Supervised video summarization by content-based video segment selection

V. Mygdalis, A. Iosifidis, A. Tefas, I. Pitas

Research output: Contribution to conferenceConference Paperpeer-review

21 Downloads (Pure)

Abstract

In this paper, we formulate the video summarization problem as the one of automatic video segment selection based on one-class classification. We introduce a novel variant of the One-Class Support Vector Machine classifier that exploits subclass information in its optimization problem, in order to jointly minimize the data dispersion within each subclass and determine the optimal decision function. We evaluate the proposed approach in Hollywood movies, where the performance of the proposed SOC-SVM algorithm is compared with that of the OC-SVM.
Original languageEnglish
Number of pages1
Publication statusPublished - 13 Nov 2014
EventEuropean Conference on Visual Media Production (CVMP) - London, United Kingdom
Duration: 13 Nov 201414 Nov 2014

Conference

ConferenceEuropean Conference on Visual Media Production (CVMP)
CountryUnited Kingdom
CityLondon
Period13/11/1414/11/14

Keywords

  • One class classification
  • Subclass One-Class SVM
  • Supervised Video Summarization

Fingerprint Dive into the research topics of 'Supervised video summarization by content-based video segment selection'. Together they form a unique fingerprint.

Cite this