no code implementations • 7 Mar 2024 • Mariano V. Ntrougkas, Nikolaos Gkalelis, Vasileios Mezaris
While some techniques for generating explanations have been proposed, primarily for Convolutional Neural Networks, adapting such techniques to the new paradigm of Vision Transformers is non-trivial.
1 code implementation • 28 Nov 2023 • Konstantinos Gkrispanis, Nikolaos Gkalelis, Vasileios Mezaris
Face detectors are becoming a crucial component of many applications, including surveillance, that often have to run on edge devices with limited processing power and memory.
no code implementations • 24 Aug 2023 • Dimitrios Daskalakis, Nikolaos Gkalelis, Vasileios Mezaris
In this paper, we introduce Masked Feature Modelling (MFM), a novel approach for the unsupervised pre-training of a Graph Attention Network (GAT) block.
1 code implementation • 18 Jan 2023 • Nikolaos Gkalelis, Dimitrios Daskalakis, Vasileios Mezaris
In this paper, Gated-ViGAT, an efficient approach for video event recognition, utilizing bottom-up (object) information, a new frame sampling policy and a gating mechanism is proposed.
1 code implementation • 18 Jan 2023 • Mariano Ntrougkas, Nikolaos Gkalelis, Vasileios Mezaris
TAME can easily be applied to any convolutional neural network (CNN) by streamlining the optimization of the attention mechanism's training method and the selection of target model's feature maps.
1 code implementation • 22 Sep 2022 • Ioanna Gkartzonika, Nikolaos Gkalelis, Vasileios Mezaris
In this paper two new learning-based eXplainable AI (XAI) methods for deep convolutional neural network (DCNN) image classifiers, called L-CAM-Fm and L-CAM-Img, are proposed.
1 code implementation • 20 Jul 2022 • Nikolaos Gkalelis, Dimitrios Daskalakis, Vasileios Mezaris
In this paper a pure-attention bottom-up approach, called ViGAT, that utilizes an object detector together with a Vision Transformer (ViT) backbone network to derive object and frame features, and a head network to process these features for the task of event recognition and explanation in video, is proposed.
no code implementations • 27 Apr 2015 • Nikolaos Gkalelis, Vasileios Mezaris
In this paper, using a novel matrix factorization and simultaneous reduction to diagonal form approach (or in short simultaneous reduction approach), Accelerated Kernel Discriminant Analysis (AKDA) and Accelerated Kernel Subclass Discriminant Analysis (AKSDA) are proposed.