上海科技大学知识管理系统

This paper presents a novel Separation-and-UnioN Network (SUNNet) for simultaneous human parsing and pose estimation. Our SUNNet consists of two stages: a feature separation stage and a feature union stage. In feature separation stage, we leverage a common feature extractor to implicitly encode the cor-relation between human parsing and pose estimation, meanwhile, two task-specific feature extractors are designed to extract the features for both tasks. By combining the task-specific features and common features with a feature consolidation module in a coarse-to-fine manner, we can get an initial prediction for parsing and pose estimation; In feature union stage, we refine the initial prediction by explicitly lever-aging the features from parallel task to predict the kernels' receptive fields in a convolutional neural net-work. We further propose to leverage a 3D human body reconstructed from the image to facilitate these tasks, and a novel Gated Feature Fusion (GFF) block is designed to automatically decide whether to use or skip the priors from the reconstructed 3D human body. Extensive experiments demonstrate the effective-ness of our SUNNet model for human body configuration analysis. (c) 2020 Published by Elsevier B.V.