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 265 for “"Feature representations"”.
-
Spatio-temporal feature representations of reactivated memories
… thesis is concerned with the spatio-temporal feature representations of reactivated episodic memories. Classical theories and empirical evidence suggest that the revival of memory representations in the brain is initiated in the hippocampus, before activity patterns in cortical regions …
-
Prioritising feature representations in visual working memory
Representations of our external environment and of our internal memories together guide our awareness and actions. While large numbers of features and objects from the boundless external environment compete for sensory processing, working memory capacity is highly limited. Though extracting and …
-
Learning Discriminative Feature Representations for Visual Categorization
Learning discriminative feature representations has attracted a great deal of attention due to its potential value and wide usage in a variety of areas, such as image/video recognition and retrieval, human activities analysis, intelligent surveillance and human-computer interaction. In this thesis …
-
Learning deep acoustic feature representations for HRTF individualization
… To this end, it proposes learning deep representations of the HRTF's acoustic features around each source direction. In particular, it uses explainable Artificial Intelligence to analyse a CNN trained for sound-source elevation classification, identifying population-wide spectral cues …
-
Learning Discriminative Feature Representations for Action Recognition and Segmentation
… on analysis of the distribution of low-level feature descriptors such as space-time interest points and dense trajectories. These feature descriptors are typically handcrafted local features, thus they are not interpretable and discriminative enough. Recent advances in deep learning have led …
-
Learning Deep Feature Representations of 3D Point Cloud Data
… In this thesis, we focus on learning deep feature representations of point clouds for 3D data processing and analysis. Basically, we start from investigating low-level vision problems of 3D point clouds, which helps to comprehend and deal with the inherent sparsity, irregularity and …
-
COMPUTATIONAL MODELS OF FEATURE REPRESENTATIONS IN THE VENTRAL VISUAL STREAM
Understanding vision requires unpacking the representations of the visual processing hierarchy. One major and unresolved challenge is to understand the representations of high-level category-selective areas – areas that respond preferentially to certain semantic categories of stimuli (e.g., …
-
Towards robust and domain invariant feature representations in Deep Learning
… perception-based systems is to define and learn representations of the scene that are more robust and adaptive to several nuisance factors. Over the recent past, for a variety of tasks involving images, learned representations have been empirically shown to outperform handcrafted ones. However, …
-
The application of range imaging for improved local feature representations
… achieve pose invariant object recognition. Local feature matching is a fundamental technique in image analysis that underpins many computer vision-based applications; the approach comprises identifying a collection of interest points in an image, characterising the local image region surrounding …
-
Interpreting intermediate feature representations of raw-waveform deep CNNs by sonification
… sonification, a method to interpret intermediate feature representations of sound event recognition (SER) 1D-convolutional neural networks (1D-CNNs) trained on raw waveforms by mapping these representations back into the discrete-time input signal domain, highlighting substructures in the input …
-
Feature Representations for Visual and Language Task: Towards Deeper Video Understanding
Yang Z., Garcia N., Chu C., et al. A comparative study of language transformers for video question answering. Neurocomputing 445, 121 (2021); https://doi.org/10.1016/j.neucom.2021.02.092.
-
Actigraphy Feature Representations for Mild Cognitive Impairment Classification: Comparing Summary, Circadian and Wavelet Features across Sensitivity–Specificity Operating Points
Η ήπια γνωστική διαταραχή (MCI) χαρακτηρίζεται από γνωστικά ελλείμματα πέραν των αναμενόμενων για τη φυσιολογική γήρανση, χωρίς σημαντικό περιορισμό της αυτονομίας στις καθημερινές δραστηριότητες. Η ακτιγραφία αποτελεί μη επεμβατική μέθοδο καταγραφής των προτύπων ανάπαυσης–δραστηριότητας και …
-
Improving Representation Learning for Diverse Modalities and Distributions with Metric Learning
… information from data and creating enhanced feature representations. These representations have found applications in various computer vision tasks, such as face recognition, image retrieval, and few-shot learning, to name a few. One of the major factors that play a vital role in creating …
-
Leveraging Foundation Models for Wave-Based Sensing Classification Tasks
… learning approaches by comparing different feature representations such as the raw waveform and time-frequency feature representations. Additionally, trainable encoders to improve the feature embeddings and classifcation performance are also explored in this work. The results show that the …
-
Leveraging Foundation Models for Wave-Based Sensing Classification Tasks
… learning approaches by comparing different feature representations such as the raw waveform and time-frequency feature representations. Additionally, trainable encoders to improve the feature embeddings and classifcation performance are also explored in this work. The results show that the …
-
Leveraging Foundation Models for Wave-Based Sensing Classification Tasks
… learning approaches by comparing different feature representations such as the raw waveform and time-frequency feature representations. Additionally, trainable encoders to improve the feature embeddings and classifcation performance are also explored in this work. The results show that the …
-
Theory-Guided Algorithm Design for Scalable Machine Learning
… role: fair machine learning and randomized feature representations. In fair machine learning, my research concentrates on achieving individual fairness in the single model and decoupled model settings with minimum data labeling budgets. For randomized feature representations, I propose a …
-
Representation Learning for Partitioning Problems
… methods assume the knowledge of a mapping into a feature space. Their statistical performance can, however, be impeded if this mapping, usually called a feature representation, is improperly specified or simply unknown. As larger datasets become available we can contemplate the possibility of, …
-
Detecting Common Objects in Context
… scale datasets, high quality annotations, and feature representations learned with novel convolutional neural network architectures. This thesis discusses both the process of dataset creation and the subsequent challenges in algorithm design for object detection. We create a large scale visual …
-
Towards Robust and Fair Vision Learning in Open-World Environments
… achieved impressive performance, their knowledge representations are often uninterpretable. These challenges motivate this dissertation to develop novel approaches toward fairness and robustness in vision learning. To address these challenges, the dissertation presents four key contributions …
Page 1 of 14