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 80 for “"Visual Attributes"”.
-
LEARNING VISUAL ATTRIBUTES FOR DISCOVERY OF ACTIONABLE MEDIA
… understanding of what are the discriminative visual attributes of actionable media. We formalize the task of discovery of actionable brand media as a learning-to-rank framework and design a discovery framework that integrates three different classes of visual attributes. The method addresses …
-
The influence of visual attributes of solo marimbists on perceived qualitative response of listeners /
The evaluation instrument consisted of four bipolar adjective scales; (1) sensitive-insensitive, (2) good-bad, (3) effective-ineffective, (4) positive-negative. The scales, each consisting of seven steps, were converted into numerical values allowing for the computation of means. Analyses of …
-
On Biological Network Visualization: Understanding Challenges, Measuring the Status Quo, and Estimating Saliency of Visual Attributes
… research increasingly relies on the analysis and visualization of a wide range of collected data. However, for certain research questions, such as those investigating the interconnectedness of biological elements, the sheer quantity and variety of data results in rather uninterpretable—this is …
-
Literally and figuratively speaking: How concepts and perception influence each other using Stroop paradigms
… a relationship between semantic meaning and visual attributes. We tested the dominant direction of influence between abstract semantic processing and visual perception by pairing words and visual attributes in the same stimulus. Semantic categorization was used to test if visual attributes …
-
Modelling image quality for automotive display technologies
… form their image quality rating by weighting the visual attributes they perceive. Visual algorithms, which can be investigated via psychometric scaling, link visual attributes to the underlying physical image parameters which are typically measure by physical instruments. The visual attributes …
-
Manipulating natural images by learning relationships between visual domains
Manipulation of visual attributes of real images is a fundamental generative computer vision task. The goal is to alter specified visual attributes of a given input image while preserving all other visual attributes. The manipulations can be global, such as changes in lighting or view angle, or …
-
Deep Learning Based Face Image Synthesis
… namely thermal to visible face synthesis and visual attribute to face synthesis. In particular, for thermal to visible face synthesis, we propose a model which makes use of facial attributes to obtain better synthesis. We use attributes extracted from visible images to synthesize …
-
Desenvolvimento da instrumentação para um protótipo de sistema flexível de manufatura
… vision routines were developed to recognize visual attributes of the objects contained on the conveyor belt. A control based on inverse kinematics by the algebraic method aimed to manipulate these recognized objects on the conveyor belt to predefined locations and based on these visual …
-
Influence of material optical characteristics on vision and fruition of Cultural Heritage
… the observer experience assuring the best visual and conceptual appearance of artefacts. Several factors affect the visual appearance of artistic materials. However, available measurement methodologies for the material characterisation are not able to accurately predict the visual …
-
The Role of Aesthetics in a Successful Logo Design
… a strong first impression, and are a valuable visual representation of a brand. The visual appearance of logos is therefore important in terms of how they are viewed by consumers and how they influence consumer perceptions of the brand that the logos represent. The central question that is …
-
Integration of complex shapes and natural patterns
… three steps: modelling of the shape or geometric attributes (such as height, width, and length), modelling of the visual attributes (how the object is going to look), and an integration step that connects the first two (a visual attribute is defined for every point on the surface of the object). …
-
A psychophysical investigation of human visual perceptual memory. A study of the retention of colour, spatial frequency and motion visual information by human visual short term memory mechanisms.
The aim of this thesis was to investigate how visual information is organised in perceptual short term memory, with special interest in colour, spatial frequency and velocity. Previous studies of VSTM have indicated the existence of specific memory mechanisms for visual attributes such as …
-
MTL vs STL: NIR Video metadata classification using self-supervised semi-supervised learning
… The research focuses on the classification of visual attributes in human subjects, specifically in near-infrared (NIR) images.
-
Deciphering the Language of Bronze Age Clothing: Identifying Attributes and Iconographic Associations Through a Data-Driven Analysis of Aegean Glyptic Clothing Depictions in the CMS
… a case study for the possibility of identifying visual “Attributes” for “Characters” in the depictions, who could represent mortals or deities. Seven potential “Characters” are proposed, their visual “Attributes” identified, and their possible roles and statuses considered. The establishment of …
-
Interpretation, grounding and imagination for machine intelligence
… in imagination, I study how to ‘imagine’ visual concepts completely and accurately across the full range and (potentially unseen) compositions of their visual attributes. This thesis analyzes these problems from computational as well as algorithmic perspectives and suggests exciting …
-
Identity in the Late Woodland Northeast: interpreting communities of practice from paste composition at the Thomas/Luckey and the Losey 3 sites
… with pXRF. While pottery types are based on visual attributes, pXRF looks at elemental composition. Decoration is mimicable, but paste is not; paste accurately illustrates a vessel’s origin. Cultural groups are not static entities, and internal development or outgroup interaction indicates …
-
Multi-Modal Deep Learning for Computer Vision and Its Application
Although the exponential growth of visual data in various forms, such as images and videos, enables unprecedented opportunities for us to interpret the surrounding environment, natural language is still the main way to convey knowledge and information among us. Therefore, there is currently an …
-
Automatic Video Captioning using Deep Neural Network
… to appropriate locations in a video by using visual attributes. The Multi-stream Hierarchical Boundary model combines a fixed hierarchy recurrent architecture with a soft hierarchy layer by using intrinsic feature boundary cuts within a video to define clips. This thesis also introduces a …
Page 1 of 4