activity
20222026
most citedViGAT: Bottom-up event recognition and explanation in video using factorized graph attention network

15 citations · 35 across the 8 of their papers we have counts for

collaborators

8 papers

cs.CV2026

LLaVA-CKD: Bottom-Up Cascaded Knowledge Distillation for Vision-Language Models

Nikolaos Gkalelis, Vasileios Mezaris

Large Vision-Language Models (VLMs) are successful in addressing a multitude of vision-language understanding tasks, such as Visual Question Answering (VQA), but their memory and c…

cs.CV2024★ 9 cited

T-TAME: Trainable Attention Mechanism for Explaining Convolutional Networks and Vision Transformers

Mariano V. Ntrougkas, Nikolaos Gkalelis, Vasileios Mezaris

The development and adoption of Vision Transformers and other deep-learning architectures for image classification tasks has been rapid. However, the "black box" nature of neural n…

cs.CV2023

Filter-Pruning of Lightweight Face Detectors Using a Geometric Median Criterion

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. There…

cs.CV2023

Masked Feature Modelling: Feature Masking for the Unsupervised Pre-training of a Graph Attention Network Block for Bottom-up Video Event Recognition

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. MFM utilizes a pretrained V…

cs.CV2023★ 1 cited

Gated-ViGAT: Efficient Bottom-Up Event Recognition and Explanation Using a New Frame Selection Policy and Gating Mechanism

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 propo…

cs.CV2023★ 10 cited

TAME: Attention Mechanism Based Feature Fusion for Generating Explanation Maps of Convolutional Neural Networks

Mariano Ntrougkas, Nikolaos Gkalelis, Vasileios Mezaris

The apparent ``black box'' nature of neural networks is a barrier to adoption in applications where explainability is essential. This paper presents TAME (Trainable Attention Mecha…