Daniel Kienzle

Research Assistant & PhD Student
Chair for Machine Learning & Computer Vision
Phone: +49 (821) 598 2451
Email:
Room: 1018 (N)
Opening hours: by appointment
Address: Universitätsstraße 6a, 86159 Augsburg

CV

Ausbildung:
2021--Now   PhD in Machine Learning & Computer Vision at University of Augsburg
2018--2021   Master of Science in Solid State Physics at University of Augsburg
2015--2018    Bachelor of Science in Physics at University of Augsburg
 
 
Forschungsinteressen:
  • Physics in Machine Learning
  • Object Localization
  • Pose Estimation
  • Self-supervised learning
 
Über mich:  
I am a Master's graduate in Physics who is now pursuing a PhD in Machine Learning and Computer Vision. I am interested in the intersection of Deep Learning, Image Processing, and Physics. In my previous research, I have investigated how physical knowledge can be exploited for the training process of a neural network.

Publications

2024 | 2023 | 2022

2024

Daniel Kienzle, Katja Ludwig, Julian Lorenz and Rainer Lienhart. in press. Towards learning monocular 3D object localization from 2D labels using the physical laws of motion. DOI: 10.48550/arXiv.2310.17462
PDF | BibTeX | RIS | DOI

2023

Daniel Kienzle, Julian Lorenz, Robin Schön, Katja Ludwig and Rainer Lienhart. 2023. COVID detection and severity prediction with 3D-ConvNeXt and custom pretrainings. DOI: 10.1007/978-3-031-25082-8_33
PDF | BibTeX | RIS | DOI

Katja Ludwig, Daniel Kienzle, Julian Lorenz and Rainer Lienhart. 2023. Detecting arbitrary keypoints on limbs and skis with sparse partly correct segmentation masks. DOI: 10.1109/WACVW58289.2023.00051
PDF | BibTeX | RIS | DOI

Julian Lorenz, Florian Barthel, Daniel Kienzle and Rainer Lienhart. 2023. Haystack: a panoptic scene graph dataset to evaluate rare predicate classes. DOI: 10.1109/ICCVW60793.2023.00013
PDF | BibTeX | RIS | DOI

Luuk H. Boulogne, Julian Lorenz, Daniel Kienzle, Robin Schön, Katja Ludwig, Rainer Lienhart, Simon Jegou, Guang Li, Cong Chen, Qi Wang, Derik Shi, Mayug Maniparambil, Dominik Müller, Silvan Mertes, Niklas Schröter, Fabio Hellmann, Miriam Elia, Ine Dirks, Matias Nicolas Bossa, Abel Diaz Berenguer, Tanmoy Mukherjee, Jef Vandemeulebroucke, Hichem Sahli, Nikos Deligiannis, Panagiotis Gonidakis, Ngoc Dung Huynh, Imran Razzak, Reda Bouadjenek, Mario Verdicchio, Pasquale Borrelli, Marco Aiello, James A. Meakin, Alexander Lemm, Christoph Russ, Razvan Ionasec, Nikos Paragios, Bram van Ginneken and Marie-Pierre Revel Dubios. in press. The STOIC2021 COVID-19 AI challenge: applying reusable training methodologies to private data.
BibTeX | RIS | URL

2022

Katja Ludwig, Daniel Kienzle and Rainer Lienhart. 2022. Recognition of freely selected keypoints on human limbs. DOI: 10.1109/CVPRW56347.2022.00397
PDF | BibTeX | RIS | DOI

Supervised Theses

  • Clarissa Dinu-Fröhlich, Erstellung von Modellen zur Semantischen Segmentierung von Körperteilen unter Verwendung von schwachen Segementierungsmasken, Projectmodule, June 2023
  • Jan Claar, Measurement of Droplets in Vaporized Fluids using Machine Learning Techniques, Bachelorthesis, March 2023
  • Jonas Kell, Investigation of transformer architectures for geometrical graph structures and their application to two-dimensional spin systems, Bachelorthesis, October 2022
  • Patrick Hopf, Zeitliche Dynamik in Quantenbillards mit Hilfe neuronaler Netze, Bachelorthesis, December 2021

 

 

 

Search