Multitask Learning-Based Affective Prediction for Videos of Films and TV Scenes

Film and TV video scenes contain rich art and design elements such as light and shadow, color, composition, and complex affects. To recognize the fine-grained affects of the art carrier, this paper proposes a multitask affective value prediction model based on an attention mechanism. After comparing...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Zhibin Su, Shige Lin, Luyue Zhang, Yiming Feng, Wei Jiang
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2024-05-01
coleção:	Applied Sciences
Assuntos:	film and TV scenes multitask learning fine-grained affects affective value prediction
Acesso em linha:	https://www.mdpi.com/2076-3417/14/11/4391
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!