Luc Van Gool

TL;DR: Deep Retinal Image Understanding (DRIU) as mentioned in this paper uses a base network architecture on which two set of specialized layers are trained to solve both the retinal vessel and optic disc segmentation.

TL;DR: A Riemannian network architecture is built to open up a new direction of SPD matrix non-linear learning in a deep model and it is shown that the proposed SPD matrix network can be simply trained and outperform existing SPD matrix learning and state-of-the-art methods in three typical visual classification tasks.

TL;DR: This image sequence is calibrated with a structure-from-motion approach that considers the special viewing geometry of plenoptic scenes and dense depth maps are recovered locally for each viewpoint by applying a stereo matching technique.

TL;DR: This work presents an approach to automatically learn two-dimensional attributed stochastic context-free grammars (2D-ASCFGs) from a set of labeled building facades by using Bayesian Model Merging, a technique originally developed in the field of natural language processing, which is extended to the domain of two- dimensional languages.

TL;DR: In this article, a pixel-wise contrastive framework is proposed to enforce pixel embeddings belonging to a same semantic class to be more similar than embedding from different classes.