B
Benjamin Drayer
Researcher at University of Freiburg
Publications - 6
Citations - 208
Benjamin Drayer is an academic researcher from University of Freiburg. The author has contributed to research in topics: Object detection & Object (computer science). The author has an hindex of 4, co-authored 6 publications receiving 189 citations.
Papers
More filters
Journal ArticleDOI
ViBE-Z: a framework for 3D virtual colocalization analysis in zebrafish larval brains
Olaf Ronneberger,Kun Liu,Meta Rath,Dominik Rueβ,Thomas Mueller,Henrik Skibbe,Benjamin Drayer,Thorsten Schmidt,Alida Filippi,Roland Nitschke,Thomas Brox,Hans Burkhardt,Wolfgang Driever +12 more
TL;DR: The Virtual Brain Explorer (ViBE-Z), a software that automatically maps gene expression data with cellular resolution to a 3D standard larval zebrafish (Danio rerio) brain, is developed and demonstrated its utility for mapping neurons of the dopaminergic system.
Posted Content
Object Detection, Tracking, and Motion Segmentation for Object-level Video Segmentation
Benjamin Drayer,Thomas Brox +1 more
TL;DR: An approach for object segmentation in videos that combines frame-level object detection with concepts from object tracking and motion segmentation and provides an accurate, temporally consistent segmentation of each object is presented.
Book ChapterDOI
Training Deformable Object Models for Human Detection Based on Alignment and Clustering
Benjamin Drayer,Thomas Brox +1 more
TL;DR: This work considers the deformable part model of Felzenszwalb et al., where each mixture component includes a learned deformation model, and shows that alignment based clustering distributes the data better to the mixture components of the DPM than previous methods.
Proceedings ArticleDOI
Combinatorial Regularization of Descriptor Matching for Optical Flow Estimation
Benjamin Drayer,Thomas Brox +1 more
TL;DR: The proposed refinement improves all optical flow algorithms that build upon pre-computed correspondences by removing outliers from the initial matching and increasing the number of reliable matches.
Book ChapterDOI
Distances Based on Non-rigid Alignment for Comparison of Different Object Instances
Benjamin Drayer,Thomas Brox +1 more
TL;DR: In contrast to the classical Procrustes distance, this work proposes distances based on non-rigid alignment and shows that this increases performance in nearest neighbor tasks.