CLIP via Adversarial Fine-Tuning'', published at ICLR 2025, which proposes an unsupervised…
cs.CV2026
FUSED: Forensic-Semantic Mixture-of-Experts for AI Inpainting Detection and Localization
Anton Nuzhdin, Marcel Worring, Ivona Najdenkoska
Diffusion-based inpainting models modify only a localized part of an image, while many AI-image detectors rely on global artifacts and do not localize. These artifacts vary across…
cs.CV2024
HaGRIDv2: 1M Images for Static and Dynamic Hand Gesture Recognition
Anton Nuzhdin, Alexander Nagaev, Alexander Sautin +2
This paper proposes the second version of the widespread Hand Gesture Recognition dataset HaGRID -- HaGRIDv2. We cover 15 new gestures with conversation and control functions, incl…