N-ary relationships, which relate N entities where N is not necessarily two, are omnipresent in real life. In this thesis, we develop a visualization technique for N-ary relationships.
First, we propose a visual metaphor that utilizes vertices and polygons to represent entities and N-ary relationships. Based on this visual metaphor,...
Secure Computation is a powerful tool that enables a set of parties to jointly compute any function over their private inputs, without a trusted third party. Private Set Intersection is a specific case of two-party Secure Computation, where Alice (with private set X) and Bob (with private set Y) specifically...
The outsourcing of data storage and related infrastructure to third-party services in the cloud is a trend that has gained considerable momentum in the last decade due to the savings it affords companies in both capital and operational costs. Although encryption can alleviate some of the privacy concerns associated with...
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...
This dissertation addresses the problem of video labeling at both the frame and pixel levels using deep learning. For pixel-level video labeling, we have studied two problems: i) Spatiotemporal video segmentation and ii) Boundary detection and boundary flow estimation. For the problem of spatiotemporal video segmentation, we have developed recurrent...
Intuitively, it seems as though natural language processing tasks might benefit from explicit representations of the syntactic and semantic properties of text. Ontonotes is a dataset which attempts to annotate texts, to represent as much as possible of the meaning of the text explicitly within the annotation. Many tools exist...
In this dissertation, we address action segmentation in videos under limited supervision. The goal of action segmentation is to predict an action class for each frame of a video. The limited supervision means ground truth labels of video frames are not available in training. We focus on three types of...
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...
Many database users are not familiar with formal query languages, the concept of schema, or the exact content of their database. Thus, it is challenging for these users to formulate their information needs over semi-structured and structured databases. To address this problem, researchers have proposed usable query interfaces over which...
Recognizing human actions in videos is a long-standing problem in computer vision with a wide range of applications including video surveillance, content retrieval, and sports analysis. This thesis focuses on addressing efficiency and robustness of video classification in unconstrained real-world settings. The thesis work can be broadly divided into four...