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 25 for “"Similarity learning"”.
-
Towards similarity learning in security applications
Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2027-08-01
-
Instance Segmentation of Point Clouds via Similarity Learning
… segmentation of point clouds using a form of similarity learning. Specifically, our neural network, called PointSimNet, based on PointNet, learns to predict point features that are close to each other in feature space if the points belong to the same semantic category. A similarity matrix is …
-
Similarity learning in the era of big data
This dissertation studies the problem of similarity learning in the era of big data with heavy emphasis on real-world applications in social media. As in the saying “birds of a feather flock together,” in similarity learning, we aim to identify the notion of being similar in a data-driven and …
-
Similarity Learning and Stochastic Language Models for Tree-Represented Music
Similarity computation is a difficult issue in music information retrieval tasks, because it tries to emulate the special ability that humans show for pattern recognition in general, and particularly in the presence of noisy data. A number of works have addressed the problem of what is the best …
-
Similarity learning for person re-identification and semantic video retrieval
Many computer vision problems boil down to the learning of a good visual similarity function that calculates a score of how likely two instances share the same semantic concept. In this thesis, we focus on two problems related to similarity learning: Person Re-Identification, and Semantic Video …
-
Leveraging Deep Learning for Trajectory Similarity Learning and Trajectory Pathlet Dictionary Construction
… and navigation services. Of interest are similarity search tasks that several works addressed through representation learning. Our method ST2Box offers refined representations by first representing trajectories as sets of roads, then adapting set-to-box architectures for learning accurate, …
-
Academic Recommendation System Based on the Similarity Learning of the Citation Network Using Citation Impact
… nearby citation network. We combine the content similarity with the bibliometric indices to evaluate the citation impact of articles, authors, and venues in their surrounding citation network. Using the article metadata, we calculate the semantic similarity between any two articles in the …
-
Weakly Supervised Roadside Object Geolocation from Street-Level Imagery with Similarity Learning and Graph-Based Reasoning
… framework integrates visual localization, similarity learning, and geometric reasoning to address these challenges. Roadside objects are first localized in images using weak supervision. Multi-view geometric cues are then used to estimate their real-world locations from multiple camera …
-
Energy efficient, secure and noise robust deep learning for the internet of things
… energy efficient, secure and noise robust deep learning system for the Internet of Things (IoTs). The research particularly focuses on energy efficient training of deep learning, adversarial machine learning, and noise robust deep learning. To enable energy efficient training of deep learning, …
-
Robust, Efficient and Scalable Learning of Point Process
This thesis describes novel approaches to learning from time series and point processes, including latent pattern learning, classification, clustering and event prediction, among which similarity learning is the common theme. In the machine learning and data analysis domain, time series and point …
-
All Malware Looks Similar Until It Doesn’t
This thesis investigates the use of machine learning to learn embeddings from static, dynamic, and hybrid malware representations. The learned embeddings are evaluated through similarity search and zero-shot clustering, with particular focus on their ability to generalize beyond malware families …
-
Similarity modeling for machine learning
Similarity is the extent to which two objects resemble each other. Modeling similarity is an important topic for both machine learning and computer vision. In this dissertation, we first propose a discriminative similarity learning method, then introduce two novel sparse similarity modeling methods …
-
Facilitating Adaptive and Dynamic Learning Transfer Using Genre-based, Translingual, and Multimodal Pedagogies in L2 Composition Instruction
… that pedagogies based in adaptive and dynamic learning transfer, defined as the repurposing or innovation of knowledge to negotiate new and unfamiliar writing contexts, are more successful in preparing students to transfer their knowledge to future contexts than pedagogies based in similarity …
-
Learning sparse features and metric in signal and image processing
This dissertation studies two aspects of feature learning: representation learning and metric in feature space, from a machine learning perspective. Feature learning is a fundamental problem in computer vision and machine learning. First introduced in computational neuroscience in the context of …
-
Towards diverse generation and reliable classification using neural networks
… To tackle this, we finally introduce a similarity learning approach, that can learn to perform dense label transfer from one image to the other. More specifically, the objective is to learn a similarity metric for dense pixel-wise correspondence between two images. This learned model can …
-
From Line Drawings to Human Actions: Deep Neural Networks for Visual Data Representation
… for the applications which rely on the learning of large scale deep neural networks with millions of parameters. The deep learning approaches have been proved to be able to learn powerful representations of the inputs in various tasks, such as image classification, object recognition, …
-
Autonomous inter-task transfer in reinforcement learning domains
Reinforcement learning (RL) methods have become popular in recent years because of their ability to solve complex tasks with minimal feedback. While these methods have had experimental successes and have been shown to exhibit some desirable properties in theory, the basic learning algorithms have …
-
Show Me How You Move and I Tell You Who You Are – Motion-Based User Identification and Verification for the Metaverse
… this dissertation further proposes a novel similarity-learning approach, advancing the feasibility of motion-based user recognition in real-world scenarios. Recognizing the need for standardization in the field, this research introduces `The XR Motion Dataset Catalogue'. This resource, …
-
Identifying cell types with single cell sequencing data
… feature selection, dimensionality reduction, similarity matrix construction and unsupervised clustering. Many single-cell clustering algorithms rely on similarity matrices of cells, but many existing studies have not received the expectant results. There are some unique challenges in analyzing …
Page 1 of 2