Recurrent human pose estimation
We propose a novel ConvNet model for predicting 2D human body poses in an image. The model regresses a heatmap representation for each body keypoint, and is able to learn and represent both the part appearances and the context of the part configuration. We make the following three contributions: (i)...
Hoofdauteurs: | Belagiannis, V, Zisserman, A |
---|---|
Formaat: | Internet publication |
Taal: | English |
Gepubliceerd in: |
arXiv
2016
|
Gelijkaardige items
-
Recurrent human pose estimation
door: Belagiannis, V, et al.
Gepubliceerd in: (2017) -
Personalizing human video pose estimation
door: Charles, J, et al.
Gepubliceerd in: (2016) -
2D human pose estimation in TV shows
door: Ferrari, V, et al.
Gepubliceerd in: (2009) -
Progressive search space reduction for human pose estimation
door: Ferrari, V, et al.
Gepubliceerd in: (2008) -
Flowing ConvNets for human pose estimation in videos
door: Pfister, T, et al.
Gepubliceerd in: (2016)