论文标题
自然场景中人体部位自动分割的深度神经网络工具
A Deep Neural Network Tool for Automatic Segmentation of Human Body Parts in Natural Scenes
论文作者
论文摘要
这篇简短的文章描述了一个深层的神经网络，该网络训练有素，可以在自然场景中对人体部位进行自动分割。更具体地说，我们在Pascal-Parts数据集上训练了一个带有混凝土掉落的贝叶斯塞格内特，以预测给定框架中的每个像素是否是一个人的头发，头部，耳朵，眉毛，腿，手臂，嘴巴，嘴巴，脖子，鼻子或躯干的一部分。
This short article describes a deep neural network trained to perform automatic segmentation of human body parts in natural scenes. More specifically, we trained a Bayesian SegNet with concrete dropout on the Pascal-Parts dataset to predict whether each pixel in a given frame was part of a person's hair, head, ear, eyebrows, legs, arms, mouth, neck, nose, or torso.
