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 286 for “"Computer vision tasks"”.

  1. Computational Efficiency Studies in Computer Vision Tasks

    Computer vision has made massive progress in recent years, thanks to hardware and algorithms development. Most methods are performance-driven meanwhile have a lack of consideration for energy efficiency. This dissertation proposes computational efficiency boosting methods for three different vision …

    tamu Repository record for Computational Efficiency Studies in Computer Vision Tasks (opens in a new tab)

  2. Attention mechanism in deep neural networks for computer vision tasks

    … mechanism has been widely adopted in solving computer vision tasks by guiding deep neural networks (DNNs) to focus on specific image features for better understanding the semantic information of the image. However, the attention mechanism is not only capable of helping DNNs understand …

    must-thes Repository record for Attention mechanism in deep neural networks for computer vision tasks (opens in a new tab)

  3. Deep learning and DCT-based hand-crafted features for computer vision tasks

    … and matching are critical components for many computer vision tasks including camera pose estimation, 3D reconstruction, simultaneous localization and mapping (SLAM), and object tracking, etc. Features are image patterns that have distinctive characteristics in its immediate neighborhood and …

    missouri Repository record for Deep learning and DCT-based hand-crafted features for computer vision tasks (opens in a new tab)

  4. ON ANNOTATION EFFICIENT LEARNING FOR COMPUTER VISION TASKS AND ITS APPLICATION ON MEDICAL IMAGE DATASETS

    … achieve state-of-the-art results in several SSL tasks. These methods can typically reach performances that are comparable to their fully supervised counterparts while using only a fraction of labelled examples. Despite these methodological advances, understanding of these methods is still …

    nus Repository record for ON ANNOTATION EFFICIENT LEARNING FOR COMPUTER VISION TASKS AND ITS APPLICATION ON MEDICAL IMAGE DATASETS (opens in a new tab) Download file for ON ANNOTATION EFFICIENT LEARNING FOR COMPUTER VISION TASKS AND ITS APPLICATION ON MEDICAL IMAGE DATASETS (opens in a new tab)

  5. The FineView Dataset: a 3D Scanned Multi-View Object Dataset of Fine-Grained Category Instances

    … models have shown impressive performance in many computer vision tasks by learning from large and diverse image datasets. Most of these datasets consist of web-scraped image collections. This approach, however, makes it very challenging to obtain desirable data such as multiple views of the same …

    byu Repository record for The FineView Dataset: a 3D Scanned Multi-View Object Dataset of Fine-Grained Category Instances (opens in a new tab) Download PDF for The FineView Dataset: a 3D Scanned Multi-View Object Dataset of Fine-Grained Category Instances (opens in a new tab)

  6. Combining bayesian and deep learning methods in computer vision problems

    Neural networks dominate computer vision tasks, yet their predictions often lack reliability. Bayesian Deep Learning (BDL) offers a solution by treating model parameters as random variables. This approach leads to well-calibrated predictions and handles distribution shifts better than deterministic …

    greece Repository record for Combining bayesian and deep learning methods in computer vision problems (opens in a new tab)

  7. Robust and Efficient Corner Detection for Computer Vision

    Corner detection is a fundamental computer vision problem that has been widely studied in image retrieval, object tracking, motion estimation, visual localization and 3D reconstruction. The accuracy and repeatability of corner detection are important for image matching and retrieval, while the …

    unsw Repository record for Robust and Efficient Corner Detection for Computer Vision (opens in a new tab)

  8. Robust Machine Learning In Computer Vision

    … have been shown to be successful in various computer vision tasks such as image classification and object detection. Although deep neural networks have exceeded human performance in many tasks, robustness and reliability are always the concerns of using deep learning models. On the one hand, …

    jhu Repository record for Robust Machine Learning In Computer Vision (opens in a new tab)

  9. Convolutional neural network compression via tensor decomposition

    Computer vision models, such as image and video classifiers, are increasingly prevalent in Internet-of-Things systems. Since the advent of the AlexNet neural network model in 2012, convolutional neural networks have been demonstrated to be very effective at performing many computer vision tasks. …

    ubc Repository record for Convolutional neural network compression via tensor decomposition (opens in a new tab) Download PDF for Convolutional neural network compression via tensor decomposition (opens in a new tab)

  10. Advances in Stimulated Raman Scattering Microscopy via Deep Learning

    … of deep learning platforms for a wide variety of computer vision tasks. In this work I document my contributions in integrating SRS microscopy and deep learning towards advancing the capability to study biological systems. Specifically, deep learning will be shown to address technical limitations …

    washington Repository record for Advances in Stimulated Raman Scattering Microscopy via Deep Learning (opens in a new tab)

  11. Mažos apšvietos vaizdų transformavimas į pagerintos kokybės optinius vaizdus /

    … The importance of this topic is discussed. Computer vision tasks are reviewed, with further focus on the image reconstruction problem. Models used to solve this problem are described. Super-resolution and generative adversarial network models are presented. The task is implemented using the …

    vilnius Repository record for Mažos apšvietos vaizdų transformavimas į pagerintos kokybės optinius vaizdus / (opens in a new tab)

  12. Using Efficient Vision Transformers to Improve Perception Systems in Autonomous Off-Road Vehicles

    … sensor systems or modalities. Deep learning computer vision algorithms have shown to be the strongest tool for trans- lating this data into accurate and safe decisions about a vehicle’s environment. This understanding of the environment allows the vehicle to make real-time decisions on …

    clemson Repository record for Using Efficient Vision Transformers to Improve Perception Systems in Autonomous Off-Road Vehicles (opens in a new tab)

  13. Acceleration of real-time face recognition pipeline on heterogeneous hardware platforms

    … unprecedented results in previously unsolvable computer vision tasks. Face recognition, one of the critical computer vision tasks, also sees breakthrough in terms of accuracy. This thesis presents an accelerated and optimized end-to-end face recognition pipeline. Such a pipeline consists of …

    uiuc Repository record for Acceleration of real-time face recognition pipeline on heterogeneous hardware platforms (opens in a new tab)

  14. A computer vision framework towards automated scene understanding & analysis

    … intelligence and the increased capability of computer hardware have significantly advanced the field of computer vision – a field of study which enables computers to “see” and extract meaningful information from visual inputs, similar to human perception. A prominent application area within …

    stellenbosch Repository record for A computer vision framework towards automated scene understanding & analysis (opens in a new tab)

  15. Impact of Video Compression and Metrics to Assess Image Quality for Automated Video Analytics in Video Surveillance Systems

    … focuses on defining image quality metrics for computer vision tasks. In a machine learning context, image quality determines the suitability of an image for use by machine learning algorithms. First, we analyzed the performance of vision algorithms on a dataset of videos of different quality …

    houston Repository record for Impact of Video Compression and Metrics to Assess Image Quality for Automated Video Analytics in Video Surveillance Systems (opens in a new tab)

  16. Relating First-person and Third-person Vision

    … third-person (exocentric) videos. In many computer vision tasks (e.g. identification, action recognition, face recognition, pose estimation, etc.), the human actors are the main focus. Hence, detecting, localizing, and recognizing the human actor is often incorporated as a vital component. …

    ucf Repository record for Relating First-person and Third-person Vision (opens in a new tab)

  17. Modeling Data Metrics And Distributions For Representation And Efficient Transfer Learning

    … in deep learning, particularly for downstream computer vision tasks. While existing research predominantly focuses on loss functions and network architectures, this dissertation explores how modeling distance metrics and data distributions can enhance representation and transfer learning …

    ucf Repository record for Modeling Data Metrics And Distributions For Representation And Efficient Transfer Learning (opens in a new tab)

  18. Deep learning in sequential data analysis

    … has achieved great success in recent years in computer vision and its related areas. For core computer vision tasks such as image classification, image semantic segmentation, image super-resolution, and object detection from images, deep learning based methods outperform various traditional …

    uiuc Repository record for Deep learning in sequential data analysis (opens in a new tab)

  19. Systems and Methods for Scalable Retinal Screening Programs

    … addresses gaps in artificial intelligence-based computer vision tasks in the medical image processing field. We demonstrate effective methods for standardizing and augmenting digital fundus photographs so that robust convolutional neural network-based systems can perform high-throughput disease …

    unm Repository record for Systems and Methods for Scalable Retinal Screening Programs (opens in a new tab)

Page 1 of 15