B
Bogdan Alexe
Researcher at University of Bucharest
Publications - 20
Citations - 5822
Bogdan Alexe is an academic researcher from University of Bucharest. The author has contributed to research in topics: Object detection & Anomaly detection. The author has an hindex of 16, co-authored 19 publications receiving 5365 citations. Previous affiliations of Bogdan Alexe include ETH Zurich.
Papers
More filters
Journal ArticleDOI
Measuring the Objectness of Image Windows
TL;DR: In this paper, a generic objectness measure is proposed to quantify how likely an image window is to contain an object of any class, such as cows and telephones, from amorphous background elements such as grass and road.
Measuring the objectness of image windows
TL;DR: A generic objectness measure, quantifying how likely it is for an image window to contain an object of any class, and uses objectness as a complementary score in addition to the class-specific model, which leads to fewer false positives.
Book ChapterDOI
ClassCut for unsupervised class segmentation
TL;DR: A novel method for unsupervised class segmentation on a set of images that alternates between segmenting object instances and learning a class model based on a segmentation energy defined over all images at the same time, which can be optimized efficiently by techniques used before in interactive segmentation.
Proceedings ArticleDOI
What is an object
TL;DR: A generic objectness measure, quantifying how likely it is for an image window to contain an object of any class, is presented, combining in a Bayesian framework several image cues measuring characteristics of objects, such as appearing different from their surroundings and having a closed boundary.
Journal ArticleDOI
Weakly Supervised Localization and Learning with Generic Knowledge
TL;DR: A conditional random field that starts from generic knowledge and then progressively adapts to the new class is proposed that allows training any state-of-the-art object detector in a weakly supervised fashion, although it would normally require object location annotations.