Search Constraints

Start Over
Filtering by: Has journal International Journal of Computer Vision Remove constraint Has journal: International Journal of Computer Vision License All rights reserved Remove constraint License: All rights reserved

Search Results

  • Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression

    Creator:
    Wang, Xinyao
    Abstract:
    Heatmap regression has became one of the mainstream approaches to localize facial landmarks. As Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) are becoming popular in solving computer vision tasks, extensive research has been done on these architectures. However, the loss function for heatmap regression is rarely studied. In...
    Resource Type:
    Masters Thesis
    Full Text:
    of Master of Science in Computer Science presented on December 7, 2018. Title: Adaptive Wing Loss

  • Analysis of bio-based composites for image segmentation with the aid of games

    Creator:
    Inouye, Jennifer A.
    Abstract:
    A fundamental problem in computer vision is to partition an image into meaningful segments. While image segmentation is required by many applications, the thesis focuses on segmentation of computed tomography (CT) images for analysis and quality control of composite materials. The key research contribution of this thesis is a novel...
    Resource Type:
    Masters Thesis
    Full Text:
    testing of the computer vision algorithm, which we can use to track the area and volume of these

  • Learning affinities of exemplar videos for multi-view action recognition

    Creator:
    Roy, Anirban
    Abstract:
    This thesis addresses a fundamental computer vision problem, that of action recognition. The goal of action recognition is to recognize a class of human actions in a given video. Action recognition has a wide range of applications, including automated surveillance, sports video analysis, internet-based searches etc. The main challenge is...
    Resource Type:
    Masters Thesis
    Full Text:
    addresses a fundamental computer vision problem, that of action recognition. The goal of action recognition

  • 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:
    of Doctor of Philosophy in Computer Science presented on December 7, 2018. Title: Pixel- and Frame

  • Video Object Segmentation by Jointly Tracking Foreground and Background

    Creator:
    Borkar, Rahul
    Abstract:
    This report presents an efficient method for semi-supervised video object segmentation – the problem of identifying foreground pixels occupied by a target object. The target is specified by the ground-truth mask in the first video frame. While the state of the art achieves a segmentation accuracy greater than 80%, it...
    Resource Type:
    Capstone Project
    Full Text:
    various types of fields. Particular to the field of computer vision, Convo- lutional Neural Networks

  • Computer vision for geometrical analysis of bridge gusset plates

    Creator:
    Varakantham, Shravya
    Abstract:
    Gusset plates are an important component of bridges. They are thick sheets of steel that join steel members together using fasteners and also strengthen their joint. Transportation agencies regularly evaluate and rate their inventories of gusset plate connections using visual inspection, which is very costly. To address this issue, we...
    Resource Type:
    Masters Thesis
    Full Text:
    October 24, 2014. Title: Computer Vision for Geometrical Analysis of Bridge Gusset Plates. Abstract

  • Toward computer vision for understanding American football in video

    Creator:
    Hess, Robin W.
    Abstract:
    In this work, I examine the problem of understanding American football in video. In particular, I present several mid-level computer vision algorithms that each accomplish a different sub-task within a larger system for annotating, interpreting, and analyzing collections of American football video. The analysis of football video is useful in...
    Resource Type:
    Dissertation
    Full Text:
    and other markings, computer vision algorithms developed towards the end goal of understanding

  • 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:
    degree of Doctor of Philosophy in Computer Science presented on April 25, 2011. Title: From Multitarget

  • Automated Monitoring of Modular Construction Factories using Computer Vision

    Creator:
    Panahi, Roshan
    Abstract:
    Modular construction is increasingly seen as an efficient construction method in terms of time, cost, and energy. The full realization of these advantages partly relies on the efficiency of the production process inside the modular factories, which currently rely on tedious manual monitoring methods or expensive automated techniques. As a...
    Resource Type:
    Dissertation
    Full Text:
    . Title: Automated Monitoring of Modular Construction Factories using Computer Vision. Abstract

  • Offensive Direction Inference in Real-World Football Video

    Creator:
    Lu, Qingkai
    Abstract:
    Automatic analysis of American football videos can help teams develop strategies and extract patterns with less human effort. In this work, we focus on the problem of automatically determining which team is on offense/defense, which is an important subproblem for higher-level analysis. While seemingly mundane, this problem is quite challenging...
    Resource Type:
    Masters Thesis
    Full Text:
    of computer vision, which aims at automatically analysing ongoing events and their contexts from