34 citations · 130 across the 19 of their papers we have counts for
10 papers · 1 filter
Scaling Vision-Language Models Is Not Enough to Mitigate Bias
Ioannis Sarridis, Ioannis Kompatsiaris, Symeon Papadopoulos
Vision-Language Models (VLMs) such as CLIP are now foundational to multimodal systems, yet their robustness to spurious correlations remains poorly understood at scale. We present…
Face Age Verification Vulnerabilities Under Simple Appearance Manipulations
Ioannis Sarridis, Ioannis Kompatsiaris, Symeon Papadopoulos
Online platforms increasingly rely on automated age estimation systems to enforce minimum-age policies. Focusing on vision-based models designed for this task, concerns arise regar…
Test-Time Noise Guided Adaptation for Realistic Autoregressive Video Generation
Dimitrios Karageorgiou, Symeon Papadopoulos, Ioannis Kompatsiaris +1
Autoregressive video diffusion models have enabled the generation of arbitrarily long videos by removing conditioning on future frames, thus greatly improving computational efficie…
CycleCap: Improving VLMs Captioning Performance via Self-Supervised Cycle Consistency Fine-Tuning
Marios Krestenitis, Christos Tzelepis, Konstantinos Ioannidis +5
Visual-Language Models (VLMs) have achieved remarkable progress in image captioning, visual question answering, and visual reasoning. Yet they remain prone to vision-language misal…
Few-Shot Class-Incremental Learning For Efficient SAR Automatic Target Recognition
George Karantaidis, Athanasios Pantsios, Ioannis Kompatsiaris +1
Synthetic aperture radar automatic target recognition (SAR-ATR) systems have rapidly evolved to tackle incremental recognition challenges in operational settings. Data scarcity rem…
Multimodal Quasi-AutoRegression: Forecasting the visual popularity of new fashion products
Stefanos I. Papadopoulos, Christos Koutlis, Symeon Papadopoulos +1
Estimating the preferences of consumers is of utmost importance for the fashion industry as appropriately leveraging this information can be beneficial in terms of profit. Trend de…