Search Constraints

Start Over
Filtering by: Creator Bogan, Michael T. Remove constraint Creator: Bogan, Michael T. Committee Member Fern, Alan Remove constraint Committee Member: Fern, Alan Resource Type Dissertation Remove constraint Resource Type: Dissertation

Search Results

  • Fine-Grained Object Recognition Under Limited Training Data

    Creator:
    Lam, Michael Q.
    Abstract:
    This dissertation addresses object recognition in challenging settings, where distinct object classes are visually very similar (e.g., species of birds and insects) and/or access to training examples of object classes is limited (e.g., due to the associated high costs of data annotation). In this dissertation, we present a variety of...
    Resource Type:
    Dissertation
    Full Text:
    AN ABSTRACT OF THE DISSERTATION OF Michael Lam for the

  • From shape-based object recognition and discovery to 3D scene interpretation

    Creator:
    Payet, Nadia
    Abstract:
    This dissertation addresses a number of inter-related and fundamental problems in computer vision. Specifically, we address object discovery, recognition, segmentation, and 3D pose estimation in images, as well as 3D scene reconstruction and scene interpretation. The key ideas behind our approaches include using shape as a basic object feature, and...
    Resource Type:
    Dissertation
    Full Text:
    contours s′ in a vicinity of u′ and auxiliary contours t′ in a vicinity of v′. For every neighbor s′ of u

  • 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:
    , Tieqiao Wang, Peng Lei, Dimitrios Trigkakis, Michael Lam, Anirban Roy, and Behrooz Mahasseni. I would

  • Improving automated email tagging with implicit feedback

    Creator:
    Sorower, Mohammad Shahed
    Abstract:
    Machine learning systems are generally trained offline using ground truth data that has been labeled by experts. However, these batch training methods are not a good fit for many applications, especially in the cases where complete ground truth data is not available for offline training. In addition, batch methods do...
    Resource Type:
    Dissertation
    Full Text:
    . However, these batch training methods are not a good �t for many applications, especially in the cases

  • From multitarget tracking to event recognition in videos

    Creator:
    Brendel, William
    Abstract:
    This dissertation addresses two fundamental problems in computer vision—namely, multitarget tracking and event recognition in videos. These problems are challenging because uncertainty may arise from a host of sources, including motion blur, occlusions, and dynamic cluttered backgrounds. We show that these challenges can be successfully addressed by using a multiscale,...
    Resource Type:
    Dissertation
    Full Text:
    activities. These spatiotemporal subvolumes are also referred to as 2D+t tracks, or tubes. We consider real

  • 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:
    , Anirban Roy, Michael Lam, Sheng Chen, Peng Lei, Christos Margiolas, Alberto Garcia, Suren Jayasuriya and

  • Efficient training and feature induction in sequential supervised learning

    Creator:
    Hao, Guohua
    Abstract:
    Sequential supervised learning problems arise in many real applications. This dissertation focuses on two important research directions in sequential supervised learning: efficient training and feature induction. In the direction of efficient training, we study the training of conditional random fields (CRFs), which provide a flexible and powerful model for sequential...
    Resource Type:
    Dissertation
    Full Text:
    each Yi = (yi,1, . . . , yi,Ti) is a correspond- ing sequence of class labels, where yi,t ∈ Y = {1

  • 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:
    with T frames with a transcript of N ordered actions, there are (N+T )!N !T ! possible labelings for

  • Anomaly Detection and Probabilistic Diagnosis for Automated Data Quality Control

    Creator:
    Zemicheal, Tadesse H.
    Abstract:
    Advances in sensor technology are greatly expanding the range of quantities that can be measured while simultaneously reducing the cost. However, deployed sensors drift out of calibration and fail, so every sensor network requires quality control procedures to promptly detect these failures. To address these problems, we propose a two-level...
    Resource Type:
    Dissertation
    Full Text:
    would like to thank Dr. John Selker and Dr. Michael Piasecki for their valuable guidance and feedback

  • Behavior graphs for data-driven animation of 3d characters

    Creator:
    Srinivasan, Madhusudhanan
    Abstract:
    In this dissertation, we present a user-in-the-loop method for the design of an interactive motion data structure that benefits from the advantages of both motion graphs and blend-based techniques. Our novel approach automatically analyzes a traditional motion graph built from labeled motion clips. The result is a more condensed, coarser...
    Resource Type:
    Dissertation
    Full Text:
    requested. 70 6.2 An overview of our character navigation system. At each time- step t, the steering model