• DocumentCode
    172960
  • Title

    Benchmarking Violent Scenes Detection in movies

  • Author

    Demarty, Claire-Helene ; Ionescu, Bogdan ; Yu-Gang Jiang ; Vu Lam Quang ; Schedl, Markus ; Penet, Cedric

  • Author_Institution
    Technicolor, Cesson-Sevigne, France
  • fYear
    2014
  • fDate
    18-20 June 2014
  • Firstpage
    1
  • Lastpage
    6
  • Abstract
    This paper addresses the issue of detecting violent scenes in Hollywood movies. In this context, we describe the MediaEval 2013 Violent Scene Detection task which proposes a consistent evaluation framework to the research community. 9 participating teams proposed systems for evaluation in 2013, which denotes an increasing interest for the task. In this paper, the 2013 dataset, the annotations process and the task´s rules are detailed. The submitted systems are thoroughfully analysed and compared through several metrics to draw conclusions on the most promising techniques among which multimodal systems and mid-level concept detection. Some further late fusions of the systems are investigated and show promising performances.
  • Keywords
    entertainment; object detection; video signal processing; Hollywood movies; MediaEval 2013 Violent Scene Detection task; mid-level concept detection; multimodal systems; violent movie scene detection benchmarking; Benchmark testing; Context; Electronic mail; Histograms; Measurement; Motion pictures; Visualization;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Content-Based Multimedia Indexing (CBMI), 2014 12th International Workshop on
  • Conference_Location
    Klagenfurt
  • Type

    conf

  • DOI
    10.1109/CBMI.2014.6849827
  • Filename
    6849827