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 138 for “"image-text"”.
-
Ramble: To Wander & Wayfind in Image & Text
… particular, I am interested in the ways in which image and text might ramble (move or talk seemingly without set destination) alongside each other in purposeful ambiguity. As Rebecca Solnit states, it is in the “indeterminacy of a ramble” that there “much is to be discovered.”
-
IMAGE, TEXT, AND SOUND THROUGH THE ARABESQUE IN THOREAU'S WALDEN
… to analyze the poems of Goethe in the context of an arabesque frame which gives the sensation of sound by imitating the repeatedly playful consonants of the text written in the center. Thus, text, image, and sound are joined using the arabesque. When turning directly to the Arabic …
-
Multimodal deep learning methods for image-text verification in misinformation detection
This doctoral dissertation investigates automated image-text verification for detecting multimodal misinformation, contributing to the development of novel deep learning methods, the creation of dedicated datasets, and evaluation under realistic conditions. Despite progress in the field, …
-
Hybrid ConVIRT - enhancing medical image-text representation learning of vision language models
… are being addressed through advancements in image-text representation learning, as demonstrated by Hybrid-ConVIRT, which builds on contrastive learning frameworks such as ConVIRT and MedCLIP. These medical contrastive learning models trained on domain-specific datasets, have tackled issues …
-
clip-mesh: generating textured meshes from text using pretrained image-text models
… introduces a novel technique for generating textured mesh models without any 3D supervision based solely on a text prompt. This is done by deforming the control shape of a limit subdivided surface along with its texture and normal map to match an input text prompt. The generated mesh asset …
-
Body-Image-Text: Exploring Female Adolescents on Facebook and Concurrent Identity Formation (CIF)
… their identities on Facebook and in ‘real’ contexts such as at school and at home. Overall, findings reveal an interplay of body, image, and text within the girls’ systems of imagery and language. I suggest that the female adolescent body is virtually self-represented in negotiated as well as …
-
An image-text model for effective retrieval of seventeenth-century Spanish American notary records
… search due to their physical format (e.g., poor image quality) and varied handwriting. The existing work on handwritten documents has predominantly utilized traditional optical character recognition (OCR) techniques, which struggle with the varied and complex handwriting styles. In this thesis, …
-
Pictures and page numbers - image, text and formal structure in the visual book and the artist's book
… emphasise the ability of book forms, and of text and language, to acquire meaning through form and structure alone. The physical and conceptual mechanics, or syntax, of the book - whose basis lies as much in the formal, functional dictates of the book's material characteristics, as in …
-
Hidden in Plain Sight: Image, Text, and Social Commentary in Victor Ekpuk's Cartoons for The Daily Times of Nigeria, 1989-1998
… Museum of African Art are examined in the context of indigenous masking practices and other indirect methods employed by indigenous comedians to protect themselves. Moreover, the cartoons’ use of caricature and their nsibidi scripts within are argued to provide a connotative and denotative …
-
“I'm No Cactus Expert, But I Know A Prick When I See One” -Image, Text, Therapy and Vengeance in Art by Women
This dissertation examines the roles of text and image, therapy and vengeance in art made by women since the 20th century. It discusses the uses of text and image to create political artworks that can play important roles in feminism in regards to the artistic world and how often vengeance is used …
-
Recognizing Object-Centric Attributes and Relations
… that leverages large-scale, readily available image-text data for learning attribute prediction. The proposed framework can effectively scale up to predict a larger space of attribute concepts in real-world settings, including novel attributes represented in arbitrary text phrases that are not …
-
Shining through the surface
… largely been explored in the philosophical context of aesthetics rather than in terms of its practical application in image-text studies of the Romantic period. It has also traditionally served as a marker for the period designation 'Romantic', which in image-text studies continues to be played …
-
A Field Guide to Adaptation
… and elegiac poems, prose poems, and hybrid image/text poems, which explores various types of memory (personal, historical, cultural, and political), and human processes of memory (construction, interpretation, commodification, and loss).
-
Advancing vision-language models for open-vocabulary recognition and generative evaluation
… With VLMs, we can recognize objects using text descriptions, answer questions about images, and generate images from text prompts. Despite this progress, many challenges remain. This thesis explores key advancements in VLMs, tests their capabilities, and points toward unanswered questions …
-
Buried In Pixels
… shaping what is seen and unseen—especially in contexts of war, media, and displacement. Through image, text, and installation, the work questions representation, visibility, and the aesthetics of documentation. The book does not follow a fixed narrative structure; instead, it invites nonlinear …
-
The Artist as Critic: Bi-Textuality in Fin-De-Siècle Illustrated Books
… that the illustrator is the first reader of the text, and that the artist and writer produce their work within a common context. I examine the ways in which the artist as first reader of the author's words provides a critical text for the verbal, and also the ways in which the reader of this …
-
Representing Information Collections for Visual Cognition
… Collections are typically represented with text-only, in a linear list format, which turns out to be a weak representation for cognition. We learned this from empirical research in cognitive psychology, and by conducting a study to develop an understanding of current practices and resulting …
-
Foundations of Self-Supervised Fine-Tuning for Open-Weight CLIP Models
… learning. Among them, Contrastive Language-Image Pre-training (CLIP) stands out as a foundational model, learning unified image-text representations through large-scale self-supervised training on web-scale datasets. CLIP has had a significant impact and is used extensively in downstream …
Page 1 of 7