Art generative modeling is increasingly shifting towards methodologies that incorporate cross-modality and multimodality. This paper introduces an effective approach to advancing these research directions: Museart, a new music-image dataset that, thanks to its versatility and culturally oriented categorization, significantly enhances the artistic potential of AI in cross-modal generative contexts.
Museart: A Refined Music-Image Dataset
Alfredo Baione
Methodology
;Genoveffa Tortora
Supervision
In corso di stampa
Abstract
Art generative modeling is increasingly shifting towards methodologies that incorporate cross-modality and multimodality. This paper introduces an effective approach to advancing these research directions: Museart, a new music-image dataset that, thanks to its versatility and culturally oriented categorization, significantly enhances the artistic potential of AI in cross-modal generative contexts.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
