Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 85 for “"Visual Understanding"”.

  1. Language-based Visual Understanding

    … some important problems in Language-based Visual Understanding. First, we study the problem of Image Captioning. We introduce the Discrete Mode Learning (DML) paradigm to address the “mode collapse” problem in existing methods. It consists of a conditioned discrete variational autoencoder …

    adelaide Repository record for Language-based Visual Understanding (opens in a new tab)

  2. Towards Comprehensive Visual Understanding

    … conveying information that goes beyond the visual content therein. Traditional computer vision tasks focus on the recognition of tangible properties of images, such as objects and scenes. Relatively little attention has been paid to tasks that involve private states where subjectivity …

    cornell Repository record for Towards Comprehensive Visual Understanding (opens in a new tab)

  3. Toward ontological visual understanding

    … remains when it comes to automatic multimedia understanding. One difference between the human cognition system and state-of-the-art machine vision algorithms is that the former possesses and uses high-level semantic knowledge, or ontology. In this thesis, we present our work on image-level …

    uiuc Repository record for Toward ontological visual understanding (opens in a new tab)

  4. Toward Open World Visual Understanding

    Thesis (Ph.D.)--Michigan State University. Computer Science - Doctor of Philosophy, 2024

    msu Repository record for Toward Open World Visual Understanding (opens in a new tab)

  5. Visual Understanding of Social Human Activity

    … This thesis refers to social human activity understanding as addressing the high-level tasks of recognizing individual human actions, identifying social groups and activities within those groups with a social context focus, setting the groundwork for advancing AI systems proficient in …

    adelaide Repository record for Visual Understanding of Social Human Activity (opens in a new tab)

  6. Visual understanding of the physical world

    … and it is structured around three themes: (1) understanding occlusion and occlusion handling, (2) understanding the 3D and physical properties of the scene, and (3) bridging visual understanding with language. For all the themes, we build our method on top of large-scale pre-trained models or …

    oxford Repository record for Visual understanding of the physical world (opens in a new tab)

  7. Object-Attribute Compositionality for Visual Understanding

    … appearances evolve overtime, which results in visually discernible changes in their colors, shapes, sizes and materials. Humans are innately good at recognizing and understanding the evolution of object states, which is also crucial for visual understanding across images and videos. However, …

    maryland Repository record for Object-Attribute Compositionality for Visual Understanding (opens in a new tab)

  8. Towards in-the-wild visual understanding

    Computer vision research has seen tremendous success in recent times . This success can be attributed to recent breakthroughs in deep learning technology and such systems have been shown to achieve super human performance on several academic datasets. Driven by this success, these systems are …

    maryland Repository record for Towards in-the-wild visual understanding (opens in a new tab)

  9. Structured visual understanding, generation and reasoning

    … This structure manifests itself in the visual data that captures the world around us and in the text describing it and thus can potentially provide a strong inductive bias to various vision tasks. In this thesis, we focus on exploiting the structures existing in visual data to improve …

    gatech Repository record for Structured visual understanding, generation and reasoning (opens in a new tab)

  10. Representation Learning for Intelligent Visual Understanding

    … that generalize across specialized visual domains remains a fundamental challenge. Hyperspectral imagery, surgical video, and mathematical expressions differ substantially in statistical structure, semantic content, and available supervision, making generic visual representations …

    arizona-thes Repository record for Representation Learning for Intelligent Visual Understanding (opens in a new tab)

  11. Visual understanding by salient proto-objects

    … we propose biologically inspired approaches for visual understanding tasks including object detection, image categorization, and visual tracking, based on the concept of salient proto-objects. A salient proto-object refers to a visual unit that can form a coherent and stable object on the basis …

    unsw Repository record for Visual understanding by salient proto-objects (opens in a new tab)

  12. EFFICIENT LEANRING FOR VISUAL UNDERSTANDING AND GENERATION

    Recent progress in visual recognition and generation has brought unprecedented capabilities, but at the cost of vast human-annotated datasets and significant computational overhead. This dissertation confronts these challenges by developing efficiency-focused learning approaches for both visual …

    nus Repository record for EFFICIENT LEANRING FOR VISUAL UNDERSTANDING AND GENERATION (opens in a new tab) Download file for EFFICIENT LEANRING FOR VISUAL UNDERSTANDING AND GENERATION (opens in a new tab)

  13. A HUMAN-CENTERED APPROACH FOR VISUAL UNDERSTANDING

    This thesis presents three works related to human visual perception. The first work is human visual sensitivity to images. It aims to investigate and understand how humans perceive differences in images and apply this study to privacy protection areas. The second work is human visual attention to …

    nus Repository record for A HUMAN-CENTERED APPROACH FOR VISUAL UNDERSTANDING (opens in a new tab) Download file for A HUMAN-CENTERED APPROACH FOR VISUAL UNDERSTANDING (opens in a new tab)

  14. Exploring neural network interpretability in visual understanding

    … to explore the NN interpretability in diverse visual tasks from post-hoc explanation and intrinsic interpretability perspectives. Convolutional neural networks (CNNs) have outperformed humans in image classification. However, the logic of network decisions remains a puzzle. As such, we propose …

    ubc Repository record for Exploring neural network interpretability in visual understanding (opens in a new tab) Download PDF for Exploring neural network interpretability in visual understanding (opens in a new tab)

  15. Label-Efficient Visual Understanding with Consistency Constraints

    … networks are proficient at solving various visual recognition and understanding tasks, as long as a sufficiently large labeled dataset is available during the training time. However, the progress of these visual tasks is limited by the number of manual annotations. On the other hand, it is …

    vt Repository record for Label-Efficient Visual Understanding with Consistency Constraints (opens in a new tab)

  16. TOWARDS UNIFIED MODELS FOR VISUAL UNDERSTANDING AND GENERATION

    … thesis addresses the historical divide between visual understanding and visual generation by proposing a unified framework aimed at achieving visual Artificial General Intelligence (AGI). By leveraging shared representations, the research seeks to enhance performance and computational efficiency …

    nus Repository record for TOWARDS UNIFIED MODELS FOR VISUAL UNDERSTANDING AND GENERATION (opens in a new tab) Download file for TOWARDS UNIFIED MODELS FOR VISUAL UNDERSTANDING AND GENERATION (opens in a new tab)

  17. Towards Comprehensive Visual Understanding via Deep Neural Networks

    … (DNNs) have made significant advancements in visual scene understanding, demonstrating great potential for applications in downstream tasks such as autonomous driving, robotic navigation, and human-computer interaction. Despite these successes, generalization ability remains a major obstacle …

    uts Repository record for Towards Comprehensive Visual Understanding via Deep Neural Networks (opens in a new tab)

  18. Towards Grounded Visual Understanding in Vision–Language Models

    … does not necessarily indicate grounded visual understanding: the ability to connect language to the actual objects, attributes, relations, and dynamics present in visual input. This thesis studies how to build vision-language models with stronger grounded visual understanding, with …

    washington Repository record for Towards Grounded Visual Understanding in Vision–Language Models (opens in a new tab)

  19. LEARNING STRUCTURED ALIGNMENT: FROM VISUAL UNDERSTANDING TO ROBOT CONTROL

    The rapid growth of visual data and the increasing demand for intelligent robotic systemshave created a pressing need for methods that can establish meaningful correspondences and relationships across diverse visual modalities and robotic tasks. This dissertation addresses the fundamental challenge …

    maryland Repository record for LEARNING STRUCTURED ALIGNMENT: FROM VISUAL UNDERSTANDING TO ROBOT CONTROL (opens in a new tab)

  20. Advancing Multi-Modal Deep Learning: Towards Language-Grounded Visual Understanding

    … opening doors to tackle new challenges in image understanding. Among these challenges, understanding and reasoning about language grounded visual content is of fundamental importance to advancing artificial intelligence. Recently, multiple datasets and algorithms have been created as proxy tasks …

    rit Repository record for Advancing Multi-Modal Deep Learning: Towards Language-Grounded Visual Understanding (opens in a new tab)

Page 1 of 5