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 60 for “"Multi-Modal Learning"”.
-
Multi-Modal Learning for Threat Analysis
In recent years, the area of multi-modality has gained immense interest in computer vision, where it has showed to be powerful for the purpose of letting models learn visual concepts from raw text instead of from manual annotations. One specific model using this concept is CLIP [1], which has shown …
-
Multi-modal learning using deep neural networks
… to process and understand information from multiple sources such as images, video, text, and speech. Recent success of deep neural networks has enabled us to develop algorithms which give machines the ability to understand and interpret this information. Convolutional Neural Networks (CNN) …
-
Multi-modal learning for image and beyond
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-12-01
-
Enhanced Feature Representation in Multi-Modal Learning for Driving Safety Assessment
… in driving safety through the development of multi-modal learning frameworks that leverage high-frequency, high-resolution driving data and videos to detect safety-critical events (SCEs). The research unfolds across four methodologies, each contributing to advance the field. The introductory …
-
Multi-Modal Learning for Cross-Domain Analysis of Egocentric Action and Object Recognition
L'abstract è presente nell'allegato / the abstract is in the attachment
-
Self-supervised and multi-modal learning for perception in mobile robots and autonomous driving
… robots. These domains typically contain multiple dynamic agents such as pedestrians or vehicles, obstacles such as sidewalks or poles, and multiple types of ground surfaces such as cobblestone, asphalt, or grass. Robot perception must detect and register each entity in the scene and make …
-
A 5G Security Recommendation System Based on Multi-Modal Learning and Large Language Models
… 5G security recommendation system that leverages multi-modal learning to correlate alerts from four aspects of a cloud-native 5G deployment, i.e., security monitoring and security auditing systems, deployed at both 5G/Kubernetes® levels. Also, 5GSecRec further eases security analysts’ job by …
-
Toward Federated and Multi-Modal Learning: From Optimized Edge Intelligence to Bias-Aware Foundation Models
Traditional Machine Learning (gls{ml}) paradigms rely on centralized data and training, where all raw data are aggregated into a single location. This approach has been effective in scenarios where data are abundant, homogeneous, and easy to access. However, as applications increasingly span …
-
Development of an Instructional Design Framework to Guide the Design of Multi-Modal Learning Environments
… compared to instructors and students in multi-modal research. Instructional designers need to keep up with the emerging technologies and changing educational landscape in order to equip instructors with the skills and knowledge they need to create meaningful learning experiences. One way …
-
Towards Multi-Modal Interactive Systems that Connect Audio, Vision and Beyond
Human perception relies on the integration of multi-sensory signals such as vision, audio and language, enabling complex tasks such as interpreting environments and making decisions. In Artificial Intelligence (AI), multi-modal learning seeks to enable such abilities. Significant progress has been …
-
Multimodal Adversarial Learning
… object recognition, generative modelling, and multi-modal learning in various computer vision applications. However, recent findings have shown that such state-of-the-art models can be easily deceived by inserting slight imperceptible perturbations to key pixels in the input. A good target …
-
Annotation efficient learning with affinity graphs
Annotation-efficient learning has emerged as a critical area of research due to the scarcity of labeled samples posing a substantial barrier to developing robust fullysupervised deep neural networks. When the availability of labeled samples is limited, developing an effective learning system …
-
Multi-modal Data-efficient Learning for 3D Machine Vision
… labeled data, the complexity of integrating multiple modalities, and the inherently imbalanced and long-tailed nature of 3D datasets. This dissertation addresses these challenges by proposing data-efficient, multi-modal learning frameworks that improve the accuracy, generalization, and …
-
Enforcing structure in visual attention
… which has shown to be especially valuable in multi-modal learning tasks. However, all prior attention frameworks lack the ability to explicitly model structural dependencies among attention variables, making it difficult to predict consistent attention masks. In this work we develop a novel …
-
Reduce, reuse, redefine: An interactive framework for repurposing packaging materials through a sustainability-focused craft kit system using traditional and digital methods
… of supplemental instruments and digital learning tools. A multi-modal learning environment, established as the Caravan Craft Kit System, promotes consumer-driven methods for reusing materials found in homes, offices, and community spaces with increased accessibility and community …
-
Mining Health Data for Decision Making with Deep Learning Models
… recent success and development of deep learning techniques is revolutionizing many fields and holds a great potential to advance healthcare research. It is expected that mining useful knowledge from health data with deep learning models would tremendously improve clinical decision …
-
Personalized, Safe, and Interactive Robot Programming via Human Demonstrations
The increasing capability of robots and machine learning algorithms shed light on the future where robots can be deployed ubiquitously. Yet, current robot learning algorithms require robotic and programming expertise, limiting the functionality users can gain from robots. Learning from …
-
Reimagining wireless networks: Generative AI for integrated sensing and communications
… focusing on the convergence of \ac{ISAC}, multi-modal learning, and agentic reasoning. A series of systems and methodologies are introduced which span from foundational language model integration to real-time perception and control. As a core study, NextG-GPT is a domain-specialized large …
Page 1 of 3