Temporal Action Detection in Untrimmed Videos from Fine to Coarse Granularity

Temporal action detection in long, untrimmed videos is an important yet challenging task that requires not only recognizing the categories of actions in videos, but also localizing the start and end times of each action. Recent years, artificial neural networks, such as Convolutional Neural Network...

Descripción completa

Detalles Bibliográficos

Autores principales:	Guangle Yao, Tao Lei, Xianyuan Liu, Ping Jiang
Formato:	Artigo
Lenguaje:	Inglês
Publicado:	MDPI AG 2018-10-01
Colección:	Applied Sciences
Materias:	action detection action proposal convolutional neural network regression network
Acceso en línea:	http://www.mdpi.com/2076-3417/8/10/1924
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!