J
Jens-Uwe Garbas
Researcher at Fraunhofer Society
Publications - 28
Citations - 432
Jens-Uwe Garbas is an academic researcher from Fraunhofer Society. The author has contributed to research in topics: Reference frame & Motion compensation. The author has an hindex of 11, co-authored 28 publications receiving 329 citations.
Papers
More filters
Journal ArticleDOI
Machine Learning and End-to-End Deep Learning for Monitoring Driver Distractions From Physiological and Visual Signals
TL;DR: This study compared data from physiological sensors and visual sensors for the detection of four types of distractions and identified problems, such as label jitter, scenario overfitting and unsatisfactory generalization performance, that may adversely affect related ML approaches.
Journal ArticleDOI
Automatic Detection of Pain from Facial Expressions: A Survey
Teena Hassan,Dominik Seuß,Johannes Wollenberg,Katharina Weitz,Miriam Kunz,Stefan Lautenbacher,Jens-Uwe Garbas,Ute Schmid +7 more
TL;DR: This paper surveys the literature published in this field over the past decade, categorizes it, and identifies future research directions, and covers the pain datasets used in the reviewed literature, the learning tasks targeted by the approaches, the features extracted from images and image sequences to represent pain-related information, and the machine learning methods used.
Journal ArticleDOI
Deep-learned faces of pain and emotions: Elucidating the differences of facial expressions with the help of explainable AI methods
TL;DR: The aim of this paper is to investigate the explainable AI methods Layer-wise Relevance Propagation (LRP) and Local Interpretable Model-agnostic Explanations (LIME), applied to explain how a deep neural network distinguishes facial expressions of pain from facial expression of emotions such as happiness and disgust.
Patent
Inter-layer prediction between layers of different dynamic sample value range
Jens-Uwe Garbas,Thomas Herbert +1 more
TL;DR: In this paper, a global predictor and a local predictor are used in combination, where the global predictor derives a global tone-mapping function based on a statistical analysis of pairs of values of co-located samples in the first tonemapped version and the second version of the picture.
Journal ArticleDOI
High dynamic range video reconstruction from a stereo camera setup
TL;DR: A framework is presented that utilizes two cameras to realize a spatial exposure bracketing, for which the different exposures are distributed among the cameras, and which enables the use of more complex camera setups with different sensors and provides robust camera responses.