The analysis of the leading social video sharing platform YouTube reveals a high amount of redundancy, in the form of videos with overlapping or duplicated content. In this paper, we show that this redundancy can provide useful information about connections between videos. We reveal these links using robust content-based video analysis techniques and exploit them for generating new tag assignments. To this end, we propose different tag propagation methods for automatically obtaining richer video annotations. Our techniques provide the user with additional information about videos, and lead to enhanced feature representations for applications such as automatic data organization and search. Experiments on video clustering and classification as well as a user evaluation demonstrate the viability of our approach.
%0 Conference Paper
%1 siersdorfer2009automatic
%A Siersdorfer, Stefan
%A San Pedro, Jose
%A Sanderson, Mark
%B Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval
%C New York, NY, USA
%D 2009
%I ACM
%K autotagging video
%P 395--402
%R 10.1145/1571941.1572010
%T Automatic video tagging using content redundancy
%U http://doi.acm.org/10.1145/1571941.1572010
%X The analysis of the leading social video sharing platform YouTube reveals a high amount of redundancy, in the form of videos with overlapping or duplicated content. In this paper, we show that this redundancy can provide useful information about connections between videos. We reveal these links using robust content-based video analysis techniques and exploit them for generating new tag assignments. To this end, we propose different tag propagation methods for automatically obtaining richer video annotations. Our techniques provide the user with additional information about videos, and lead to enhanced feature representations for applications such as automatic data organization and search. Experiments on video clustering and classification as well as a user evaluation demonstrate the viability of our approach.
%@ 978-1-60558-483-6
@inproceedings{siersdorfer2009automatic,
abstract = {The analysis of the leading social video sharing platform YouTube reveals a high amount of redundancy, in the form of videos with overlapping or duplicated content. In this paper, we show that this redundancy can provide useful information about connections between videos. We reveal these links using robust content-based video analysis techniques and exploit them for generating new tag assignments. To this end, we propose different tag propagation methods for automatically obtaining richer video annotations. Our techniques provide the user with additional information about videos, and lead to enhanced feature representations for applications such as automatic data organization and search. Experiments on video clustering and classification as well as a user evaluation demonstrate the viability of our approach.},
acmid = {1572010},
added-at = {2011-12-15T11:20:37.000+0100},
address = {New York, NY, USA},
author = {Siersdorfer, Stefan and San Pedro, Jose and Sanderson, Mark},
biburl = {https://www.bibsonomy.org/bibtex/271c3a120e154ed135408292eb4b96278/dbenz},
booktitle = {Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval},
description = {Automatic video tagging using content redundancy},
doi = {10.1145/1571941.1572010},
interhash = {276b49e417d441ba50bfc6e4b85be1f3},
intrahash = {71c3a120e154ed135408292eb4b96278},
isbn = {978-1-60558-483-6},
keywords = {autotagging video},
location = {Boston, MA, USA},
numpages = {8},
pages = {395--402},
publisher = {ACM},
series = {SIGIR '09},
timestamp = {2013-07-31T15:39:42.000+0200},
title = {Automatic video tagging using content redundancy},
url = {http://doi.acm.org/10.1145/1571941.1572010},
year = 2009
}