The purpose of this paper is to describe the work carried out for the Violent Scenes Detection task at MediaEval 2013 by team TUDCL. Our work is based on the combination of visual, temporal and audio features with machine learning at segment-level. Block-saliency-map based dense trajectory is proposed for visual and temporal features, and MFCC and delta-MFCC is used for audio features. For the classification, Multiple Kernel Learning is applied, which is effective if multi-modal features exist.
|Journal||CEUR Workshop Proceedings|
|Publication status||Published - 2013 Jan 1|
|Event||2013 Multimedia Benchmark Workshop, MediaEval 2013 - Barcelona, Spain|
Duration: 2013 Oct 18 → 2013 Oct 19
ASJC Scopus subject areas
- Computer Science(all)