Context-oriented web video tag recommendation

Zhineng Chen, Juan Cao, Yicheng Song, Junbo Guo, Yongdong Zhang, Jintao Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

17 Citations (Scopus)

Abstract

Tag recommendation is a common way to enrich the textual annotation of multimedia contents. However, state-of-the-art recommendation methods are built upon the pair-wised tag relevance, which hardly capture the context of the web video, i.e., when who are doing what at where. In this paper we propose the context-oriented tag recommendation (CtextR) approach, which expands tags for web videos under the context-consistent constraint. Given a web video, CtextR first collects the multi-form WWW resources describing the same event with the video, which produce an informative and consistent context; and then, the tag recommendation is conducted based on the obtained context. Experiments on an 80,031 web video collection show CtextR recommends various relevant tags to web videos. Moreover, the enriched tags improve the performance of web video categorization.

Original languageEnglish (US)
Title of host publicationProceedings of the 19th International Conference on World Wide Web, WWW '10
Pages1079-1080
Number of pages2
DOIs
StatePublished - Jul 20 2010
Event19th International World Wide Web Conference, WWW2010 - Raleigh, NC, United States
Duration: Apr 26 2010Apr 30 2010

Other

Other19th International World Wide Web Conference, WWW2010
CountryUnited States
CityRaleigh, NC
Period4/26/104/30/10

Fingerprint

World Wide Web
Experiments

Keywords

  • context-oriented
  • social tagging
  • tag recommendation
  • web video

Cite this

Chen, Z., Cao, J., Song, Y., Guo, J., Zhang, Y., & Li, J. (2010). Context-oriented web video tag recommendation. In Proceedings of the 19th International Conference on World Wide Web, WWW '10 (pp. 1079-1080) https://doi.org/10.1145/1772690.1772813

Context-oriented web video tag recommendation. / Chen, Zhineng; Cao, Juan; Song, Yicheng; Guo, Junbo; Zhang, Yongdong; Li, Jintao.

Proceedings of the 19th International Conference on World Wide Web, WWW '10. 2010. p. 1079-1080.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chen, Z, Cao, J, Song, Y, Guo, J, Zhang, Y & Li, J 2010, Context-oriented web video tag recommendation. in Proceedings of the 19th International Conference on World Wide Web, WWW '10. pp. 1079-1080, 19th International World Wide Web Conference, WWW2010, Raleigh, NC, United States, 4/26/10. https://doi.org/10.1145/1772690.1772813
Chen Z, Cao J, Song Y, Guo J, Zhang Y, Li J. Context-oriented web video tag recommendation. In Proceedings of the 19th International Conference on World Wide Web, WWW '10. 2010. p. 1079-1080 https://doi.org/10.1145/1772690.1772813
Chen, Zhineng ; Cao, Juan ; Song, Yicheng ; Guo, Junbo ; Zhang, Yongdong ; Li, Jintao. / Context-oriented web video tag recommendation. Proceedings of the 19th International Conference on World Wide Web, WWW '10. 2010. pp. 1079-1080
@inproceedings{a14a1a066c94400d9a79359b47336b2a,
title = "Context-oriented web video tag recommendation",
abstract = "Tag recommendation is a common way to enrich the textual annotation of multimedia contents. However, state-of-the-art recommendation methods are built upon the pair-wised tag relevance, which hardly capture the context of the web video, i.e., when who are doing what at where. In this paper we propose the context-oriented tag recommendation (CtextR) approach, which expands tags for web videos under the context-consistent constraint. Given a web video, CtextR first collects the multi-form WWW resources describing the same event with the video, which produce an informative and consistent context; and then, the tag recommendation is conducted based on the obtained context. Experiments on an 80,031 web video collection show CtextR recommends various relevant tags to web videos. Moreover, the enriched tags improve the performance of web video categorization.",
keywords = "context-oriented, social tagging, tag recommendation, web video",
author = "Zhineng Chen and Juan Cao and Yicheng Song and Junbo Guo and Yongdong Zhang and Jintao Li",
year = "2010",
month = "7",
day = "20",
doi = "10.1145/1772690.1772813",
language = "English (US)",
isbn = "9781605587998",
pages = "1079--1080",
booktitle = "Proceedings of the 19th International Conference on World Wide Web, WWW '10",

}

TY - GEN

T1 - Context-oriented web video tag recommendation

AU - Chen, Zhineng

AU - Cao, Juan

AU - Song, Yicheng

AU - Guo, Junbo

AU - Zhang, Yongdong

AU - Li, Jintao

PY - 2010/7/20

Y1 - 2010/7/20

N2 - Tag recommendation is a common way to enrich the textual annotation of multimedia contents. However, state-of-the-art recommendation methods are built upon the pair-wised tag relevance, which hardly capture the context of the web video, i.e., when who are doing what at where. In this paper we propose the context-oriented tag recommendation (CtextR) approach, which expands tags for web videos under the context-consistent constraint. Given a web video, CtextR first collects the multi-form WWW resources describing the same event with the video, which produce an informative and consistent context; and then, the tag recommendation is conducted based on the obtained context. Experiments on an 80,031 web video collection show CtextR recommends various relevant tags to web videos. Moreover, the enriched tags improve the performance of web video categorization.

AB - Tag recommendation is a common way to enrich the textual annotation of multimedia contents. However, state-of-the-art recommendation methods are built upon the pair-wised tag relevance, which hardly capture the context of the web video, i.e., when who are doing what at where. In this paper we propose the context-oriented tag recommendation (CtextR) approach, which expands tags for web videos under the context-consistent constraint. Given a web video, CtextR first collects the multi-form WWW resources describing the same event with the video, which produce an informative and consistent context; and then, the tag recommendation is conducted based on the obtained context. Experiments on an 80,031 web video collection show CtextR recommends various relevant tags to web videos. Moreover, the enriched tags improve the performance of web video categorization.

KW - context-oriented

KW - social tagging

KW - tag recommendation

KW - web video

UR - http://www.scopus.com/inward/record.url?scp=77954567761&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77954567761&partnerID=8YFLogxK

U2 - 10.1145/1772690.1772813

DO - 10.1145/1772690.1772813

M3 - Conference contribution

SN - 9781605587998

SP - 1079

EP - 1080

BT - Proceedings of the 19th International Conference on World Wide Web, WWW '10

ER -