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
Posted Content
Revisiting Multi-Task Learning in the Deep Learning Era
TL;DR: This survey provides a well-rounded view on state-of-the-art MTL techniques within the context of deep neural networks and examines various optimization methods to tackle the joint learning of multiple tasks.
Proceedings ArticleDOI
End-to-end Lane Detection through Differentiable Least-Squares Fitting
TL;DR: In this paper, the authors propose an end-to-end network that predicts a segmentation-like weight map for each lane line, and a differentiable least-squares fitting module that returns for each map the parameters of the best fitting curve in the weighted least squares sense.
Easy and cost-effective cuneiform digitizing
TL;DR: A new fully automated cuneiform tablet digitizing solution is presented which is relatively inexpensive and easily field-deployable, and allows for photorealistic virtual re-lighting and non-photorealistic rendering of the tab lets in real-time through the use of programmable graphics hardware.
Journal ArticleDOI
The Visual System's Measurement of Invariants Need Not Itself Be Invariant
TL;DR: In this article, the authors argue that these effects are not necessarily solid evidence for the use of mental transformations and argue that the visual system's measurement of invariants need not itself be invariant.
Journal Article
Backprojection revisited: scalable multi-view object detection and similarity metrics for detections
TL;DR: In this paper, the authors investigate the use of the support and its backprojection to the image domain for multi-view object detection, and demonstrate that superior accuracy and efficiency can be achieved in comparison to the popular one-vs-the-rest detectors by treating views jointly especially with few training examples and no view annotations.