Using web sources for improving video categorization

From WikiLit
Jump to: navigation, search
Publication (help)
Using web sources for improving video categorization
Authors: José M. Perea-Ortega, Arturo Montejo-Ráez, M. Teresa Martín-Valdivia, L. Alfonso Ureña-López [edit item]
Citation: Journal of Intelligent Information Systems  : . 2010.
Publication type: Journal article
Peer-reviewed: Yes
Database(s):
DOI: 10.1007/s10844-010-0123-6.
Google Scholar cites: Citations
Link(s): Paper link
Added by Wikilit team: Added on initial load
Search
Article: Google Scholar BASE PubMed
Other scholarly wikis: AcaWiki Brede Wiki WikiPapers
Web search: Bing Google Yahoo!Google PDF
Other:
Services
Format: BibTeX
Using web sources for improving video categorization is a publication by José M. Perea-Ortega, Arturo Montejo-Ráez, M. Teresa Martín-Valdivia, L. Alfonso Ureña-López.


[edit] Abstract

In this paper, several experiments about video categorization using a supervised learning approach are presented. To this end, the VideoCLEF 2008 evaluation forum has been chosen as experimental framework. After an analysis of the VideoCLEF corpus, it was found that video transcriptions are not the best source of information in order to identify the thematic of video streams. Therefore, two web-based corpora have been generated in the aim of adding more informational sources by integrating documents from Wikipedia articles and Google searches. A number of supervised categorization experiments using the test data of VideoCLEF have been accomplished. Several machine learning algorithms have been proved to validate the effect of the corpus on the final results: Naive Bayes, K-nearest-neighbors (KNN), Support Vectors Machine (SVM) and the j48 decision tree. The results obtained show that web can be a useful source of information for generating classification models for video data.

[edit] Research questions

"In this paper, several experiments about video categorization using a supervised learning approach are presented."

Research details

Topics: Multimedia information retrieval [edit item]
Domains: Computer science [edit item]
Theory type: Design and action [edit item]
Wikipedia coverage: Other [edit item]
Theories: "Undetermined" [edit item]
Research design: Statistical analysis [edit item]
Data source: Wikipedia pages [edit item]
Collected data time dimension: Cross-sectional [edit item]
Unit of analysis: Article [edit item]
Wikipedia data extraction: Dump [edit item]
Wikipedia page type: Article [edit item]
Wikipedia language: English [edit item]

[edit] Conclusion

"Our main conclusion is that it is possible to use the information from web sources in order to improve the results for the video categorization system. Firstly, the experiments with Google and/or Wikipedia overcome the baseline using the VideoCLEF corpus in all cases. On the other hand, the corpus with Google works better than the Wikipedia one. However, it is very interesting that the combined use of Google and Wikipedia obtains the best results for all the machine learning algorithms. Based on these results, we conclude that the informal content found on the web, probably helps to enrich the learning corpora used to train video categorization systems."

[edit] Comments

"web can be a useful source of information for generating classification models for video data"


Further notes[edit]

Facts about "Using web sources for improving video categorization"RDF feed
AbstractIn this paper, several experiments about vIn this paper, several experiments about video categorization using a supervised learning approach are presented. To this end, the VideoCLEF 2008 evaluation forum has been chosen as experimental framework. After an analysis of the VideoCLEF corpus, it was found that video transcriptions are not the best source of information in order to identify the thematic of video streams. Therefore, two web-based corpora have been generated in the aim of adding more informational sources by integrating documents from Wikipedia articles and Google searches. A number of supervised categorization experiments using the test data of VideoCLEF have been accomplished. Several machine learning algorithms have been proved to validate the effect of the corpus on the final results: Naive Bayes, K-nearest-neighbors (KNN), Support Vectors Machine (SVM) and the j48 decision tree. The results obtained show that web can be a useful source of information for generating classification models for video data.ting classification models for video data.
Added by wikilit teamAdded on initial load +
Collected data time dimensionCross-sectional +
Commentsweb can be a useful source of information for generating classification models for video data
ConclusionOur main conclusion is that it is possibleOur main conclusion is that it is possible to use the information from web sources in order to improve the results for the video categorization system. Firstly, the experiments with Google and/or Wikipedia overcome the baseline using the VideoCLEF corpus in all cases. On the other hand, the corpus with Google works better than the Wikipedia one. However, it is very interesting that the combined use of Google and Wikipedia obtains the best results for all the machine learning algorithms. Based on these results, we conclude that the informal content found on the web, probably helps to enrich the learning corpora used to train video categorization systems.sed to train video categorization systems.
Data sourceWikipedia pages +
Doi10.1007/s10844-010-0123-6 +
Google scholar urlhttp://scholar.google.com/scholar?ie=UTF-8&q=%22Using%2Bweb%2Bsources%2Bfor%2Bimproving%2Bvideo%2Bcategorization%22 +
Has authorJosé M. Perea-Ortega +, Arturo Montejo-Ráez +, M. Teresa Martín-Valdivia + and L. Alfonso Ureña-López +
Has domainComputer science +
Has topicMultimedia information retrieval +
Peer reviewedYes +
Publication typeJournal article +
Published inJournal of Intelligent Information Systems +
Research designStatistical analysis +
Research questionsIn this paper, several experiments about video categorization using a supervised learning approach are presented.
Revid11,026 +
TheoriesUndetermined
Theory typeDesign and action +
TitleUsing web sources for improving video categorization
Unit of analysisArticle +
Urlhttp://dx.doi.org/10.1007/s10844-010-0123-6 +
Wikipedia coverageOther +
Wikipedia data extractionDump +
Wikipedia languageEnglish +
Wikipedia page typeArticle +
Year2010 +