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 666 for “"Visual data"”.
-
Similarity search in visual data
… a significant increase in the amount of data available on the Internet. Organizing such big data so that it is easily and promptly accessible, is a necessity that has been growing in importance. Among the various data modalities such as text, audio, etc., visual data (in the form of …
-
Reconstructing 3D Humans From Visual Data
Understanding humans in visual content is fundamental for numerous computer vision applications. Extensive research has been conducted in the field of human pose estimation (HPE) to accurately locate joints and construct body representations from images and videos. Expanding on HPE, human mesh …
-
RICH AND EFFICIENT VISUAL DATA REPRESENTATION
Increasing the size of training data in many computer vision tasks has shown to be very effective. Using large scale image datasets (e.g. ImageNet) with simple learning techniques (e.g. linear classifiers) one can achieve state-of-the-art performance in object recognition compared to sophisticated …
-
Learning from Human-Centric Visual Data
… neural networks can learn from human-centric visual data, including images and videos of individuals, is a topic receiving increased attention. The main concern exists on the sensitivity and scarcity of human related data. We learn from human centric visual data on two aspects: 1) …
-
Evaluating cluster quality for visual data
… it easy to collect large amounts of unlabeled data that can be used to learn to recognize objects and actions. Collecting ground-truth labels for this data, however, is a much more time consuming task that requires human intervention. One approach to train on this data, while keeping the human …
-
Visual Data Analysis in Device Ecologies
… continued development towards a digitalized and data-driven world, the importance of visual data analysis is increasing as well. Visual data analysis enables people to interactively explore and reason on certain data through the combined use of multiple visualizations. This is relevant for a wide …
-
Grounding deep models of visual data
… temporal progression. 2) Spatial Grounding. We visualize spatial evidence of deep model predictions using a discriminative top-down attention mechanism, called Excitation Backprop. We show how such visualizations are equally informative for correct and incorrect model predictions, and highlight …
-
Dense 3D Reconstructions from Sparse Visual Data
… machines to recover 3D geometry from such sparse data due to occlusions, and irregularity and complexity of 3D objects. To solve these, in this dissertation, we explore learning-based 3D reconstruction methods for different 3D object representations on different tasks: 3D reconstructions of static …
-
Learning from Hidden Signals in Visual Data
… and generative priors learned from large-scale data. In the first part, the structure comes from physics and geometry. We use this structure to extract information from reflections, motion, and defocus cues in photos and videos. We reconstruct 3D scenes from the reflections in a person's eyes, …
-
Visual Data Representation using Context-Aware Samples
The rapid growth in the complexity of geometry models has necessisated revision of several conventional techniques in computer graphics. At the heart of this trend is the representation of geometry with locally constant approximations using independent sample primitives. This generally leads to a …
-
Understanding Immersive Environments for Visual Data Analysis
Augmented Reality enables combining virtual data spaces with real-world environments through visual augmentations, transforming everyday environments into user interfaces of arbitrary type, size, and content. In the past, the development of Augmented Reality was mainly technology-driven. This made …
-
Overcoming visual data scarcity with synthetic examples
… large numbers of parameters can easily fit to visual recognition tasks on large labeled datasets and generalize reasonably well. This task however becomes hard with few training data. Also challenging are scenarios where generalization is expected across test distributions that are further …
-
Towards expressive and scalable visual data exploration
Data visualization is the primary means by which data analysts explore patterns, trends, and insights in their data. Despite of their growing popularity, existing visualization tools (e.g., Tableau, PowerBI, Excel) are limited in their ability to automatically find desired visualizations or …
-
Prior-guided Neural Compression of Visual Data
… methods have been widely applied in the field of visual data compression, some of which have delivered the best rate-distortion performances in history. The target domain of neural data compression started from that of still images and then rapidly expanded into various modalities, including …
-
Binary Representation Learning for Large Scale Visual Data
… large amount of multimodal or multidomain visual data, which usually reside in high dimensional space. And it is crucial to provide not only effective but also efficient understanding of the data.In this dissertation, we focus on learning binary representation of visual dataset, whose …
-
Interactive Visual Data Exploration: A Multi-focus Approach
… rate. This huge, heterogeneous, and complicated data that we are continuously generating could be an incredible resource for us to seek insights and make informed decisions. For this knowledge extraction to be efficient, visual exploration of data is demanded in addition to fully automatic …
-
Leveraging Visual Data For Play-Based Kindergarten Assessment
… Pyle et al., 2020). When leveraged effectively, visual data (e.g. information captured through photos/videos) is endorsed as an optimal method for integrative play-based assessment (Dahlberg, 2012; Ontario Ministry of Education, 2012, 2015; Pyle et al., 2020). However, studies show that although …
-
Behavior Monitoring Using Visual Data and Immersive Environments
Mental health disorders are the leading cause of disability in the United States and Canada, accounting for 25 percent of all years of life lost to disability and premature mortality (Disability Adjusted Life Years or DALYs). Furthermore, in the United States alone, spending for mental disorder …
-
Human-centered AI through scalable visual data analytics
… a human-centered approach, by creating novel data visualization tools that are scalable, interactive, and easy to learn and to use. With such tools, users can better understand models by visually exploring how large input datasets affect the models and their results. Specifically, my …
Page 1 of 34