T
Thomas Unterthiner
Researcher at Google
Publications - 51
Citations - 31915
Thomas Unterthiner is an academic researcher from Google. The author has contributed to research in topics: Convolutional neural network & Deep learning. The author has an hindex of 26, co-authored 47 publications receiving 15696 citations. Previous affiliations of Thomas Unterthiner include Johannes Kepler University of Linz & University of Göttingen.
Papers
More filters
Proceedings Article
FVD: A new Metric for Video Generation
Journal ArticleDOI
Detection of viral sequence fragments of HIV-1 subfamilies yet unknown
Thomas Unterthiner,Anne-Kathrin Schultz,Jan Bulla,Burkhard Morgenstern,Mario Stanke,Ingo Bulla +5 more
TL;DR: The developed Unknown Subtype Finder (USF), an algorithm based on a probabilistic model, which automatically determines which parts of an input sequence originate from a subtype yet unknown, demonstrates that it performs as good as the Branching Index or better.
Book ChapterDOI
Visual Scene Understanding for Autonomous Driving Using Semantic Segmentation
Markus Hofmarcher,Thomas Unterthiner,Jose A. Arjona-Medina,Günter Klambauer,Sepp Hochreiter,Bernhard Nessler +5 more
TL;DR: This work suggests the use of a tiered approach, whose main component is a semantic segmentation model, over an end-to-end approach for an autonomous driving system.
Journal ArticleDOI
DeepTox: Toxicity prediction using deep learning
Journal ArticleDOI
DEXUS: identifying differential expression in RNA-Seq studies with unknown conditions
TL;DR: On real-world data sets, DEXUS was able to detect differentially expressed transcripts related to sex, species, tissue, structural variants or quantitative trait loci and performed excellently in identifying differentially expression transcripts in data with unknown conditions.