Sökning: "Visual World paradigm"

Visar resultat 1 - 5 av 8 avhandlingar innehållade orden Visual World paradigm.

  1. 1. One of a kind. The processing of indefinite one-anaphora in spoken Danish

    Författare :Philip Diderichsen; Kognitionsvetenskap; []
    Nyckelord :HUMANIORA; HUMANITIES; Accessibility; Referring expressions; Eye-tracking; Givenness; Spoken Danish; Visual World paradigm; Definiteness; Spoken language processing;

    Sammanfattning : It is a hallmark of natural language use that the way we talk about something reflects how it is represented in the mind of our conversation partner. This thesis studies the use and cognitive processing of referring expressions like one in comparison with other expression types in spoken Danish. LÄS MER

  3. 2. Self-supervised Representation Learning for Visual Domains Beyond Natural Scenes

    Författare :Prakash Chandra Chhipa; Marcus Liwicki; Seiichi Uchida; Rajkumar Saini; Josep Lladós; Luleå tekniska universitet; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; self-supervised learning; representation learning; computer vision; learning with few labels; Maskininlärning; Machine Learning;

    Sammanfattning : This thesis investigates the possibility of efficiently adapting self-supervised representation learning on visual domains beyond natural scenes, e.g., medical imagining and non-RGB sensory images. LÄS MER

  4. 3. Towards Accurate and Reliable Deep Regression Models

    Författare :Fredrik K. Gustafsson; Thomas B. Schön; Martin Danelljan; Søren Hauberg; Uppsala universitet; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Machine Learning; Deep Learning; Regression; Probabilistic Models; Energy-Based Models; Uncertainty Estimation; Machine learning; Maskininlärning;

    Sammanfattning : Regression is a fundamental machine learning task with many important applications within computer vision and other domains. In general, it entails predicting continuous targets from given inputs. LÄS MER

  5. 4. Random Forest for Histogram Data : An application in data-driven prognostic models for heavy-duty trucks

    Författare :Ram Bahadur Gurung; Henrik Boström; Tony Lindgren; Niklas Lavesson; Stockholms universitet; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Histogram data; random forest; NOx sensor failure; random forest interpretation; Computer and Systems Sciences; data- och systemvetenskap;

    Sammanfattning : Data mining and machine learning algorithms are trained on large datasets to find useful hidden patterns. These patterns can help to gain new insights and make accurate predictions. Usually, the training data is structured in a tabular format, where the rows represent the training instances and the columns represent the features of these instances. LÄS MER

  7. 5. "Not So Simple" : Reassessing 1951, G.B. Giorgini and the launch of Italian fashion

    Författare :Chiara Faggella; Louise Wallenberg; Alessandra Vaccari; Stephen Gundle; Stockholms universitet; []
    Nyckelord :HUMANIORA; HUMANITIES; SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; Italian fashion; Giovanni Battista Giorgini; Commissionaire; Fashion Buyer; Italian couture; Italian handicrafts; Italy at Work; Italian High Fashion Show; Florence fashion; Pitti Immagine; Italian studies; Postwar Italy; Occupation of Italy; modevetenskap; Fashion Studies;

    Sammanfattning : This dissertation aims to shed light on the circumstances that allowed Italy to become a reputable country of origin in the international fashion market. In particular, my contribution to the historiography of Italian fashion is a reassessment of the role played by Giovanni Battista Giorgini, whose involvement with the fashion and handicraft industries has not been fully investigated by scholars so far. LÄS MER