A deformable mixture parsing model with parselets

Abstract

In this work, we address the problem of human parsing, namely partitioning the human body into semantic regions, by using the novel Parse let representation. Previous works often consider solving the problem of human pose estimation as the prerequisite of human parsing. We argue that these approaches cannot obtain optimal pixel level parsing due to the inconsistent targets between these tasks. In this paper, we propose to use Parse lets as the building blocks of our parsing model. Parse lets are a group of parsable segments which can generally be obtained by low-level over-segmentation algorithms and bear strong semantic meaning. We then build a Deformable Mixture Parsing Model~(DMPM) for human parsing to simultaneously handle the deformation and multi-modalities of Parse lets. The proposed model has two unique characteristics: (1) the possible numerous modalities of Parse let ensembles are exhibited as the "And-Or' structure of sub-trees, (2) to further solve the practical problem of Parse let occlusion or absence, we directly model the visibility property at some leaf nodes. The DMPM thus directly solves the problem of human parsing by searching for the best graph configuration from a pool of Parse let hypotheses without intermediate tasks. Comprehensive evaluations demonstrate the encouraging performance of the proposed approach. © 2013 IEEE.