M
Marc-André Carbonneau
Researcher at École de technologie supérieure
Publications - 20
Citations - 790
Marc-André Carbonneau is an academic researcher from École de technologie supérieure. The author has contributed to research in topics: Instance-based learning & Computer science. The author has an hindex of 8, co-authored 20 publications receiving 440 citations. Previous affiliations of Marc-André Carbonneau include Ubisoft Montreal & École Normale Supérieure.
Papers
More filters
Journal ArticleDOI
Multiple instance learning: A survey of problem characteristics and applications
TL;DR: A comprehensive survey of the characteristics which define and differentiate the types of MIL problems is provided, providing insight on how the problem characteristics affect MIL algorithms, recommendations for future benchmarking and promising avenues for research.
BookDOI
Intravascular Imaging and Computer Assisted Stenting, and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis
M.J. Cardoso,Tal Arbel,Veronika Cheplygina,S.-L. Lee,Simone Balocco,Diana Mateus,Guillaume Zahnd,Lena Maier-Hein,Stefanie Demirci,Eric Granger,Luc Duong,Marc-André Carbonneau,Shadi Albarqouni,Gustavo Carneiro +13 more
TL;DR: A technique to automatically estimate circular cross-sections of the vessels in CT scans by using the Hough transform and a parametric snake model to estimate the local probability density functions of the image intensity inside and outside the vessels.
Journal ArticleDOI
Robust multiple-instance learning ensembles using random subspace instance selection
TL;DR: Results obtained with several real-world and synthetic databases show the robustness of MIL ensembles designed with the proposed RSIS method over a range of witness rates, noisy features and data distributions compared to reference methods in the literature.
Posted Content
Measuring Disentanglement: A Review of Metrics
TL;DR: This work surveys supervised disentanglement metrics and proposes a new taxonomy in which all metrics fall into one of three families: intervention-based, predictor-based and information-based.
Journal ArticleDOI
Detection of alarms and warning signals on an digital in-ear device
TL;DR: New algorithms to automatically detect alarm signals in the digitized audio stream fed to the processor are developed and performed in real-time with low latency to quickly inform the user of a dangerous situation.