Generative Adversarial Networks (GANs) have taken on a significant role in the fashion industry, influencing how designers develop and how consumers interact with fashion. This research introduces an innovative application that uses GANs and word embedding techniques to show the importance of GANs in the fashion industry to create fashion illustrations based on written descriptions. First, the significance of word embedding for understanding the linguistic connections between words is discussed. Then, GANs' significance in the fashion industry is explained, highlighting their function in trend prediction and creativity. Next, the novel method, Text2FashionGAN which uses GAN technology and word embedding to create fashion images from text inputs is explained. Text2FashionGAN helps people find trends that suit their tastes while enabling designers to easily generate ideas by bridging the text-to-image gap. With the revolutionary potential of GANs and the practicality of textual descriptions, this method revolutionizes fashion recommendations for both designers and consumers.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Text2FashionGAN: Augmenting Personalized Style Recommendations with cGANs and Word2Vec


    Beteiligte:
    Madhan, S (Autor:in) / B, Neha (Autor:in) / Neemkar, Sandeep (Autor:in) / Abhishek, S (Autor:in) / T, Anjali (Autor:in)


    Erscheinungsdatum :

    22.11.2023


    Format / Umfang :

    2766478 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Matching Transportation Ontologies with Word2Vec and Alignment Extraction Algorithm

    Xingsi Xue / Haolin Wang / Jie Zhang et al. | DOAJ | 2021

    Freier Zugriff


    The Establishment of Human-Computer Interaction Based on Word2Vec

    Lin, Bo-Sheng / Wang, Chuin-Mu / Yu, Cheng-Ning | British Library Conference Proceedings | 2017


    Personalized Recommendations Based on Vehicle Portraits

    Li, Na / Ji, Zhenlei / Song, Gang et al. | IEEE | 2024