Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

NII, Japan at MediaEval 2012 Violent Scenes Detection Affect Task


Published on

Published in: Technology
  • Be the first to comment

  • Be the first to like this

NII, Japan at MediaEval 2012 Violent Scenes Detection Affect Task

  1. 1. NII, Japan at MediaEval 2012Violent Scenes Detection TaskVu Lam(1), Duy-Dinh Le(2), Sang-Phan Le(2)Shin’ichi Satoh(2), Duc Anh Duong(3)(1) University of Science National Institute of Informatics {ledduy,plsang,satoh} University of Information Technology
  2. 2. Our approaches Using NII-KAORI-SECODE, a general frame-work for semantic concept detection. Using 5 keyframes per shot. Try to apply shot-based features using the global features (color moments, color histogram, edge orientation histogram, and local binary patterns) for violent scenes detection. Evaluate the performance of late fusion with visual attributes (blood, fights, gore, car chase, gore, cold arms, firearm).10/5/2012 NII, Japan at MediaEval 2012 2 Violent Scenes Detection Task
  3. 3. Shot-based features10/5/2012 NII, Japan at MediaEval 2012 3 Violent Scenes Detection Task
  4. 4. Classifier learning & Experiment Classifier learning: LibSVM10/5/2012 NII, Japan at MediaEval 2012 4 Violent Scenes Detection Task
  5. 5. NII Runs10/5/2012 NII, Japan at MediaEval 2012 5 Violent Scenes Detection Task
  6. 6. Discussion & Future work The definition of violence is so general The length of shots are very diverse, many shots are very short, and might be easily classified as non- violent shots based on the definition. Fusion of the violence detection results with other visual attributes results cannot improve the performance. Future work is to study how to use visual attributes to represent violent scenes10/5/2012 NII, Japan at MediaEval 2012 6 Violent Scenes Detection Task