Automating Annotation of Media with Linked Data Workflows

Thomas Wilmering; Kevin Page; György Fazekas; S Dixon; S Bechhofer

doi:10.1145/2740908.2742913

Automating Annotation of Media with Linked Data Workflows

Thomas Wilmering, Kevin Page, György Fazekas, S Dixon, S Bechhofer

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

193 Downloads (Pure)

Abstract

Computational feature extraction provides one means of gathering structured analytic metadata for large media collections. We demonstrate a suite of tools we have developed that automate the process of feature extraction from audio in the Internet Archive. The system constructs an RDF description of the analysis workflow and results which is then reconciled and combined with Linked Data about the recorded performance. This Linked Data and provenance information provides the bridging information necessary to employ analytic output in the generation of structured metadata for the underlying media files, with all data published within thesame description framework.

Original language	English
Title of host publication	Proceedings of the 24th International Conference on World Wide Web Companion
Publisher	ACM Digital Library
Pages	737-738
Number of pages	2
ISBN (Print)	978-1-4503-3473-0
DOIs	https://doi.org/10.1145/2740908.2742913
Publication status	Published - 2015
Event	WWW 2015 Companion - Florence, Italy Duration: 18 May 2015 → 22 May 2015

Conference

Conference	WWW 2015 Companion
City	Florence, Italy
Period	18/05/15 → 22/05/15

Keywords

audio metadata, feature extraction, linked data, semantic web

Access to Document

10.1145/2740908.2742913

FULL-TEXT

Cite this

@inproceedings{8e89897e0263440a96dabc6f36eba996,

title = "Automating Annotation of Media with Linked Data Workflows",

abstract = "Computational feature extraction provides one means of gathering structured analytic metadata for large media collections. We demonstrate a suite of tools we have developed that automate the process of feature extraction from audio in the Internet Archive. The system constructs an RDF description of the analysis workflow and results which is then reconciled and combined with Linked Data about the recorded performance. This Linked Data and provenance information provides the bridging information necessary to employ analytic output in the generation of structured metadata for the underlying media files, with all data published within thesame description framework.",

keywords = "audio metadata, feature extraction, linked data, semantic web",

author = "Thomas Wilmering and Kevin Page and Gy{\"o}rgy Fazekas and S Dixon and S Bechhofer",

note = "Accepted 25/02/2015; WWW 2015 Companion ; Conference date: 18-05-2015 Through 22-05-2015",

year = "2015",

doi = "10.1145/2740908.2742913",

language = "English",

isbn = "978-1-4503-3473-0",

pages = "737--738",

booktitle = "Proceedings of the 24th International Conference on World Wide Web Companion",

publisher = "ACM Digital Library",

address = "United States",

}

TY - GEN

T1 - Automating Annotation of Media with Linked Data Workflows

AU - Wilmering, Thomas

AU - Page, Kevin

AU - Fazekas, György

AU - Dixon, S

AU - Bechhofer, S

N1 - Accepted 25/02/2015

PY - 2015

Y1 - 2015

N2 - Computational feature extraction provides one means of gathering structured analytic metadata for large media collections. We demonstrate a suite of tools we have developed that automate the process of feature extraction from audio in the Internet Archive. The system constructs an RDF description of the analysis workflow and results which is then reconciled and combined with Linked Data about the recorded performance. This Linked Data and provenance information provides the bridging information necessary to employ analytic output in the generation of structured metadata for the underlying media files, with all data published within thesame description framework.

AB - Computational feature extraction provides one means of gathering structured analytic metadata for large media collections. We demonstrate a suite of tools we have developed that automate the process of feature extraction from audio in the Internet Archive. The system constructs an RDF description of the analysis workflow and results which is then reconciled and combined with Linked Data about the recorded performance. This Linked Data and provenance information provides the bridging information necessary to employ analytic output in the generation of structured metadata for the underlying media files, with all data published within thesame description framework.

KW - audio metadata, feature extraction, linked data, semantic web

U2 - 10.1145/2740908.2742913

DO - 10.1145/2740908.2742913

M3 - Conference contribution

SN - 978-1-4503-3473-0

SP - 737

EP - 738

BT - Proceedings of the 24th International Conference on World Wide Web Companion

PB - ACM Digital Library

T2 - WWW 2015 Companion

Y2 - 18 May 2015 through 22 May 2015

ER -

Automating Annotation of Media with Linked Data Workflows

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this