K
Kevin Smith
Researcher at Royal Institute of Technology
Publications - 60
Citations - 10918
Kevin Smith is an academic researcher from Royal Institute of Technology. The author has contributed to research in topics: Image segmentation & Breast cancer. The author has an hindex of 25, co-authored 60 publications receiving 8802 citations. Previous affiliations of Kevin Smith include Karolinska Institutet & École Polytechnique Fédérale de Lausanne.
Papers
More filters
Proceedings ArticleDOI
Vignetting and photo-bleaching correction in automated fluorescence microscopy from an array of overlapping images
TL;DR: A novel acquisition scheme and non-parametric multi-image based method for correcting illumination in fluorescence images by measuring changes in intensity by moving the microscope stage at regularly spaced intervals, and exploiting this information to learn the correction function.
Supervoxel-Based Segmentation of EM Image Stacks with Learned Shape Features
TL;DR: This work proposes an automated graph partitioning scheme that reduces the computational complexity by operating on supervoxels instead of voxels, incorporates global shape features capable of describing the 3D shape of the target objects, and learns to recognize the distinctive appearance of true boundaries.
Book ChapterDOI
Audio-Visual processing in meetings: seven questions and current AMI answers
Marc Al-Hames,Thomas Hain,Jan Cernocky,Sascha Schreiber,Mannes Poel,Ronald Müller,Sébastien Marcel,David A. van Leeuwen,Jean-Marc Odobez,Silèye O. Ba,Hervé Bourlard,Fabien Cardinaux,Daniel Gatica-Perez,Adam Janin,Petr Motlicek,Stephan Reiter,Steve Renals,Jeroen van Rest,Rutger Rienks,Gerhard Rigoll,Kevin Smith,Andrew Thean,Pavel Zemcik +22 more
TL;DR: The Augmented Multi-Party Interaction (AMI) project as mentioned in this paper addresses the automatic recognition from audio, video, and combined audio-video streams, that have been recorded during meetings and describes the progress that has been made in the first two years of the project.
Tracking Attention for Multiple People: Wandering Visual Focus of Attention Estimation
TL;DR: This work proposes a multi-person tracking solution based on a hybrid Dynamic Bayesian Network that simultaneously infers the number of people in a scene, their body locations, their head locations, and their head pose and proposes a trans-dimensional Markov Chain Monte Carlo sampling scheme that efficiently searches the state-space by allowing person-part state updates.
Journal ArticleDOI
A Role for the VPS Retromer in Brucella Intracellular Replication Revealed by Genomewide siRNA Screening
Alain Casanova,Shyan Huey Low,Maxime Québatte,Jaroslaw Sedzicki,Therese Tschon,Maren Ketterer,Kevin Smith,Mario Emmenlauer,Houchaima Ben-Tekaya,Christoph Dehio +9 more
TL;DR: Using assays for pathogen entry, knockdown complementation, and colocalization at single-cell resolution, the requirement of the VPS retromer for Brucella to escape the lysosomal degradative pathway and to establish its intracellular replicative niche is identified and validated by a systematic cell-based small interfering RNA (siRNA) knockdown screen.