C
Charles Dubout
Researcher at Idiap Research Institute
Publications - 12
Citations - 360
Charles Dubout is an academic researcher from Idiap Research Institute. The author has contributed to research in topics: Fourier transform & Object detection. The author has an hindex of 7, co-authored 12 publications receiving 330 citations. Previous affiliations of Charles Dubout include NEC.
Papers
More filters
Book ChapterDOI
Exact acceleration of linear object detectors
Charles Dubout,Fran,ois Fleuret +2 more
TL;DR: A general and exact method to considerably speed up linear object detection systems operating in a sliding, multi-scale window fashion, such as the individual part detectors of part-based models, by making use of properties of the Fourier transform and of clever implementation strategies.
Journal ArticleDOI
Comparing machines and humans on a visual categorization test
TL;DR: This work compares the efficiency of human and machine learning in assigning an image to one of two categories determined by the spatial arrangement of constituent parts and demonstrates that human subjects grasp the separating principles from a handful of examples, whereas the error rates of computer programs fluctuate wildly and remain far behind that of humans even after exposure to thousands of examples.
Proceedings ArticleDOI
Deformable Part Models with Individual Part Scaling
Charles Dubout,François Fleuret +1 more
TL;DR: It is demonstrated in this paper that if one settles for approximately optimal placements, it is possible to efficiently deform the parts across scales as well.
Journal Article
Adaptive sampling for large scale boosting
Charles Dubout,François Fleuret +1 more
TL;DR: Experiments in image classification and object recognition on four standard computer vision data sets show that the adaptive methods proposed outperform basic sampling and state-of-the-art bandit methods.
Proceedings ArticleDOI
Tasting families of features for image classification
Charles Dubout,François Fleuret +1 more
TL;DR: Using multiple families of image features is a very efficient strategy to improve performance in object detection or recognition but induces multiple challenges for machine learning methods, both from a computational and a statistical perspective.