Flowing ConvNets for human pose estimation in videos

The objective of this work is human pose estimation in videos, where multiple frames are available. We investigate a ConvNet architecture that is able to benefit from temporal context by combining information across the multiple frames using optical flow. To this end we propose a network architectur...

Descripción completa

Detalles Bibliográficos
Autores principales: Pfister, T, Charles, J, Zisserman, A
Formato: Conference item
Publicado: IEEE 2016