Search Constraints

Start Over
Filtering by: Creator Hadley, Adam S. Remove constraint Creator: Hadley, Adam S. Advisor Todorovic, Sinisa Remove constraint Advisor: Todorovic, Sinisa

Search Results

  • 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:
    frames within a window centered at bn (the black rectangles), and corresponding new edges (vns, vn′s

  • Relational Networks for Visual Relationship Detection in Images

    Creator:
    Nguyen, Khoi
    Abstract:
    This thesis is about visual relationship detection. This is an important task in computer vision. The goal is to detect all visual relationships in a given image between objects. This thesis presents a new approach to this problem. Our approach does not use an object detector as a common pre-processing...
    Resource Type:
    Masters Thesis
    Full Text:
    v is u a l re la ti o n sh ip d et ec ti o n . It h a s fo u r m o d u le s: o b je

  • A Deep Action Segmentation and Its Explanation with a Dictionary of Meaningful Attention Maps

    Creator:
    Trigkakis, Dimitrios
    Abstract:
    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...
    Resource Type:
    Masters Thesis
    Full Text:
    use a learning rate of 1e−4 and weight decay 1e−6 as the hyper-parameters of the Adam optimizer [8

  • 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:
    classification accuracy of the proposed regularized LSTM r different αs 41 4.1 Overview of our generative video

  • 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:
    in a query image, given a single (few) support image(s) showing the same class with the known ground

  • 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:
    boundary, we will need to then move xt so that they fall on the same side. Note that s1 and s2, s ′ 1 and

  • 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:
    for computing the heuristic function, S-layer for realizing the successor function, and Long Short

  • Window Axial Vision Transformer for Image Classification

    Creator:
    Lee, Jisoo
    Abstract:
    Currently, a popular approach to image classification uses the deep Transformer architecture. In a Transformer, the attention mechanism enables the model to learn efficiently with fewer computational resources than the convolutional neural networks (CNNs). In this thesis, we study the sparse attention mechanism widely used in the Transformers developed specifically...
    Resource Type:
    Masters Thesis
    Full Text:
    [1] Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel

  • Efficient Incremental Panorama Reconstruction from Multiple Videos

    Creator:
    Feng, Zhongyuan
    Abstract:
    Constructing a panorama from a set of videos is a long-standing problem in computer vision. A panorama represents an enhanced still-image representation of an entire scene captured in a set of videos, where each video shows only a part of the scene. Importantly, a panorama shows only the scene background,...
    Resource Type:
    Capstone Project
    Full Text:
    parameter predefined as 0.6 in practice. 3© similarity distance s(i,j), indicating how similar H(i,j) is to

  • 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:
    3.2 The T at stage s enhances features of a query video segment X (s) i based on compressed