TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Video summarization based on Subclass Support Vector Data Description

Tutkimustuotosvertaisarvioitu

Yksityiskohdat

AlkuperäiskieliEnglanti
OtsikkoIEEE SSCI 2014 - 2014 IEEE Symposium Series on Computational Intelligence - CIES 2014: 2014 IEEE Symposium on Computational Intelligence for Engineering Solutions, Proceedings
KustantajaThe Institute of Electrical and Electronics Engineers, Inc.
Sivut183-187
Sivumäärä5
ISBN (painettu)9781479945108
DOI - pysyväislinkit
TilaJulkaistu - 15 tammikuuta 2015
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
Tapahtuma2014 IEEE Symposium on Computational Intelligence for Engineering Solutions, CIES 2014 - Orlando, Yhdysvallat
Kesto: 9 joulukuuta 201412 joulukuuta 2014

Conference

Conference2014 IEEE Symposium on Computational Intelligence for Engineering Solutions, CIES 2014
MaaYhdysvallat
KaupunkiOrlando
Ajanjakso9/12/1412/12/14

Tiivistelmä

In this paper, we describe a method for video summarization that operates on a video segment level. We formulate this problem as the one of automatic video segment selection based on a learning process that employs salient video segment paradigms. We design an hierarchical learning scheme that consists of two steps. At the first step, an unsupervised process is performed in order to determine salient video segment types. The second step is a supervised learning process that is performed for each of the salient video segment type independently. For the latter case, since only salient training examples are available, the problem is stated as an one-class classification problem. In order to take into account subclass information that may appear in the video segment types, we introduce a novel formulation of the Support Vector Data Description method that exploits subclass information in its optimization process. We evaluate the proposed approach in three Hollywood movies, where the performance of the proposed Subclass SVDD (SSVDD) algorithm is compared with that of related methods. Experimental results show that the adoption of both hierarchical learning and the proposed SSVDD method contribute to the final classification performance.