No Cover Image

Other 725 views

Classification of Non-edited Broadcast Video Using Holistic Low-level Features

Roach Matthew, Xu Li-qun, Mason John, Heath Martlesham, Ip Ipswich, Matt Roach Orcid Logo

Int. Tyrrhenian Workshop on Digital Communications (IWDC)

Swansea University Author: Matt Roach Orcid Logo

Abstract

A data driven learning based approach has been adopted to classify a video programme into a set of five pre-defined genre including a7orts, cartoons, news, commercials and music. The video database studied is a collection of five-hour non-edited TV broadcast programme of dozens of video clips: one h...

Full description

Published in: Int. Tyrrhenian Workshop on Digital Communications (IWDC)
Published: 2002
URI: https://cronfa.swan.ac.uk/Record/cronfa39129
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2018-03-22T05:12:36Z
last_indexed 2018-03-22T05:12:36Z
id cronfa39129
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2018-03-21T20:19:42.2652639</datestamp><bib-version>v2</bib-version><id>39129</id><entry>2018-03-21</entry><title>Classification of Non-edited Broadcast Video Using Holistic Low-level Features</title><swanseaauthors><author><sid>9722c301d5bbdc96e967cdc629290fec</sid><ORCID>0000-0002-1486-5537</ORCID><firstname>Matt</firstname><surname>Roach</surname><name>Matt Roach</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2018-03-21</date><deptcode>SCS</deptcode><abstract>A data driven learning based approach has been adopted to classify a video programme into a set of five pre-defined genre including a7orts, cartoons, news, commercials and music. The video database studied is a collection of five-hour non-edited TV broadcast programme of dozens of video clips: one hour long in total for each genre with an even split of training and testing data. This paper reports the classification result for the two media modes - acoustic and visual - used separately, and for a linear fusion of the two modes at the score level. The correaIonding classification accuracy achieved is approximately 74%, 73%, and 87%, reaIectively, given a 30-second decision window, or for every 30 second non-overlap video segment an answer of its identity is provided Further analysis of the confusion matrices of the classification errors is given. The extension of the approach to the open-set video genre verification and semantic scene segmentation and classification is expected.</abstract><type>Other</type><journal>Int. Tyrrhenian Workshop on Digital Communications (IWDC)</journal><volume></volume><journalNumber></journalNumber><paginationStart/><paginationEnd/><publisher/><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords/><publishedDay>31</publishedDay><publishedMonth>12</publishedMonth><publishedYear>2002</publishedYear><publishedDate>2002-12-31</publishedDate><doi/><url/><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2018-03-21T20:19:42.2652639</lastEdited><Created>2018-03-21T20:19:42.2652639</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>Roach</firstname><surname>Matthew</surname><order>1</order></author><author><firstname>Xu</firstname><surname>Li-qun</surname><order>2</order></author><author><firstname>Mason</firstname><surname>John</surname><order>3</order></author><author><firstname>Heath</firstname><surname>Martlesham</surname><order>4</order></author><author><firstname>Ip</firstname><surname>Ipswich</surname><order>5</order></author><author><firstname>Matt</firstname><surname>Roach</surname><orcid>0000-0002-1486-5537</orcid><order>6</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling 2018-03-21T20:19:42.2652639 v2 39129 2018-03-21 Classification of Non-edited Broadcast Video Using Holistic Low-level Features 9722c301d5bbdc96e967cdc629290fec 0000-0002-1486-5537 Matt Roach Matt Roach true false 2018-03-21 SCS A data driven learning based approach has been adopted to classify a video programme into a set of five pre-defined genre including a7orts, cartoons, news, commercials and music. The video database studied is a collection of five-hour non-edited TV broadcast programme of dozens of video clips: one hour long in total for each genre with an even split of training and testing data. This paper reports the classification result for the two media modes - acoustic and visual - used separately, and for a linear fusion of the two modes at the score level. The correaIonding classification accuracy achieved is approximately 74%, 73%, and 87%, reaIectively, given a 30-second decision window, or for every 30 second non-overlap video segment an answer of its identity is provided Further analysis of the confusion matrices of the classification errors is given. The extension of the approach to the open-set video genre verification and semantic scene segmentation and classification is expected. Other Int. Tyrrhenian Workshop on Digital Communications (IWDC) 31 12 2002 2002-12-31 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University 2018-03-21T20:19:42.2652639 2018-03-21T20:19:42.2652639 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Roach Matthew 1 Xu Li-qun 2 Mason John 3 Heath Martlesham 4 Ip Ipswich 5 Matt Roach 0000-0002-1486-5537 6
title Classification of Non-edited Broadcast Video Using Holistic Low-level Features
spellingShingle Classification of Non-edited Broadcast Video Using Holistic Low-level Features
Matt Roach
title_short Classification of Non-edited Broadcast Video Using Holistic Low-level Features
title_full Classification of Non-edited Broadcast Video Using Holistic Low-level Features
title_fullStr Classification of Non-edited Broadcast Video Using Holistic Low-level Features
title_full_unstemmed Classification of Non-edited Broadcast Video Using Holistic Low-level Features
title_sort Classification of Non-edited Broadcast Video Using Holistic Low-level Features
author_id_str_mv 9722c301d5bbdc96e967cdc629290fec
author_id_fullname_str_mv 9722c301d5bbdc96e967cdc629290fec_***_Matt Roach
author Matt Roach
author2 Roach Matthew
Xu Li-qun
Mason John
Heath Martlesham
Ip Ipswich
Matt Roach
format Other
container_title Int. Tyrrhenian Workshop on Digital Communications (IWDC)
publishDate 2002
institution Swansea University
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
document_store_str 0
active_str 0
description A data driven learning based approach has been adopted to classify a video programme into a set of five pre-defined genre including a7orts, cartoons, news, commercials and music. The video database studied is a collection of five-hour non-edited TV broadcast programme of dozens of video clips: one hour long in total for each genre with an even split of training and testing data. This paper reports the classification result for the two media modes - acoustic and visual - used separately, and for a linear fusion of the two modes at the score level. The correaIonding classification accuracy achieved is approximately 74%, 73%, and 87%, reaIectively, given a 30-second decision window, or for every 30 second non-overlap video segment an answer of its identity is provided Further analysis of the confusion matrices of the classification errors is given. The extension of the approach to the open-set video genre verification and semantic scene segmentation and classification is expected.
published_date 2002-12-31T03:49:40Z
_version_ 1763752416596983808
score 10.997956

Similar Items