5 papers · 1 filter
Prescriptive SVD-Inspired Attention via Spectral Energy Retention
Vasileios Arampatzakis, Vasileios Sevetlidis, George Pavlidis
Self-attention is central to modern Transformer architectures, but its dense dot-product formulation makes it difficult to identify which internal directions are structurally impor…
Towards complete digital twins in cultural heritage with ART3mis 3D artifacts annotator
Dimitrios Karamatskos, Vasileios Arampatzakis, Vasileios Sevetlidis +5
Archaeologists, as well as specialists and practitioners in cultural heritage, require applications with additional functions, such as the annotation and attachment of metadata to…
ART3mis: Ray-Based Textual Annotation on 3D Cultural Objects
Vasileios Arampatzakis, Vasileios Sevetlidis, Fotis Arnaoutoglou +7
Beyond simplistic 3D visualisations, archaeologists, as well as cultural heritage experts and practitioners, need applications with advanced functionalities. Such as the annotation…
Interpretable Vision Transformers in Monocular Depth Estimation via SVDA
Vasileios Arampatzakis, George Pavlidis, Nikolaos Mitianoudis +1
Monocular depth estimation is a central problem in computer vision with applications in robotics, AR, and autonomous driving, yet the self-attention mechanisms that drive modern Tr…
Interpretable Vision Transformers in Image Classification via SVDA
Vasileios Arampatzakis, George Pavlidis, Nikolaos Mitianoudis +1
Vision Transformers (ViTs) have achieved state-of-the-art performance in image classification, yet their attention mechanisms often remain opaque and exhibit dense, non-structured…