Proceedings chapter
OA Policy
English

Identification of Narrative Peaks in Video Clips: Text Features Perform Best

Presented at

Corfu (Greece), September 30 - October 2, 2009

Publisher

Springer

Collection

  • Lecture Notes in Computer Science; 6242

Publication date

2010

Abstract

A methodology is proposed to identify narrative peaks in video clips. Three basic clip properties are evaluated which reflect on video, audio and text related features in the clip. Furthermore, the expected distribution of narrative peaks throughout the clip is determined and exploited for future predictions. Results show that only the text related feature, related to the usage of distinct words throughout the clip, and the expected peak-distribution are of use when finding the peaks. On the training set, our best detector had an accuracy of 47% in finding narrative peaks. On the test set, this accuracy dropped to 24%.

Keywords

  • Petamedia
  • Language Translation and Linguistics
  • Information Systems Applications (incl.Internet)
  • Information Storage and Retrieval
  • Database Management
  • Data Mining and Knowledge Discovery
  • Pattern Recognition

Citation (ISO format)

KIERKELS, Joep Johannes Maria, SOLEYMANI, Mohammad, PUN, Thierry. Identification of Narrative Peaks in Video Clips: Text Features Perform Best. In: Multilingual Information Access Evaluation II Multimedia Experiments : 10th Workshop of the Cross-Language Evaluation Forum, CLEF 2009. Corfu (Greece). [s.l.] : Springer, 2010. p. 393–400. (Lecture Notes in Computer Science) doi: 10.1007/978-3-642-15751-6_51

Main files (1)

Proceedings chapter (Published version)

Identifiers

710views
661downloads

Technical informations

Creation

06/03/2015 17:12:05

First validation

06/03/2015 17:12:05

Update

14/03/2023 22:58:22

Status update

14/03/2023 22:58:22

Last indexation

30/10/2024 23:16:44
All rights reserved by Archive ouverte UNIGE and the University of Geneva
OpenAIRE Indexed & Validated