Scene understanding using deep learning

Deep learning is a type of machine perception method that attempts to model high-level abstractions in data and encode them into a compact and robust representation. Such representations have found immense usage in applications related to computer vision. In this chapter we introduce two such applic...

Descripción completa

Detalles Bibliográficos
Autores: Husain, Farzad, Dellen, Babette, Torras, Carme
Tipo de recurso: otro
Estado:Versión enviada para evaluación y publicación
Fecha de publicación:2017
País:España
Institución:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/168996
Acceso en línea:http://hdl.handle.net/10261/168996
Access Level:acceso abierto
Palabra clave:Semantic segmentation
Action recognition
Deep learning
Descripción
Sumario:Deep learning is a type of machine perception method that attempts to model high-level abstractions in data and encode them into a compact and robust representation. Such representations have found immense usage in applications related to computer vision. In this chapter we introduce two such applications, i.e., semantic segmentation of images and action recognition in videos. These applications are of fundamental importance for human-centered environment perception.