Past Theses
PhD Theses
-
Moritz Einfalt.?Human Motion Analysis on Visual Data - Shaping 2D Human Pose Estimation into a Tool for Sport and Medical Applications.?Dissertation, University of Augsburg, April 26,?2024. ( Official)
-
Stephan Brehm.?Image Manipulation and Image Synthesis -?Applications and Use-Cases Using Deep Neural Networks.?Dissertation, University of Augsburg, June 20,?2022. ( Official) [ PDF]
-
Philipp Harzig.?Automatic Generation of Natural Language Descriptions of Visual Data: Describing Images and Videos Using Recurrent and Self-Attentive Models.?Dissertation, University of Augsburg, March 4,?2022.?( Official) [ PDF]
-
Dan Zecha.?Motion Kinematics and Dynamics Prediction Using Human Pose Estimation in Videos: Towards Automated Kinematical Profiling of Swimmers and Ski Jumpers.
Dissertation, University of Augsburg, July 10, 2019.( Official) [ PDF] -
Christian Eggert.?Reliable Company Logo Detection with Deep Convolutional Neural Networks Addressing the Small Object Detection Problem.
Dissertation, University of Augsburg, Feb. 8, 2019.?( Official)?[ PDF ] -
Fabian Richter.?Virtual Reconstruction of Hand-Torn Documents using Discriminative Models.
Dissertation, University of Augsburg, Nov. 16, 2015. ( Official) [ PDF ] -
Christian Ries.?Automatic Object Annotations From Weakly Labeled Images.
Dissertation, University of Augsburg, Aug. 13, 2014.?[ PDF ] -
Stefan Romberg.?Aggregating Local Features into Bundles for High-Precision Object Retrieval.
Dissertation, University of Augsburg, Dec. 13, 2013.?[ PDF ] -
Johannes Schels.?Object Class Detection Using Part-Based Models Trained From Synthetically Generated Images.
Dissertation, University of Augsburg, Mar. 5, 2013.?[ PDF ] -
Eva H?rster.?Topic Models for Image Retrieval on Large-Scale Databases.
Dissertation, University of Augsburg, July 14, 2009.?[ PDF ]
Master and Diploma Theses
-
Moritz Lachenmayer.?Human Pose Estimation with Vision Transformer Backbones Operating on High Resolution Images.?Jan 2024
-
Lennart Eing.?Detecting Arbitrary Keypoints with VisionTransformer Backbones.?Jan 2024
-
Florian?Barthel.?Conditional Rendering of 3D Object from 2D Images Using Deep Generative Neural Networks. March?2022
-
Henning Cui.?Semi-Supervised Learning for Cross-Domain Semantic Segmentation Applications. November 2021.
-
Andre Schweiger. Visual Question Answering with Transformer Architecture. October 2021.
-
Jonas Rothe. Maschinell gelernte Unsicherheitssch?tzungen für Sensordaten zur Absicherung automatisierter Fahrfunktionen. September 2021.
-
Alexander Oesterling.?Textklassifizierung in Ticketsystemen: Aufbau eines neuronalen Netzwerks und Klassifikationsalgorithmus für das Open-Source-Programm OTOBO. March 2021.
-
Lena Kornd?rfer.?Examination of Basic Models for Automated Captioning of Video Sequences. January 2021.
-
Robin Sch?n. Learning Semantic Segmentation from Synthetic Data using Generative Adversarial Networks. January 2021.
-
Christine Hulm.?Image Captioning mit hierarchischen rekurrenten Netzen. December 2020.
-
Alessandro Russo. Analysis of Domain Adaptability for 3D Human Pose Estimation with Explicit Body Shape Models. October 2020
- Konrad Habel.?Image Captioning with Deep Neural Networks and Explicit Attention Models. March 2019
-
Simon Trieb.?An Advanced View on Techniques in Visual Question Answering - Augmentation, Attention and Regularization. March 2019
-
Julian Manuel Zauner.?Merkmalsbasierte Kantenerkennung in unstrukturierten Punktwolken. January 2019.
-
Roman Sraj.?Gelernte ?hnlichkeit für die schnelle Rekonstruktion von zerrissenen Dokumenten. September 2018
-
Yulia Khlyaka.Image Captioning with Deep Neural Networks and Explicit Attention Models. August 2018.
-
Moritz Einfalt.?An Analysis of Convolutional Pose Machines – Improvements, Extensions and Applications. June 2017. [ PDF]
-
Markus Wirth.?Object Detection from Low-Resolution Feature Representations. March 2017
-
Ludwig Meyer.?Erkennung korrekter Ausrichtung von Dokumentenfragmenten mittels tiefer neuronaler Netze. September 2016
-
Stephan Brehm.?Deep Convolutional Neural Networks for Object Segmentation and Part Labeling. August 2016
-
Anton Winschel.?Generierung von Objekthypothesen mittels tiefer Faltungsnetze. May 2016.?[ PDF ]
-
Philipp Harzig.?Implementation of Frequency Domain Convolution for the Caffe-Framework. February 2016.?[ PDF ]
-
Roman Hehl.?Visuelle Odometrie - Implementierung eines bildgestützten Verfahrens zur Berechnung der Eigenbewegung eines Einkamerasystems. May 2015.
-
Moritz Laudahn.?Umsetzung ausgew?hlter Aspekte von Deformable Part Models auf FPGAs.?July 2014.?[ PDF ]
-
Quyen Hoang.?Efficient Object Detection with Branch-and-Bound. June 2013.
-
Dan Zecha.?An Analysis and Efficient Implementation of Felzenszwalb's Object Detection System. March 2013.?[ PDF ]
-
Christian Eggert.?Implementation and Evaluation of the gPb Contour Detector. August 2012.?[ PDF ]
-
Christoph Lassner.?An Analysis of Successful Approaches to Human Pose Estimation. May 2012.?[ PDF ]
-
Georg D?hring.?Estimating Planes in Images from Cellphones and noisy Sensor Data. January 2012.
-
Christian Loos.?Vectorization of Pixel Art. January 2012.?[ PDF ]
-
Michael Lugmair.?Viewpoint Learning and Pose Estimation in Videos. June 2011.
-
Elnaz Alyari.?Automatische Vordergrund/Hintergrundsegmentierung in Videos mit stark verrauschtem Hintergrund. April 2011.
-
Fabian Richter.?Tag Relevance for Image Retrieval. November 2009.?[ PDF ]
-
Christian Ries.?Automatic Pose Initialization of Swimmers in Videos. April 2009. [ PDF ]
-
Thomas Greif.?A Probabilistic Motion Model for Swimmers: A Computer Vision Approach. March 2009.?[ PDF ]
-
Sebastian Adolf.?Pitch Shifting and Time Warping.? December 2008.
-
Stefan Romberg.?Image Retrieval on Large Community Databases. November 2008. [ PDF ]
-
Carde-Michaela Hackbarth.?Untersuchung von Bildauswertungsalgorithmen zur Abstandsbestimmung mit Stereokamerasystemen. November 2008. [ PDF ]
-
Ingo Reese.?Schnitterkennung für komplexe ?berg?nge in Videos. March 2008. [ PDF ]
-
Sandra Witt.?Face Recognition using Bayesian Networks. September 2007.
-
Thomas Meidl.?Audio2MIDI: A System for Converting Audio Recordings to MIDI. August 2007.?[ PDF ]
-
Cristina Anton.?Text Localization and Recognition with Salient Points in Images. May 2007.
-
Rui Dong.?Multimedia Search Engine.? March 2007.
-
Viktor Schellenberg.?Objektklassenerkennung mittels Boundary Fragment Model. March 2007.
-
Christopulu Konstadina.?Automatische Klassifikation auf optischen Datentr?gern. Februray 2007 (jointly with company Dr.Schwab)
-
Jochen Wenzel.?Untersuchung zur bilddatenorientierten Regelung des Farbregisters in Rollendruckmaschinen. December 2006 (jointly with MAN Roland Druckmaschinen AG)
-
Jochen Lux.?Learning People's Appearances from Multiple Views. September 2006.?[ PDF ]
-
Eva H?rster.?Calibration of Cameras and Displays in a Distributed Computing Platform. December 2004.?[ PDF ]
Bachelor Theses
-
Nourhen Khiari.?Usage of the Segment Anything Model for Scribble-based Segmentation. May?2024.
-
Lukas Bayer.?Incorporating Token Merging into Transformers for Efficient Ground State Search of Quantum Spin Models Using minSR. May 2024.
-
Raphael Arndt.?Imitating and Learning Physically Plausible 3D Human Motion with MuJoCo. April 2024.
-
Simon Reichert.?Exploring Image Registration Techniques for XANES Data using Traditional Methods and Machine Learning Techniques. April 2024.
-
Bui Tuan.?Bidirectional Mapping Between Antrophometric Measurements and SMPL(-X) Human Mesh Models. April 2024.
-
Alexander Pest.?Domain-Specific Evaluation Metrics of Deep Learning Models for Scene Graph Generation. April 2024.
-
Ghazi Jallouli.?Test Time Adaptation of Neural Networks with a Minimum of Additional Parameters. January 2024.
?
-
Ludwig Holl. Semi-supervised neural network learning for visual relationship recognition (in German). October 2023.
-
Eloy da Silva Benze.?Rendering and Analyzing the Human Mesh Model. September 2023
-
Jan Claar, Measurement of Droplets in Vaporized Fluids using Machine Learning Techniques.?March 2023
-
Johannes F?rth.?Learning Semantic Segmentation from Bounding Box Annotations. March 2023.
-
Thomas Schmitz.?Generating Synthetic Human Pose Datasets with Highly Diverse Poses. February 2023.
-
Marcel Nowocyn.?Generierung von synthetischen Dantens?tzen mit kontrollierbaren visuellen Beziehungen. January 2023
?
-
Jonathan Leis. An Evaluation of Real-Time 2D-to-3D Pose Lifting Transformers. October 2022.
-
Jonas Kell. Investigation of transformer architectures for geometrical graph structures and their application to two-dimensional spin systems. October 2022.
-
Tim Lukas Dirr. Decoder Architectures for Retraining Full Resolution in Semantic Segmentation. September 2022. [ PDF ]
-
Marco Riedenauer.?Integrating Keypoint Classification in Semi-Supervised Human Pose Estimation. August 2022.
-
Dominik Schwer.?Semi-Supervised Learning for Unsupervised Domain Adaptation in Semantic Segmentation. June?2022.
-
Johannes Moll.?Analysis of Unsupervised Representation Learning for Image Classification. May?2022.
-
Reinhard Johannes Seidl.?Analyzing Different Network Target Variants for Human Pose Estimation. March 2022.
-
Dominik Witoschek. Semi-Supervised 3D Human Pose Estimation via Sequence-based Pseudo Annotations. February 2022.
-
Orelle Nguekeng Djazet. Semi-Supervised Learning for Image Classification. February 2022.
-
Simon Graeber. Generating Synthetic Bounding Box Datasets with Controllable Complexity.?February 2022.
-
Thomas Schmitz.?Generating Synthetic Human Pose Datasets with Highly Diverse Poses.?February 2022.
-
Patrick Hopf. Temporal Dynamics in Quantum Billiards Using Neural Networks (in German). January 2022.
?
-
Boodo Ba Elouga Frank Pavel.?Integrating Keypoint Classification in Semi-Supervised Human Pose Estimation. November 2021.
-
Michael Danzer.?Self-Supervised Learning for Unsupervised Domain Adaptation in Image Classification. September 2021.
-
Boris Hristov.?Unsupervided Domain Adaptation for Semantic Segmentation using Image-to-Image Translation. September 2021.
-
Stefan Jung.?Maximize the Recognition Performance of HRNet-like Backbones with Low Computational Complexity (in German). September 2021.
-
Yannick Steinhage. Robust Learning from Noisy Labels with Deep Neural Networks. May?2021.
-
Lena Kornd?rfer. Examination of Basic Models for Automated Captioning of Video Sequences. January 2021.
?
-
Florian Barthel. An Extensive Study of the StyleGAN Architecture for Deep Image Synthesis. September 2020
-
Maximilian Gartner. Stragegien zur Modellierung und Extraktion meschlicher K?rperpunkte in Bildern mittels tiefer Faltungsnetze. August 2020.
-
Florian Kimmel. Analyse von Wordvektoren (Word2Vec) unter Betrachtung von verschiedenen Modellen und Datens?tzen. August 2020.
-
Simone Pompe. Image Expansion with Deep Generative Adversarial?Networks. August 2020
-
Joachim Wichert. Integration of AMASS into 3D Human Pose Estimation with Explicit Body Shape Models. July 2020
?
-
Georg Staber.?K?nnen 3D-Absch?tzungen von 2D-Posen durch Betrachtung von Sequenzen von 2D-Posen verbessert werden? October 2019
-
Nikolas Klug. Effects of Pose Normalization on Weakly Supervised?3D Human Pose Estimation. September 2019
-
Henning Cui.?Adversarial Reprojektion Networks for 3D Human Pose Estimation.?September 2019
-
Joachim Meyer. Comparison of modern GPGPU technologies for use in image processing libraries by the example of processing polarization-camera images. September 2019.?
-
Thomas Glamsch.?An Appplication of Dense Pose for 3D Head Pose Estimation. May 2019.
-
Andre Michael Schweiger.?Image Super-resolution using Deep Generative Adversarial Networks. May 2019.
-
Jan Hüttemann.?SSD with Deep Layer Aggregation for Small Company Logo Detection. March 2019.
-
Leon Jakob Schneider.?Manipulation von Objektfarben in Bildern mit Hilfe von tiefen neuronalen Netzen. Januar 2019.
?
-
Fabio Tempelmann.?Posenerhaltende Bildausrichtung für parallele nicht-überlappende Kameraansichten. November 2018.
-
Marcel Schneider.?Tiefe neuronale Faltungsnetze zur Erkennung von Lungenkrankheiten auf Thorax-R?ntgenaufnahmen. August 2018.
-
Martin Lautenbacher.?Visualizing the Effects of Fine-Tuning in Deep Neural Networks. March 2018.
?
-
Leon W?hrl.?Logoklassifikation mit tiefen neuronalen Netzen – Eine Untersuchung des Zusammenhangs zwischen Objektgr??e und Wahrnehmungsbereich. October 2017.
-
Daniel Bermuth.?Implementierung und Evaluation von BinaryConnect. August 2017.
?
-
Leonhard Melzer.?Evaluating Training Set Augmentation for Logo Recognition with Deep Convolutional Neural Networks. December 2015.
-
Christian Diller.?Implementation and Evaluation of Spatial Pyramid Pooling in Deep Convolutional Neural Networks. October 2015.
-
Philipp Herrle.?Sovling Square Jigsaw Puzzles with Genetic Algorithm. August 2015.
-
Daniel Born.?Relative Positionssch?tzung anderer Flugobjekte mit Hilfe von Stereokameras an Bord eines Multicoptors. July 2015.
-
Benedikt Jenik.?Logo Detection with Deep Neural Networks Using the Caffe Framework. May 2015.
-
Ingo Sewing.?Training and Selecting Poselets for People Detection. January 2015.
?
-
Moritz Einfalt.?Decision Forests for Regression. September 2014. [ PDF]
-
Martin Osiadly.?Effziente Implementierung eines Wavelet-basierten Algorithmus zur Entrauschung mehrkanaliger Videodaten. September 2014.
?
-
Thomas Ossowski.?Unüberwachte Bestimmung von Unterkategorien aus Bildern einer Objektklasse aus unterschiedlichen Blickrichtungen. December 2013.
-
Anton Winschel.?Random Forests zur Sch?tzung menschlicher Posen. November 2013.
-
Macro Schumacher.?拉斯维加斯赌城 von 3D-Teilobjekten in einer 3D-Datenbank. January 2013.
?
-
Moritz August.?Partition Min-Hash. September 2012.?[ PDF ]
-
Jennifer Seitz.?Partition Min-Hash in der Bildsuche. August 2012
-
Jessica Seitz.?Schwache geometrische Konsistenzprüfung bei der Bildsuche. August 2012
-
Christoph Wei?.?Finding Correspondences Between Local Image Features Using Graph Matching. March 2012.
?
-
Moritz Laudahn.?Ein Modell zur automatischen Bestimmung von Gelenkmittelpunkten anhand von 3D?Motion Capture-Daten. August 2011.?[ PDF ]
-
Dan Zecha.?Detecting Swimmers and Estimating their Pose in a Swimming Channel. June 2011.?[ PDF ]
-
To Quyen Hoang.?Evaluating the Robustness of Local Image Features. April. 2011.?[ PDF ]
?
-
Markus Neubert.?Sound Fontenizer: Automatic Generation of Sample Based Wabetables for Music Synthesis. June. 2009.
-
Tobias Schmidl.?Live Stream Audio Analysis. March 2009.
-
Michael Lugmair.?Score Following. March. 2009.?[ PDF ]
?
-
Georg D?hring.?Music Retrieval with Active Learning and Support Vector Machines. September 2008.
?
-
Thomas Greif.?Implementierung eines formbasierten Regionenmerkmals. September 2007.?[ PDF ]
-
Christian X. Ries.?FliDo - Ein Werkzeug zum interaktiven Herunterladen von Bildern mit der Flickr API. June 2007.?[ PDF ]
-
Lars-Christian Larsen.?Entwicklung eines Frameworks für ein Audio-Indizierungs-Plugin in der Google-Desktop-拉斯维加斯赌城. February 2007.?[ PDF ]
-
Florian Lingenfelser.?Music Genre Classification. February 2007.
?
-
Annika Schulz.?Implementierung eines aktiven Lernansatzes. October 2006?[ PDF ]
-
Daniel Lercher.?Automatische Gesichtserkennung für Filmcharaktere. September 2006?[ PDF ]
-
Frank Jung.?Objekterkennung mit SIFT-Features. September 2006?[ PDF ]
-
Sebastian Adolf.?Erstellung einer optimierten JAVA-GUI zur Visualisierung und Bearbeitung von Audio. February 2006?[ PDF ]