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)...
Главные авторы: | Belagiannis, V, Zisserman, A |
---|---|
Формат: | Internet publication |
Язык: | English |
Опубликовано: |
arXiv
2016
|
Схожие документы
-
Recurrent human pose estimation
по: Belagiannis, V, и др.
Опубликовано: (2017) -
Personalizing human video pose estimation
по: Charles, J, и др.
Опубликовано: (2016) -
2D human pose estimation in TV shows
по: Ferrari, V, и др.
Опубликовано: (2009) -
Progressive search space reduction for human pose estimation
по: Ferrari, V, и др.
Опубликовано: (2008) -
Flowing ConvNets for human pose estimation in videos
по: Pfister, T, и др.
Опубликовано: (2016)