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 11 of 11 for “"Multimodal Retrieval"”.
-
Multimodal Retrieval Augmented Generation via Embedding Space Alignment
Retrieval-augmented generation (RAG) systems answer questions by first retrieving supporting evidence and then generating a response conditioned on that evidence. In visually rich document collections, such as Swedish municipal PDF archives, relevant information is often spread across text, maps, …
-
Advancements in ML via Efficient Generative Modeling, Robust Domain Adaptation, and Explainable Multimodal Retrieval
… adaptation under data-scarce conditions, and multimodal retrieval. Collectively, the methods reduce dependence on large, labeled datasets, improve adaptability under distribution shifts, enable deployment on resource-constrained platforms, and enhance interpretability. For classification, the …
-
Adversarial Machine Learning: Methods for Attacks and Defenses
… target models designed for fair prediction or multimodal retrieval. Furthermore, malicious users continuously devise subtle methods to disseminate harmful content on social media, necessitating the development of intelligent systems capable of detecting and mitigating such content. …
-
Extracting Knowledge with Multimodal and Multilingual Intelligent Systems
… performance on this challenging task, we develop multimodal retrieval-augmented generation systems to acquire knowledge from external resources. Inspired by the visual knowledge we found from InfoSeek, we raise an emergent privacy concern of multimodal LLM to reveal geolocation information of user …
-
A Multimodal RAG-Based Model for Automated Safety Hazard Assessment in Industrial Environments
This thesis presents a multimodal retrieval-augmented generation (RAG) model for automated safety hazard assessment in industrial environments, implemented as a cross-platform mobile application for the offshore energy sector. Workers on offshore platforms spend 10 to 15 minutes completing each …
-
A search engine using graph-based structures for lifelog retrieval
… challenge of lifelogs is how to build a lifelog retrieval system that can retrieve a specific activity efficiently from large multimodal lifelog data. Recently, there have been many workshops organized to encourage researchers to solve that problem leading to the introduction of many lifelog …
-
Learning Binary Code Representations for Effective and Efficient Image Retrieval
… an image dataset with millions of images, image retrieval becomes a seemingly intractable problem for exhaustive similarity search algorithms. Hashing methods, which encodes high-dimensional descriptors into compact binary strings, have become very popular because of their high efficiency in …
-
Resonating visuals: generative AI strategies for capturing the essence of music in image form
This thesis studies methods of generating images which captures corresponding semantic information of music. The primary goal of each method is to generate an image given a song as the input. First, I describe a model-agnostic LLM interaction method which extracts information from lyrics to …
-
Conversational Multimodal LLMs for Food Nutritional Information Retrieval: A Systematic Evaluation
… systematically evaluates eight state-of-the-art multimodal large language models (including GPT-4o, Qwen 2, and Qwen 2.5, DeepSeek, and LLaVA), in a zero-shot setting on two real-world datasets, Nutrition5k and MetaFood3D. To identify which types of information most improve model predictions, a …
-
Building a Robust Retrieval System with Dense Retrieval Models
First-stage retrieval plays a pivotal role in modern search engines, aiming to gather candidates from a large corpus for various downstream tasks, such as question answering, fact-checking, and retrieval-augmented generation. Historically, retrieval using heuristic lexical representations, such as …
-
Speaker conditioned semantic retrieval from speech databases
Tato diplomová práce se zabývá sémantickým vyhledáváním v databázích řečových dat podmíněným identitou mluvčího, kde musí výsledky vyhledávání splňovat jak požadavky na sémantickou relevanci, tak na shodu mluvčího. Současné systémy pro vyhledávání v řeči jsou typicky založeny na automatickém …