L
Luc Van Gool
Researcher at Katholieke Universiteit Leuven
Publications - 1458
Citations - 137230
Luc Van Gool is an academic researcher from Katholieke Universiteit Leuven. The author has contributed to research in topics: Computer science & Segmentation. The author has an hindex of 133, co-authored 1307 publications receiving 107743 citations. Previous affiliations of Luc Van Gool include Microsoft & ETH Zurich.
Papers
More filters
Journal Article
Unsupervised Robust Domain Adaptation without Source Data.
TL;DR: In this article, the authors study the problem of robust domain adaptation in the context of unavailable target labels and source data, where the considered robustness is against adversarial perturbations.
Proceedings ArticleDOI
Discriminative learning of apparel features
TL;DR: This work proposes to learn discriminative features based on a small set of annotated images to organize product databases by image classification, which allows for fast feature extraction and training, is easy to implement and does not require powerful dedicated hardware.
From a conservationist's point of view
Kristiaan Nuyts,Jean-Pierre Kruth,Bert Lauwers,Herman Neuckermans,Marc Pollefeys,Q Li,Joris Schouteden,Pierre Smars,Koenraad Van Balen,Luc Van Gool,Maarten Vergauwen +10 more
TL;DR: The main idea of the research project is to construct a prototype of a tool that tries to bring new technologies closer to the daily practice, which incorporates recent developments in computer vision and reverse engineering.
to appear proceedings SPIE Electronic Imaging 2000, Three-Dimensional Image Capture and Applications III
TL;DR: An approach is described which achieves this goal by combining state-of-the-art algorithms for uncalibrated projective reconstruction, self-calibration and dense correspondence matching.
Journal ArticleDOI
Editorial: Special issue on 3D representation for object and scene recognition
TL;DR: This special issue features a series of works based on the concept of representing objects as collections of elements that are connected across views so as to form a unique and coherent model for the object.