Diversity ranking for video retrieval from a broadcaster archive

Cita com:
hdl:2117/12810
Document typeConference lecture
Defense date2011
Rights accessOpen Access
Except where otherwise noted, content on this work
is licensed under a Creative Commons license
:
Attribution-NonCommercial-NoDerivs 3.0 Spain
Abstract
Video retrieval through text queries is a very common practice
in broadcaster archives. The query keywords are compared
to the metadata labels that documentalists have previously
associated to the video assets. This paper focuses on
a ranking strategy to obtain more relevant keyframes among
the top hits of the results ranked lists but, at the same time,
keeping a diversity of video assets. Previous solutions based
on a random walk over a visual similarity graph have been
modi ed to increase the asset diversity by ltering the edges
between keyframes depending on their asset. The random
walk algorithm is applied separately for ever visual feature
to avoid any normalization issue between visual similarity
metrics. Finally, this work evaluates performance with two
separate metrics: the relevance is measured by the Average
Precision and the diversity is assessed by the Average
Diversity, a new metric presented in this work.
CitationGiró Nieto, X.; Alfaro Vendrell, M.; Marqués Acosta, F. Diversity ranking for video retrieval from a broadcaster archive. A: ACM International Conference on Multimedia Retrieval. "Proceedings of the 1st ACM International Conference on Multimedia Retrieval (ICMR '11)". 2011, p. 1-8. ISBN 978-1-4503-0336-1. DOI 10.1145/1991996.1992052.
ISBN978-1-4503-0336-1
Publisher versionhttp://dx.doi.org/10.1145/1991996.1992052
Files | Description | Size | Format | View |
---|---|---|---|---|
GiroAlfaroMarques.pdf | Initial submission (no review) | 3,420Mb | View/Open | |
2011-giro-icmr.pdf | Poster | 1000,Kb | View/Open |