Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Amadeus, Marcellus"'
Recent surveys on data augmentation for natural language processing have reported different techniques and advancements in the field. Several frameworks, tools, and repositories promote the implementation of text data augmentation pipelines. However,
Externí odkaz:
http://arxiv.org/abs/2402.06766
Speech technologies rely on capturing a speaker's voice variability while obtaining comprehensive language information. Textual prompts and sentence selection methods have been proposed in the literature to comprise such adequate phonetic data, refer
Externí odkaz:
http://arxiv.org/abs/2402.05794
This work presents the early development of a model of image captioning for the Brazilian Portuguese language. We used the GRIT (Grid - and Region-based Image captioning Transformer) model to accomplish this work. GRIT is a Transformer-only neural ar
Externí odkaz:
http://arxiv.org/abs/2402.05106
Autor:
Perche-Mahlow, Felipe Rodrigues, Felipe-Zanella, André, Cruz-Castañeda, William Alberto, Amadeus, Marcellus
In recent years, groundbreaking advancements in Generative Artificial Intelligence (GenAI) have triggered a transformative paradigm shift, significantly influencing various domains. In this work, we specifically explore an integrated approach, levera
Externí odkaz:
http://arxiv.org/abs/2402.03501
Autor:
Amadeus, Marcellus, Castañeda, William Alberto Cruz, Zanella, André Felipe, Mahlow, Felipe Rodrigues Perche
Generative AI has become pervasive in society, witnessing significant advancements in various domains. Particularly in the realm of Text-to-Image (TTI) models, Latent Diffusion Models (LDMs), showcase remarkable capabilities in generating visual cont
Externí odkaz:
http://arxiv.org/abs/2401.05520
Autor:
Amadeus, Marcellus, Branco, Paulo
Improving machine learning performance while increasing model generalization has been a constantly pursued goal by AI researchers. Data augmentation techniques are often used towards achieving this target, and most of its evaluation is made using Eng
Externí odkaz:
http://arxiv.org/abs/2304.02785