Advancing human pose and gesture recognition

<p>This thesis presents new methods in two closely related areas of computer vision: human pose estimation, and gesture recognition in videos.</p> <p>In human pose estimation, we show that random forests can be used to estimate human pose in monocular videos. To this end, we propos...

ver descrição completa

Detalhes bibliográficos
Autor principal: Pfister, T
Outros Autores: Zisserman, A
Formato: Tese
Idioma:English
Publicado em: 2015
Assuntos: