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)...
Main Authors: | Belagiannis, V, Zisserman, A |
---|---|
格式: | Internet publication |
语言: | English |
出版: |
arXiv
2016
|
相似书籍
-
Recurrent human pose estimation
由: Belagiannis, V, et al.
出版: (2017) -
Personalizing human video pose estimation
由: Charles, J, et al.
出版: (2016) -
2D human pose estimation in TV shows
由: Ferrari, V, et al.
出版: (2009) -
Progressive search space reduction for human pose estimation
由: Ferrari, V, et al.
出版: (2008) -
Flowing ConvNets for human pose estimation in videos
由: Pfister, T, et al.
出版: (2016)