This dissertation interrogates postcolonial cities’ syncretic territories, using Huế’s mnemonic sites – historically and culturally significant locales that aid in remembrance – to explore displaced communities’ cohabitation tactics and decolonization effo ...
This paper introduces TACOSS a text-image alignment approach that allows explainable land cover semantic segmentation by directly integrating semantic concepts encoded from texts. TACOSS combines convolutional neural networks for visual feature extraction ...
The Institute of Electrical and Electronics Engineers, Inc2023
Natural language processing has experienced significant improvements with the development of Transformer-based models, which employ self-attention mechanism and pre-training strategies. However, these models still present several obstacles. A notable issue ...
In this dissertation, we propose multiple methods to improve transfer learning for pretrained language models (PLMs). Broadly, transfer learning is a powerful technique in natural language processing, where a language model is first pre-trained on a data-r ...
Information collected through sensor measurements has the potential to improve knowledge of complex-system behavior, leading to better decisions related to system management. In this situation, and particularly when using digital twins, the quality of sens ...
This simulation-based study aimed to contribute to gaining knowledge on how much the deviation between occupant-related input by the national standard and by insitu measurements might impact predictions of heating/cooling needs in offices. Analysis was per ...
This paper explores a novel application of textual semantic similarity to user-preference representation for rating prediction. The approach represents a user's preferences as a graph of textual snippets from review text, where the edges are defined by sem ...
Train stations have increasingly become crowded, necessitating stringent requirements in the design of stations and commuter navigation through these stations. In this study, we explored the use of mobile eye tracking in combination with observation and a ...
