A Deep Neural Network Tool for Automatic Segmentation of Human Body Parts in Natural Scenes

Patrick McClure; Gabrielle Reimann; Michal Ramot; Francisco Pereira

A Deep Neural Network Tool for Automatic Segmentation of Human Body Parts in Natural Scenes

Patrick McClure, Gabrielle Reimann, Michal Ramot, Francisco Pereira

Research output: Contribution to journal › Article

Abstract

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.

Original language	English
Article number	2009.09900
Number of pages	4
Journal	arXiv
State	Published Online - 8 Sep 2020
Externally published	Yes

Access to Document

https://arxiv.org/abs/2009.09900License: Other

Cite this

@article{d1130fbaa2324e8580f7889791ee5592,

title = "A Deep Neural Network Tool for Automatic Segmentation of Human Body Parts in Natural Scenes",

abstract = "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.",

author = "Patrick McClure and Gabrielle Reimann and Michal Ramot and Francisco Pereira",

note = "N/A",

year = "2020",

month = sep,

day = "8",

language = "الإنجليزيّة",

}

TY - JOUR

T1 - A Deep Neural Network Tool for Automatic Segmentation of Human Body Parts in Natural Scenes

AU - McClure, Patrick

AU - Reimann, Gabrielle

AU - Ramot, Michal

AU - Pereira, Francisco

N1 - N/A

PY - 2020/9/8

Y1 - 2020/9/8

N2 - 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.

AB - 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.

M3 - مقالة

SN - 2331-8422

JO - arXiv

JF - arXiv

M1 - 2009.09900

ER -