Mixture of Parts Revisited: Expressive Part Interactions for Pose Estimation

Anoop R. Katti, Anurag Mittal; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2015, pp. 59-67

Abstract


Part-based models with restrictive tree-structured interactions for the Human Pose Estimation problem, leave many part interactions unhandled. Two of the most common and strong manifestations of such unhandled interactions are self-occlusion among the parts and the confusion in the localization of the non-adjacent symmetric parts. By handling the self-occlusion in a data efficient manner, we improve the performance of the basic Mixture of Parts model by a large margin, especially on difficult poses. We address the confusion in the symmetric limb localization using a combination of two complementing trees, showing an improvement in the performance on all the parts with a very small trade-off in the running time. Finally, we show that the combination of the two solutions improves the results. We compare our HOG-based method with other methods using similar features and report results equivalent to the best method on two standard datasets with a large reduction in the running time.

Related Material


[pdf]
[bibtex]
@InProceedings{Katti_2015_CVPR_Workshops,
author = {Katti, Anoop R. and Mittal, Anurag},
title = {Mixture of Parts Revisited: Expressive Part Interactions for Pose Estimation},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2015}
}