Biblio
Bayesian Calibration of MEMS Accelerometers.
IEEE Sensors Journal.
(2023). Deep probabilistic modelling for energy forecasting.
Poster_Deep probabilistic modelling for energy forecasting TTT.pdf (839.27 KB)
(2023). ![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
Deep transformation models for functional outcome prediction after acute ischemic stroke.
Biometrical Journal. 65, 2100379.
(2023).
(2023). Extended Target Tracking With a Lidar Sensor Using Random Matrices and a Gaussian Processes Regression Model.
International Conference on Information Fusion (FUSION). 1-8.
(2023). Incremental one-class learning using regularized null-space training for industrial defect detection.
16th International Conference on Machine Vision (ICMV).
(2023). Novel AI-Based Algorithm for the Automated Computation of Coronal Parameters in Adolescent Idiopathic Scoliosis Patients: A Validation Study on 100 Preoperative Full Spine X-Rays.
Global Spine Journal. 21925682231154543.
(2023). Short-term density forecasting of low-voltage load using Bernstein-polynomial normalizing flows.
IEEE Transactions on Smart Grid.
(2023). Visual Pitch and Roll Estimation For Inland Water Vessels.
IEEE International Conference on Robotics and Automation (ICRA). 1961-1967.
(2023). 140. Automated measurement technique for coronal parameters using a novel artificial intelligence algorithm: an independent validation study on 100 preoperative AP spine X-rays.
The Spine Journal. 22, S74.
(2022). Crowd Management in der Lehre.
Seamless Learning, Grenz- und kontextübergreifendes Lehren und Lernen in der Bodenseeregion. 123-132.
(2022). Deep and interpretable regression models for ordinal outcomes.
Pattern Recognition. 122, 108263.
(2022). DeepDoubt - Improving uncertainty measures in machine learning to improve explainability and transparency.
2022 All-Hands-Meeting of the BMBF-funded AI Research Projects at Munich Center for Machine Learning.
AHM2022_DeepDoubt.pdf (238.98 KB)
(2022). ![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
Fast and efficient image novelty detection based on mean-shifts.
Sensors | Unusual Behavior Detection Based on Machine Learning .
(2022). Fast and memory-efficient independent component analysis using Lie group techniques.
International Conference on Curves and Surfaces.
(2022). Image novelty detection based on mean-shift and typical set size.
21th International Conference on Image Analysis and Processing, ICIAP.
ICIAP-mean-shift-novelty-detection-preprint.pdf (2.96 MB)
(2022). ![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
Large-scale independent component analysis by speeding up Lie group techniques.
International Conference on Acoustics, Speech, and Signal Processing, ICASSP.
conference_101719.pdf (646.58 KB)
(2022). ![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
Mathematik mit digitalen Bildern sichtbar machen.
Seamless Learning, Grenz- und kontextübergreifendes Lehren und Lernen in der Bodenseeregion. 133-145.
(2022). Targetless Lidar-camera registration using patch-wise mutual information.
International Conference on Information Fusion.
mir_reg_patch.pdf (9.58 MB)
(2022).
(2022). ![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
Accelerating Active Learning Image Labeling Through Bulk Shift Recommendations.
2021 International Conference on Data Mining Workshops (ICDMW). 398-404.
(2021). Accelerating Active Learning Image Labeling Through Bulk Shift Recommendations.
2021 International Conference on Data Mining Workshops (ICDMW). 398–404.
(2021). Biologically-inspired vs. CNN texture representations in novelty detection.
Applications of Machine Learning 2021. 118430I.
Spie2021.pdf (5.33 MB)
(2021). ![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
Deep transformation models: Tackling complex regression problems with neural network based transformation models.
Accepted for Proceedings of the 25th International Conference on Pattern Recognition (ICPR), Milan/Online, 2021.
(2021). Probabilistic Short-Term Low-Voltage Load Forecasting using Bernstein-Polynomial Normalizing Flows.
ICML 2021, Workshop Tackling Climate Change with Machine Learning, June 26, 2021, virtual.
Arpogaus2021_Probabilistic_Forecasting.pdf (427.35 KB)
(2021). ![application/pdf PDF icon](/modules/file/icons/application-pdf.png)