Help Guide Disclaimer Contact us Login
  Advanced SearchBrowse




Conference Paper

Posebits for Monocular Human Pose Estimation


Pons-Moll,  Gerard
Dept. Perceiving Systems, Max Planck Institute for Intelligent Systems, Max Planck Society;

There are no locators available
Fulltext (public)
There are no public fulltexts available
Supplementary Material (public)
There is no public supplementary material available

Pons-Moll, G., Fleet, D. J., & Rosenhahn, B. (2014). Posebits for Monocular Human Pose Estimation. In 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014) (pp. 2345-2352). Los Alamitos, CA: IEEE Computer Society. doi:10.1109/CVPR.2014.300.

Cite as:
We advocate the inference of qualitative information about 3D human pose, called posebits, from images. Posebits represent boolean geometric relationships between body parts (e.g., left-leg in front of right-leg or hands close to each other). The advantages of posebits as a mid-level representation are 1) for many tasks of interest, such qualitative pose information may be sufficient (e.g. \, semantic image retrieval), 2) it is relatively easy to annotate large image corpora with posebits, as it simply requires answers to yes/no questions; and 3) they help resolve challenging pose ambiguities and therefore facilitate the difficult talk of image-based 3D pose estimation. We introduce posebits, a posebit database, a method for selecting useful posebits for pose estimation and a structural SVM model for posebit inference. Experiments show the use of posebits for semantic image retrieval and for improving 3D pose estimation.