PoseField: an efficient mean-field based method for joint estimation of human pose, segmentation, and depth
Many models have been proposed to estimate human pose and segmentation by leveraging information from several sources. A standard approach is to formulate it in a dual decomposition framework. However, these models generally suffer from the problem of high computational complexity. In this work, we...
主要な著者: | Vineet, V, Sheasby, G, Warrell, J, Torr, PHS |
---|---|
フォーマット: | Conference item |
言語: | English |
出版事項: |
Springer
2013
|
類似資料
-
Simultaneous segmentation and pose estimation of humans using dynamic graph cuts
著者:: Kohli, P, 等
出版事項: (2008) -
POSECUT: simultaneous segmentation and 3d pose estimation of humans using dynamic graph-cuts
著者:: Bray, M, 等
出版事項: (2006) -
Filter-based mean-field inference for random fields with higher-order terms and product label-spaces
著者:: Vineet, V, 等
出版事項: (2012) -
Filter-based mean-field inference for random fields with higher-order terms and product label-spaces
著者:: Vineet, V, 等
出版事項: (2014) -
Gaussian process latent variable models for human pose estimation
著者:: Ek, CH, 等
出版事項: (2008)