Max Margin AND/OR Graph learning for parsing the human body

We present a novel structure learning method, Max Margin AND/OR Graph (MM-AOG), for parsing the human body into parts and recovering their poses. Our method represents the human body and its parts by an AND/OR graph, which is a multi-level mixture of Markov Random Fields (MRFs). Max-margin learning, which is a generalization of the training algorithm for support vector machines (SVMs), is used to learn the parameters of the AND/OR graph model discriminatively. There are four advantages from this combination of AND/OR graphs and max-margin learning. Firstly, the AND/OR graph allows us to handle enormous articulated poses with a compact graphical model. Secondly, max-margin learning has more discriminative power than the traditional maximum likelihood approach. Thirdly, the parameters of the AND/OR graph model are optimized globally. In particular, the weights of the appearance model for individual nodes and the relative importance of spatial relationships between nodes are learnt simul...

• Type: Conference
• Year: 2008
• Where: CVPR
• Authors: Long Zhu, Yuanhao Chen, Yifei Lu, Chenxi Lin, Alan L. Yuille
• Keywords: And/or Graph Model, Compact Graphical Model, Computer Vision, CVPR 2008, Enormous Articulated Poses, Margin And/or Graph, Structure Learning Method