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 58 for “"Multimodal deep learning"”.
-
Video understanding using multimodal deep learning
<p>Our experience of the world is multimodal, however deep learning networks have been traditionally designed for and trained on unimodal inputs such as images, audio segments or text. In this thesis we develop strategies to exploit multimodal information (in the form of vision, text, speech and …
-
Advancing Computational Pathology with Multimodal Deep Learning
… intelligence (AI) frameworks that integrate deep learning, computer vision, and multimodal data to enhance diagnostic precision, prognostication, and therapeutic guidance across multiple cancer settings. The research first establishes a method for improving classification robustness through …
-
Adaptive Fusion Techniques for Effective Multimodal Deep Learning
… task due to the heterogeneous nature of multimodal data. In this work, we propose fusion techniques that aim to model context from different modalities effectively. Instead of defining a deterministic fusion operation, such as concatenation, for the network, we let the network decide …
-
Multimodal deep learning for decoding visual and neural representation
Multimodal deep learning combines different types of data, like images and brain signals. Traditional models often need lots of labeled examples and focus on one type of data, making them less able to handle real-world challenges. This thesis uses new deep learning and multimodal techniques to …
-
Multimodal deep learning for diagnosing sub-aneurysmal aortic dilatation
… and medications. The solution consists of a multimodal deep learning algorithm that classifies the sub-aneurysms as either healthy or sick and thereby suggests patients that should be kept under surveillance. Due to lack of any follow-up data for the men with sub-aneurysms a comparison with …
-
Multimodal Deep Learning Techniques for Cognitive Decline Detection and Emotional Insights
… the application of artificial intelligence and deep learning techniques in healthcare. These technologies enable personalized and accessible treatments, reducing prolonged waiting times for medical consultations and alleviating the workload of healthcare professionals. Additionally, automatic …
-
Multimodal deep learning methods for image-text verification in misinformation detection
… 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, significant challenges remain, such as unimodal …
-
Novel Data Fusion Architecture in Multimodal Deep Learning for Radiotherapy Outcomes Research
… radiotherapy treatment process, and the use of deep learning computer vision techniques to develop artificial intelligence tools to aid clinics has grown significantly in recent years. The most common use case today is automatic segmentation of patient anatomy prior to treatment planning. …
-
Preoperative Nodal Metastatic Risk Evaluation in Early Breast Cancer : A Multimodal Deep Learning Approach
… nodal status. As a data-driven approach, deep learning has advanced significantly and shows strongpotential to improve predictive performance. This thesis aims to enhance preoperative assessment of axillarylymph node status by integrating deep learning techniques with diverse clinical …
-
Bridging Non-Intrusive Load Monitoring and Human Activity Recognition: A Multimodal Deep Learning Approach
… while HAR infers occupant behavior from multimodal sensors. A BiLSTM with Attention model was developed for NILM using the SDHAR-HOME dataset which includes smart plug data for a television and washing machine. The model achieved reliable performance on stable appliances but showed higher …
-
Automated Code Generation from Flowcharts: A Multimodal Deep Learning Framework for Accurate Translation and Debugging
… structured code. The DFCG leverages multi-modal deep learning to analyze flowcharts and generate structured code across various programming languages. The key innovation of this system lies in its adaptive code generation engine, which constructs an intermediate logical representation of the …
-
Multimodal Deep Learning for Fluid Intake Detection and Classification Using Bio-signals and Visual Data
… investigates biosignal-based and vision-based deep learning approaches for fluid intake detection and classification, aiming to improve accuracy and robustness in real-world applications. The objectives and outcomes of this research are as follows: <br/><br/>1. To assess the feasibility of …
-
Multimodal deep learning for emotion recognition and expression synthesis with applications in human-robot interaction
… of a human, and design architectures based on deep learning, that can efficiently combine information from these streams, with the ultimate goal of deploying the system for human-robot interaction, with an emphasis in child-robot interaction scenarios. While traditional approaches for emotion …
-
Traffic theory inspired spatiotemporal and multimodal deep learning models for trustworthy short-term urban traffic forecasting
… accuracy, trustworthiness and actionability of deep learning models for traffic management based on features such as multimodality and causality and on aspects of Traffic Flow Theory. Specifically, a multimodal forecasting framework based on the concept of Multiplex Networks is developed for …
-
Multimodal Deep Learning for Driver Monitoring: Integrating EEG and Vision for Robust Drowsiness Detection and Safety Enhancement
… driver-monitoring research by developing multimodal approaches that integrate electroencephalography (EEG) and vision data to predict reaction times and drowsiness. The investigation first demonstrates that pre-stimulus EEG signals—specifically spectral power in the alpha and theta …
-
CMTN – Cross-Modal Triage Network: A Multimodal Deep Learning Framework for Severity-Based Triage and Visual Explainability in Chest Radiographs
… the Cross-Modal Triage Network (CMTN), a multimodal framework fusing a Swin Transformer V2 visual backbone with a PubMedBERT textual encoder via Gated Cross-Attention to prioritize chest radiographs by severity while jointly predicting fourteen pathology labels. Evaluated on 3,475 …
Page 1 of 3