Search Constraints

Start Over
Filtering by: Creator Eskew, Evan A. Remove constraint Creator: Eskew, Evan A. Committee Member Li, Fuxin Remove constraint Committee Member: Li, Fuxin

Search Results

  • Counterfactual States for Atari Agents via Generative Deep Learning

    Creator:
    Olson, Matthew L.
    Abstract:
    Although deep reinforcement learning agents have produced impressive results in many domains, their decision making is difficult to explain to humans. To address this problem, past work has mainly focused on explaining why an action was chosen in a given state. A different type of explanation that is useful is...
    Resource Type:
    Masters Thesis
    Full Text:
    an action was chosen in a given state. A different type of explanation that is useful is a

  • Robust and Efficient Classification of Videos in the Wild

    Creator:
    Mahasseni, Behrooz
    Abstract:
    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...
    Resource Type:
    Dissertation
    Full Text:
    actions in videos is a long-standing problem in computer vision with a wide range of applications

  • Object Tracking-by-Segmentation in Videos

    Creator:
    Chen, Sheng
    Abstract:
    This thesis focuses on the problem of object tracking. Given a video, the general objective of tracking is to track the location over time of one or more targets in the image sequence. This is a very challenging task as algorithms need to deal with problems such as appearance variations,...
    Resource Type:
    Dissertation
    Full Text:
    object tracking. Given a video, the general objective of tracking is to track the location over time of

  • Explanations and Processes to Enable Humans to Assess AI with Respect to Manipulable Properties

    Creator:
    Dodge, Jonathan E.
    Abstract:
    Assessing AI systems is difficult. Humans rely on AI systems in increasing ways, both visible and invisible, meaning a variety of stakeholders need a variety of assessment tools (e.g., a professional auditor, a developer, and an end user all have different needs). We posit that it is possible to provide...
    Resource Type:
    Dissertation
    Full Text:
    ways, both visible and invisible, meaning a variety of stakeholders need a variety of assessment tools

  • Simultaneous segmentation and classification of bird song using CNN

    Creator:
    Narasimhan, Revathy
    Abstract:
    In bioacoustics, automatic animal voice detection and recognition from audio recordings is an emerging topic for animal preservation. Our research focuses on bird bioacoustics, where the goal is to segment bird syllables from the recording and predict the bird species for the syllables. Traditional methods for this task addresses the...
    Resource Type:
    Masters Thesis
    Full Text:
    errors. This work presents a new approach that performs simultaneous segmentation and classification of

  • Pixel- and Frame-level Video Labeling using Spatial and Temporal Convolutional Networks

    Creator:
    Lei, Peng
    Abstract:
    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...
    Resource Type:
    Dissertation
    Full Text:
    spatiotemporal video segmentation, we have developed recurrent temporal deep field (RTDF). RTDF is a conditional

  • Image Based Crypto

    Creator:
    Basa, Gungor
    Abstract:
    The ability to create reproducible cryptographically secure keys from temporal environments (e.g., images) has the potential to be a contributor to effective cryptographic mechanisms. Due to the noisy nature of these environments, achieving this goal in a user friendly fashion is a very challenging task, especially since there exists a...
    Resource Type:
    Masters Thesis
    Full Text:
    from temporal envi- ronments (e.g., images) has the potential to be a contributor to effective

  • Action Segmentation with Limited Supervision

    Creator:
    Li, Jun
    Abstract:
    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...
    Resource Type:
    Dissertation
    Full Text:
    class for each frame of a video. The limited supervision means ground truth labels of video frames are

  • Part-based and Uncertainty-Aware Few-shot Object Segmentation in Images

    Creator:
    Nguyen, Khoi D.
    Abstract:
    This dissertation addresses few-shot object segmentation in images. The goal of segmentation is to label every image pixel with a class of the object occupying that pixel, where the class may represent a semantic object category or instance. In few-shot segmentation, training and test datasets have different classes. Every new...
    Resource Type:
    Dissertation
    Full Text:
    image pixel with a class of the object occupying that pixel, where the class may represent a semantic

  • Large Scale Tensor Decomposition Algorithms Using Block-randomized Stochastic Proximal Gradient

    Creator:
    Gao, Cheng
    Abstract:
    We consider the problem of computing the cannonical polyadic decomposition (CPD) for large-scale dense tensors. This work is a combination of alternating least squares and fiber sampling. Data sparsity can be leveraged to handle large tensor CPD, but this route is not feasible for dense data. Inspired by stochastic optimization's...
    Resource Type:
    Masters Thesis
    Full Text:
    -scale dense tensors. This work is a combination of alternating least squares and fiber sampling. Data