No Cover Image

Conference Paper/Proceeding/Abstract 1787 views 305 downloads

Nested Shallow CNN-Cascade for Face Detection in the Wild

Jingjing Deng, Xianghua Xie Orcid Logo

2017 IEEE 12th International Conference on Automatic Face & Gesture Recognition, Pages: 165 - 172

Swansea University Authors: Jingjing Deng, Xianghua Xie Orcid Logo

DOI (Published version): 10.1109/FG.2017.29

Abstract

We propose a nested CNN-cascade learning algorithm that adopts shallow neural network architectures that allow efficient and progressive elimination of negative hypothesis from easy to hard via self-learning discriminative representations from coarse to fine scales. The face detection problem is con...

Full description

Published in: 2017 IEEE 12th International Conference on Automatic Face & Gesture Recognition
ISBN: 978-1-5090-4024-7 978-1-5090-4023-0
Published: IEEE 2017
Online Access: http://csvision.swan.ac.uk/uploads/Site/Publication/jd17fg.pdf
URI: https://cronfa.swan.ac.uk/Record/cronfa32108
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2017-02-25T05:04:38Z
last_indexed 2021-01-29T03:49:48Z
id cronfa32108
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2021-01-28T13:20:48.0322638</datestamp><bib-version>v2</bib-version><id>32108</id><entry>2017-02-24</entry><title>Nested Shallow CNN-Cascade for Face Detection in the Wild</title><swanseaauthors><author><sid>6f6d01d585363d6dc1622640bb4fcb3f</sid><firstname>Jingjing</firstname><surname>Deng</surname><name>Jingjing Deng</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>b334d40963c7a2f435f06d2c26c74e11</sid><ORCID>0000-0002-2701-8660</ORCID><firstname>Xianghua</firstname><surname>Xie</surname><name>Xianghua Xie</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2017-02-24</date><abstract>We propose a nested CNN-cascade learning algorithm that adopts shallow neural network architectures that allow efficient and progressive elimination of negative hypothesis from easy to hard via self-learning discriminative representations from coarse to fine scales. The face detection problem is considered as solving three sub-problems: eliminating easy background with a simple but fast model, then localising the face region with a soft-cascade, followed by precise detection and localisation by verifying retained regions with a deeper and stronger model.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>2017 IEEE 12th International Conference on Automatic Face &amp; Gesture Recognition</journal><volume/><journalNumber/><paginationStart>165</paginationStart><paginationEnd>172</paginationEnd><publisher>IEEE</publisher><placeOfPublication/><isbnPrint>978-1-5090-4024-7</isbnPrint><isbnElectronic>978-1-5090-4023-0</isbnElectronic><issnPrint/><issnElectronic/><keywords>Deep Learning, Neural Network, Face Detection, CNN</keywords><publishedDay>29</publishedDay><publishedMonth>6</publishedMonth><publishedYear>2017</publishedYear><publishedDate>2017-06-29</publishedDate><doi>10.1109/FG.2017.29</doi><url>http://csvision.swan.ac.uk/uploads/Site/Publication/jd17fg.pdf</url><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><apcterm/><lastEdited>2021-01-28T13:20:48.0322638</lastEdited><Created>2017-02-24T23:46:07.2461762</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Jingjing</firstname><surname>Deng</surname><order>1</order></author><author><firstname>Xianghua</firstname><surname>Xie</surname><orcid>0000-0002-2701-8660</orcid><order>2</order></author></authors><documents><document><filename>0032108-27052017151854.pdf</filename><originalFilename>FG2017CRC.pdf</originalFilename><uploaded>2017-05-27T15:18:54.0230000</uploaded><type>Output</type><contentLength>17090590</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2017-05-27T00:00:00.0000000</embargoDate><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling 2021-01-28T13:20:48.0322638 v2 32108 2017-02-24 Nested Shallow CNN-Cascade for Face Detection in the Wild 6f6d01d585363d6dc1622640bb4fcb3f Jingjing Deng Jingjing Deng true false b334d40963c7a2f435f06d2c26c74e11 0000-0002-2701-8660 Xianghua Xie Xianghua Xie true false 2017-02-24 We propose a nested CNN-cascade learning algorithm that adopts shallow neural network architectures that allow efficient and progressive elimination of negative hypothesis from easy to hard via self-learning discriminative representations from coarse to fine scales. The face detection problem is considered as solving three sub-problems: eliminating easy background with a simple but fast model, then localising the face region with a soft-cascade, followed by precise detection and localisation by verifying retained regions with a deeper and stronger model. Conference Paper/Proceeding/Abstract 2017 IEEE 12th International Conference on Automatic Face & Gesture Recognition 165 172 IEEE 978-1-5090-4024-7 978-1-5090-4023-0 Deep Learning, Neural Network, Face Detection, CNN 29 6 2017 2017-06-29 10.1109/FG.2017.29 http://csvision.swan.ac.uk/uploads/Site/Publication/jd17fg.pdf COLLEGE NANME COLLEGE CODE Swansea University 2021-01-28T13:20:48.0322638 2017-02-24T23:46:07.2461762 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Jingjing Deng 1 Xianghua Xie 0000-0002-2701-8660 2 0032108-27052017151854.pdf FG2017CRC.pdf 2017-05-27T15:18:54.0230000 Output 17090590 application/pdf Accepted Manuscript true 2017-05-27T00:00:00.0000000 true eng
title Nested Shallow CNN-Cascade for Face Detection in the Wild
spellingShingle Nested Shallow CNN-Cascade for Face Detection in the Wild
Jingjing Deng
Xianghua Xie
title_short Nested Shallow CNN-Cascade for Face Detection in the Wild
title_full Nested Shallow CNN-Cascade for Face Detection in the Wild
title_fullStr Nested Shallow CNN-Cascade for Face Detection in the Wild
title_full_unstemmed Nested Shallow CNN-Cascade for Face Detection in the Wild
title_sort Nested Shallow CNN-Cascade for Face Detection in the Wild
author_id_str_mv 6f6d01d585363d6dc1622640bb4fcb3f
b334d40963c7a2f435f06d2c26c74e11
author_id_fullname_str_mv 6f6d01d585363d6dc1622640bb4fcb3f_***_Jingjing Deng
b334d40963c7a2f435f06d2c26c74e11_***_Xianghua Xie
author Jingjing Deng
Xianghua Xie
author2 Jingjing Deng
Xianghua Xie
format Conference Paper/Proceeding/Abstract
container_title 2017 IEEE 12th International Conference on Automatic Face & Gesture Recognition
container_start_page 165
publishDate 2017
institution Swansea University
isbn 978-1-5090-4024-7
978-1-5090-4023-0
doi_str_mv 10.1109/FG.2017.29
publisher IEEE
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
url http://csvision.swan.ac.uk/uploads/Site/Publication/jd17fg.pdf
document_store_str 1
active_str 0
description We propose a nested CNN-cascade learning algorithm that adopts shallow neural network architectures that allow efficient and progressive elimination of negative hypothesis from easy to hard via self-learning discriminative representations from coarse to fine scales. The face detection problem is considered as solving three sub-problems: eliminating easy background with a simple but fast model, then localising the face region with a soft-cascade, followed by precise detection and localisation by verifying retained regions with a deeper and stronger model.
published_date 2017-06-29T03:39:18Z
_version_ 1763751764262125568
score 11.035634

Similar Items