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 26 for “"Multimodal representations"”.
-
Learning visual and multimodal representations
Representations lie at the heart of artificial intelligence, enabling machines to perceive, interpret and interact with the world. Visual representations, extracted from images or videos, enable tasks such as image classification, image retrieval, and object detection. Visual-textual …
-
Learning and evaluating multimodal representations for digital domains
… is the process of learning embeddings, i.e., representations, of mobile app and webpage data. In this thesis, we (1) Curate multimodal app and webpage datasets. Digital domains capture four modalities: image, text, structure, and action. We contribute the first multimodal app dataset with all …
-
Students’ meaning making of nature of science through multimodal representations
… education have argued for the importance of multimodality in students’ meaning making of scientific concepts. Although students’ expression of nature of science (NOS) can take various modes of representation, researchers in the field of NOS seldom explore how students make meaning of NOS …
-
“MOVE ON WITH LIFE” : MULTIMODAL REPRESENTATIONS OF GRIEF ON COLLEGE WEBSITES
Thesis (Ph.D.)--Michigan State University. Higher, Adult, and Lifelong Education - Doctor of Philosophy, 2026
-
Attentive Cross-Modal Connections for Learning Multimodal Representations from Wearable Signals for Affect Recognition
… a new dynamic and effective technique for multimodal representation learning from wearable data. Our solution can be integrated into any stage of the pipeline, i.e., after any convolutional layer or block, to create intermediate connections between individual streams responsible for …
-
Building scientific literacy/(IES): a cross-case analysis of how multimodal representations are used to make meaning during scientific inquiry
… Semiotic framework to describe the nature of multimodal textual representations created by fourth grade students in a small rural Texas school district south of Dallas in order to answer the question: What is the nature of the multimodal textual representations created by fourth grade students …
-
Grounding language in image, video and audio modalities
The sub-field of multimodal learning in artificial intelligence involves the problem of jointly learning representations of the audio, language and visual modalities for the purpose of automated applications including virtual assistants, chatbots and robotics. In particular, learning a multimodal …
-
The impact of student created Slowmation on the teaching and learning of primary science
… students in learning by supporting discourse and multimodal representations of science phenomena. In response, this study explored and evaluated the implementation of student created Slowmations in a Primary Connections science unit. The study aimed to investigate the ways in which the process of …
-
The relationship between vocabulary and gesture development in early childhood and infancy
… to use their right hand when they had built multimodal representations of novel verbs. This thesis then describes the first study to manipulate gesture handedness in children, which suggests that encouraging right-handed gesturing has an advantage over left-handed gesturing in a language …
-
Identification and interpretive rights in the rhetoric of violent spectacle
… the death penalty, and stealth torture as multimodal public discourse, comprised of violent events, their representations, and their surrounding debate. While the forms of violence I discuss all have avowed communicative purposes, I argue that the rhetorical emphasis on these messages often …
-
Multimodal representation learning for personalized cardiovascular care : predicting disease progression and treatment from clinical data
… thesis presents a series of deep learning-based multimodal representation learning frameworks for personalized cardiovascular disease management, using routinely collected and non-invasive clinical data. The thesis first introduces TREAT-Net, an acute coronary syndrome treatment prediction …
-
Advancing affect modelling via representation learning
… particularly in learning generalisable affective representations across different modalities and scenarios, especially in contexts where data is scarce or incomplete. This thesis explores these challenges through the lens of representation learning, with a specific focus on contrastive learning …
-
Robust Audiovisual Active Speaker Detection for Egocentric Recordings - Leveraging Contextual Information and Cross-Modal Biometric Associations
… highlight the potential of context-enriched multimodal representations as a foundation for future wearable and Augmented Reality (AR)-based audiovisual diarisation systems.
-
Lernen und Kompetenzentwicklung im dynamischen Umfeld klinischer Arbeit : Zusammenspiel und Bedeutung von Lern- und Arbeitsprozessen sowie technologischen Artefakten in medizinisch-klinischen Kontexten
… vielfältiger, miteinander eng verwobener, multimodaler Repräsentationen (wie z.B. Sprache, visueller und haptischer, körperlicher und IT- artefaktbasierter Strukturen) notwendig ist. Die einzelnen Arbeiten sind aus sozio-kognitiven, sozio- kulturellen und situierten Perspektiven theoretisch …
-
Text augmentations from music artist biographies improve performance on genre classification, emotion recognition and music tagging
… to analyse, categorise, and recommend music. Multimodal learning plays an important but challenging role in MIR. Compared to more common multimodal settings such as speech transcription or image captioning, aligning audio with textual descriptions of music is particularly difficult because …
-
Hybrid Deep Learning Model: LLM-Enhanced Linear Self-Attention Transformer-CNN for Stock Price Prediction
… raw market information into rich textual representations. These representations encapsulate intricate financial patterns using well-established technical indicators such as Bollinger Bands (BBs). By interpreting these financial metrics, the LLM generates structured textual summaries that …
-
Attacks and Defenses on Recommender Systems
… traditional collaborative filtering (CF), multimodal recommendations, and emerging large language model (LLM)-powered recommender agents. As RSs evolve from static predictors to autonomous agents, their attack surfaces expand from data space to multimodal representations and dynamic …
-
Visual-Linguistic Semantic Alignment: Fusing Human Gaze and Spoken Narratives for Image Region Annotation
… integration and interpretation of their multimodal representations (e.g. gaze, text) remain a challenge. Our work explores the hypothesis that eye movements can help us understand experts' perceptual processes and that spoken language descriptions can reveal conceptual elements of image …
-
SCIENTIFIC LITERACY IN SECONDARY SCHOOL CHEMISTRY: A MULTIMODAL PERSPECTIVE
… thesis is situated within the research field of multimodality and in the pedagogical context of science education. It aims to offer a semantic account of multi-semiotic representations and verbal discourse in secondary school chemistry education. The present study is motivated to provide …
Page 1 of 2