Search Constraints

Start Over
Filtering by: Creator Bishop, Kevin W. Remove constraint Creator: Bishop, Kevin W. Advisor Todorovic, Sinisa Remove constraint Advisor: Todorovic, Sinisa

Search Results

  • 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

  • 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:
    parameters, and updated refined parameters. . . . . . . . . . 70 4.13 Evaluation of ACV w/out and w

  • Semantic image segmentation using domain constraints

    Creator:
    Roy, Anirban
    Abstract:
    This dissertation addresses the problem of semantic labeling of image pixels. In the course of our work, we considered different types of semantic labels, including object classes (e.g., car, person), 3D depth values (in the range 0 to 80 meters), and affordance classes (e.g., walkable, sittable). Semantic pixel labeling is...
    Resource Type:
    Dissertation
    Full Text:
    framework [95]. Our approach is employed without (w/o) each type of contextual relationship

  • Region based image matching for 3D object recognition

    Creator:
    Liu, Tian
    Abstract:
    3D object recognition is a very difficult and important problem in computer vision, arising in a wide range of applications. Typically in 3D object recognition, interest points are extracted from images and then matched. A shortcoming of this approach is that points only carry local visual information. Therefore, there could...
    Resource Type:
    Masters Thesis
    Full Text:
    , l) were matched in cdtw buu′vv′ = 1− 1/2(du′u′′ + dv′v′′); 4. w = (auu′ + avv′)/2 ∗ buu′vv′ , where

  • 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:
    computed by a standard temporal convolution, F (fL−11:T/2n ;W L). In (b), the output is computed using a

  • Object detection in biological images using a search-based framework

    Creator:
    Lam, Michael
    Abstract:
    This thesis addresses a basic problem in computer vision, that of semantic labeling of images. Our work is aimed at object detection in biological images for evolutionary biology research. In particular, our goal is to detect nematocysts in Scanning Electron Microscope (SEM) images. This biological domain presents challenges for existing...
    Resource Type:
    Masters Thesis
    Full Text:
    words, C(x, y) = wT φ(x, y) where φ(x, y) are features and w are the model param­ eters. The goal then

  • Annotation of image segments with ontologies (AISO)

    Creator:
    Lingutla Venkata, Nikhil Tej
    Abstract:
    This M.S thesis presents an interactive software tool that I have developed in the course of the past two years. This interactive tool is called AISO. AISO is aimed at interactive image segmentation and annotation tool designed to allow users to segment an image – such as those produced with...
    Resource Type:
    Masters Thesis
    Full Text:
    cooperative and helpful. I would also like to acknowledge the con- tribution of the Kevin McGuinnes of Dublin

  • 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:
    Fy,v,h(x) = w > v U >Φ(x, y,h), (2.1) where v is the viewpoint, and wv ∈ RD are the multiclass DPM

  • Action Segmentation in Videos: Deep Models, Prediction Diffusion, and Deep-Temporal Augmentations

    Creator:
    Aziere, Nicolas
    Abstract:
    This paper addresses the high model complexity and overconfident frame labeling of state-of-the-art (SOTA) action segmenters. Their complexity is typically justified by the need to sequentially refine action segmentation through multiple stages of a deep architecture. However, this multistage refinement does not take into account uncertainty of frame labeling predicted...
    Resource Type:
    Dissertation
    Full Text:
    standard MSA parameters, the hybrid MSA also learns the convolution filter wc and compression parameters W

  • 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:
    cost C functions are linear in the feature function ψ(x,y) that we will specify shortly: H(x,y) = w>Hψ