E-Dissertationen: Search
Now showing items 1-10 of 24
On Modeling and Assessing Uncertainty Estimates in Neural Learning Systems
(2023-04-20)
While neural networks are universal function approximators when looked at from a theoretical perspective, we face, in practice, model size constraints and highly sparse data samples from open-world contexts. These limitations ......
Self-Supervised Video Representation Learning and Downstream Applications
(2023-05-12)
Video understanding is an important computer vision task with a great variety of different applications, such as autonomous driving, robotics and video surveillance. Much progress has recently been made on video understanding ...
Robust Information Extraction From Unstructured Documents
(2023-01-03)
In computer science, robustness can be thought of as the ability of a system to handle erroneous or nonstandard input during execution. This thesis studies the robustness of the methods that extract structured information ...
Multiplexing and Multi-Mode Super-Resolution for Digital Material Appearance
(2023-01-30)
The visual appearance of materials on the surface of objects contributes greatly to the overall perception of virtually every scene we encounter every day. However, complex material appearance can be neigh impossible to ...
Contextualizing and interpreting biological data with pathway knowledge and network algorithms
(2023-02-07)
Elucidating the mechanisms which give rise to unique biological functions is a major goal of human biology. Vast quantities of biological data that have been amassed can aid us in understanding these mechanisms, such as ...
Towards Practical Real-time Reflectance Estimation
(2023-02-22)
Virtual experiences are becoming increasingly popular, primarily due to tremendous progress in Virtual Reality (VR) and Augmented Reality (AR) technologies improving immersion and making related devices more affordable. ...
Visual Prototyping of Knitwear
(2023-07-25)
In this thesis, we address the problem of prediction and editing of the virtual appearance of knitted cloth. Among the most accurate approaches to model fabrics and other complex materials is to represent them in terms of ...
Temporal Action Segmentation: Weak Supervision and Efficiency
(2023-08-24)
Action segmentation deals with the temporal understanding of actions that occur in an untrimmed video. The output of action segmentation is an action label for each frame of the input video. This task has recently received ...
Investigating Graph Representation Learning Methods For Link Prediction in Knowledge Graphs
(2023-11-03)
Knowledge Graphs (KGs) have become a fundamental approach to represent structured data and are employed in academic and industrial applications.
KGs are used in various machine learning applications, such as question ...
Robust and Interpretable Visual Perception Using Deep Neural Networks
(2023-01-11)
Autonomous vehicles promise to revolutionize the transportation of people and goods by increasing road safety, reducing resource consumption, and improving quality of life. To achieve an unrestricted and large-scale ......