Where is the interestingness? Retrieving appealing video scenes by learning Flickr-based graded judgments
MM 2012, 20th ACM International Conference on Multimedia, 29 October-2 November 2012, Nara, Japan
In this paper we describe a system that automatically extracts appealing scenes from a set of broadcasting videos. Unlike traditional computational aesthetic models that try to predict the hardly measurable degree of "beauty", we chose to build a system that retrieves "interesting" scenes. We create a training database of Flickr images annotated with their corresponding Flickr "interestingness" degree. We then extract existing and novel aesthetic/semantic features from the training set. Based on such features, we build a graded-relevance "interestingness" model and we rank the test shots according to their predicted "interestingness".
| Keywords: | Image aesthetics, interestingness, Semantic Indexing |
| Type: | Conference |
| Language: | English |
| City: | Nara |
| Country: | JAPAN |
| Date: | October 2012 |
| Department: | Multimedia Communications |
| Eurecom ref: | 3793 |
| Copyright: | © ACM, 2012. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in MM 2012, 20th ACM International Conference on Multimedia, 29 October-2 November 2012, Nara, Japan http://dx.doi.org/10.1145/2393347.2396486 |
| Bibtex: | @inproceedings{EURECOM+3793, doi = {http://dx.doi.org/10.1145/2393347.2396486}, year = {2012}, title = {{W}here is the interestingness? {R}etrieving appealing video scenes by learning {F}lickr-based graded judgments }, author = {{R}edi, {M}iriam and {M}{\'e}rialdo, {B}ernard}, booktitle = {{MM} 2012, 20th {ACM} {I}nternational {C}onference on {M}ultimedia, 29 {O}ctober-2 {N}ovember 2012, {N}ara, {J}apan}, address = {{N}ara, {JAPAN}}, month = {10}, url = {http://www.eurecom.fr/publication/3793} } |
| See also: |
|
Permalink: http://www.eurecom.fr/publication/3793
