Teaching

Deep Learning for Papyri

The CVL offers bachelor/master theses or student projects in the domain of deep-learning-based document analysis for papyri. Supervisor: Marco Peer Status: open First Picture: Vesuvius Challenge Second Picture: Peer and Sablatnig, HIP’23 Third picture modified from FAU Erlangen Motivation Greek papyri, ancient documents made from a type of paper, offer valuable insights into the past. … Continue reading Deep Learning for Papyri

Templates for Scientific Communication and Presentation (SPCOM)

Reference description Example TeX Template: Reference description Informative Abstract Example TeX Template: Informative Abstract Extended Abstract Example TeX Template: IEEE Template as zip or via Overleaf (you can login via your student mail, free pro-version provided by TU) IEEE Word Template Complete Paper Example TeX Template: IEEE Template as zip or via Overleaf (you can … Continue reading Templates for Scientific Communication and Presentation (SPCOM)

Bias and Explainability in Long Term Care (LTC)

Internship/Master Thesis Status: available Supervisors: Martin Kampel Problem Statement Care work in long-term care (LTC) is considered as a genuine human-centred activity, requiring empathy, emotional investment, physical encounters and intimate, trust-based relations between various care-givers and care-recipients. AI technologies are introduced in this professional field to assist care workers in their daily activities and provide an … Continue reading Bias and Explainability in Long Term Care (LTC)

Self-Supervised 4D Point Cloud Feature Learning for Activity Recognition

Master Practical Training Project Status: available Supervisors: Irene Ballester, Martin Kampel Problem Statement This project aims to address the challenges associated with the expensive and time-consuming annotation of 3D data by exploring a self-supervised approach for the extraction of 4D spatio-temporal features from dynamic point cloud data. Specifically, the project investigates the prediction of the temporal … Continue reading Self-Supervised 4D Point Cloud Feature Learning for Activity Recognition

Human Activity Recognition from Real-World Depth Images

Master Practical Training Project/ Master’s thesis Status: available  taken (but if you would like to work on a similar topic, contact Irene Ballester) Supervisors: Irene Ballester, Martin Kampel Problem Statement Human Activity Recognition (HAR) in computer vision, a pivotal area for healthcare, security, and robotics, often relies on privacy-invading RGB cameras. To enhance HAR accuracy while … Continue reading Human Activity Recognition from Real-World Depth Images

A(RT)I – Finding and Recognizing Artwork

Status: available Supervisors: Martin Kampel   Abbildungen von Kunstgegenständen finden wir in Internetdatenbanken von Auktionshäusern, Kunstsammlern, Museen, aber auch in Sozialen Medien wie Facebook oder Instagram. Diese Abbildungen können professionell erstellt worden sein, oder durch eine Handyaufnahme eines Betrachters. Es kann sich um Kopien von Abbildungen handeln, oder von einer Darstellung originaler Kunst. Gemälde, chinesische … Continue reading A(RT)I – Finding and Recognizing Artwork

Writer Adaption for Handwritten Text Recognition of Historical Documents

Status: available Supervisors: Marco Peer The digitization and preservation of historical documents rely on accurate transcription of handwritten text. However, historical documents often present unique challenges due to variations in writing styles and deteriorated conditions. This thesis should explore the concepts of writer identification and writer-specific style extraction within Handwritten Text Recognition (HTR) systems, focusing … Continue reading Writer Adaption for Handwritten Text Recognition of Historical Documents

Learning Aggregation Functions for Writer Retrieval

Status: available Supervisors: Marco Peer, Florian Kleber Deep-learning-based methods for writer retrieval make use of sampling local characteristics of handwriting, for example using patches extracted at SIFT keypoint locations(see Figure 1), to learn discriminative features. To compute a global page descriptor of those local embeddings, state-of-the-art methods rely on fixed aggregation functions, e.g. sum/average pooling … Continue reading Learning Aggregation Functions for Writer Retrieval

Grundlagen der Computer Vision

Course description The lecture will cover advanced computer vision methods in depth: • Texture, Scenes, und Context • Local- and Multiscale Representations • Interest Points, Corners • Scene Emergent Features • Scene Recognition, Bag of Words, SIFT • Clustering, Pyramid Matching, Support Vector Machine • Deep Learning, CNNs • Perceptron, Linear Basis Function Models, RBF … Continue reading Grundlagen der Computer Vision

Car Occupants Counting from Near-Infrared Photos

Status: open Supervisor:  Robert Sablatnig Carpacity is a young company from Vienna that has recently finished a research project with the Institute of Spatial Planning at TU Wien. They use traffic sensors and LED walls to change how road traffic is analysed and stimulated. Its mission is to accelerate the decarbonisation of how people move … Continue reading Car Occupants Counting from Near-Infrared Photos