This paper presents a novel approach for web video categorization by leveraging Wikipedia categories (WikiCs) and open resources describing the same content as the video, i.e., content-duplicated open resources (CDORs). Note that current approaches only collect CDORs within one or a few media forms and ignore CDORs of other forms. We explore all these resources by utilizing WikiCs and commercial search engines. Given a web video, its discriminative Wikipedia concepts are first identified and classified. Then a textual query is constructed and from which CDORs are collected. Based on these CDORs, we propose to categorize web videos in the space spanned by WikiCs rather than that spanned by raw tags. Experimental results demonstrate the effectiveness of both the proposed CDOR collection method and the WikiC voting categorization algorithm. In addition, the categorization model built based on both WikiCs and CDORs achieves better performance compared with the models built based on only one of them as well as state-of-the-art approach.
[1]
Chong-Wah Ngo,et al.
Columbia University/VIREO-CityU/IRIT TRECVID2008 High-Level Feature Extraction and Interactive Video Search
,
2008,
TRECVID.
[2]
Chong-Wah Ngo,et al.
Towards google challenge: combining contextual and social information for web video categorization
,
2009,
ACM Multimedia.
[3]
Roelof van Zwol,et al.
Classifying tags using open content resources
,
2009,
WSDM '09.
[4]
Chong-Wah Ngo,et al.
On the Annotation of Web Videos by Efficient Near-Duplicate Search
,
2010,
IEEE Transactions on Multimedia.
[5]
Mark Sanderson,et al.
Automatic video tagging using content redundancy
,
2009,
SIGIR.
[6]
Hiroshi Murase,et al.
Labeling News Topic Threads with Wikipedia Entries
,
2009,
2009 11th IEEE International Symposium on Multimedia.
[7]
Andrew Zisserman,et al.
Oxford TRECVid 2007 - Notebook paper
,
2007
.
[8]
Yongdong Zhang,et al.
Context-oriented web video tag recommendation
,
2010,
WWW '10.
[9]
Gang Wang,et al.
Understanding user's query intent with wikipedia
,
2009,
WWW '09.