← Search

Nicholas Vretos

2 accepted papers

2020

Multi-view adaptive graph convolutions for graph classification

ECCV 2020poster

In this paper, a novel multi-view methodology for graph-based neural networks is proposed. A systematic and methodological adaptation of the key concepts of classical deep learning methods such as convolution, pooling and multi-view architectures is developed for the context of non-Euclidean manifol…

Cited by 13SourcePDFScholar
2017

Non-Linear Convolution Filters for CNN-Based Learning

ICCV 2017poster

During the last years, Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in image classification. Their architectures have largely drawn inspiration by models of the primate visual system. However, while recent research results of neuroscience prove the existence of non…

Cited by 121PDFScholar