Výsledky vyhledávání

Report

MMVA: Multimodal Matching Based on Valence and Arousal across Images, Music, and Musical Captions

Autor: Choi, Suhwan, Kim, Kyu Won, Kang, Myungjoo

We introduce Multimodal Matching based on Valence and Arousal (MMVA), a tri-modal encoder framework designed to capture emotional content across images, music, and musical captions. To support this framework, we expand the Image-Music-Emotion-Matchin

Externí odkaz: http://arxiv.org/abs/2501.01094

Zobrazit plný text záznamu

Report

Prompting for Discovery: Flexible Sense-Making for AI Art-Making with Dreamsheets

Autor: Almeda, Shm Garanganao, Zamfirescu-Pereira, J. D., Kim, Kyu Won, Rathnam, Pradeep Mani, Hartmann, Bjoern

Design space exploration (DSE) for Text-to-Image (TTI) models entails navigating a vast, opaque space of possible image outputs, through a commensurately vast input space of hyperparameters and prompt text. Minor adjustments to prompt input can surfa

Externí odkaz: http://arxiv.org/abs/2310.09985

Zobrazit plný text záznamu

Report

Interactive Flexible Style Transfer for Vector Graphics

Autor: Warner, Jeremy, Kim, Kyu Won, Hartmann, Bjoern

Vector graphics are an industry-standard way to represent and share visual designs. Designers frequently source and incorporate styles from existing designs into their own work. Unfortunately, popular design tools aren't well suited for this task. We

Externí odkaz: http://arxiv.org/abs/2309.11628

Zobrazit plný text záznamu