In many traditional computer graphics applications, rendered scenes typically utilize 3D meshes to represent objects within an environment. As the demand to further improve the realism of graphics applications increases, such as for movies and games, it is becoming more important to represent the inner volumes of object meshes. In...
The aim of this thesis is to study past 10 years of security vulnerabilities reported against Linux Kernel and all existing mitigation techniques that prevent the exploitation of those vulnerabilities. To systematically study the security vulnerabilities, they were categorized into classes and sub-classes based on their type.
This thesis first...
This thesis addresses the problem of temporal action segmentation in videos, where the goal is to label every video frame with the appropriate action class present. We focus on the domain of NFL football videos, where action classes represent common football play types. For action segmentation, we use a temporal...
The history of a software project plays a vital role in the software development process. Version control systems enable users of a software repository to look at the evolution of the source code, and see the changes that led to newer versions. Currently, version control systems provide commands that can...
This thesis considers the problem of training convolutional neural networks for online visual tracking. A major challenge for single object visual tracking is that most training sets with frame-level track annotations are quite small, due to the prohibitive cost of manual annotation. Current training approaches either supplement the annotations with...
Urban green space is associated with multiple physical and mental health outcomes. Several benefits of green space, such as stress reduction and attention restoration, are dependent on visual perception of green space exposures. However, traditional green space exposure measures do not capture street-level exposures. In this project, we apply deep...
Reasoning about 3D shape of objects is important for successful computer visionapplications in robotics, 3D rendering and modeling. In this thesis, we address twoproblems { First, given an image, we generate 3D shape of the foreground object thatappears in the image. Second, we predict the class label of the input...
Soft keyboards come in different shapes, sizes, and layouts. Each layout is designed to help the users in different inputting tasks. Most of these layouts, however, focus on general text entry as opposed to computer programs. This dissertation addresses the problems with current input mechanisms on touchscreen devices. The dissertation...
Many real world problems have partial solutions or intermediary steps which can lead toward solving the problem. When assembling robotic teams to solve these problems, we have intuition about which intermediary steps are more useful than others. We examine methods to identify and apply our designer intuition onto tightly coupled...
Markov Decision Processes (MDPs) are the de-facto formalism for studying sequential decision making problems with uncertainty, ranging from classical problems such as inventory control and path planning, to more complex problems such as reservoir control under rainfall uncertainty and emergency response optimization for fire and medical emergencies. Most prior research...