TUDCL at MediaEval 2013 Violent Scenes Detection: Training with Multi-modal Features by MKL.

Shinichi Goto Terumasa Aoki

Published in: MediaEval (2013)

Keyphrases

multi modal
audio visual
low level
feature space
multi modality
training examples
high dimensional
training set
image features
object detection
multiple kernel learning
video search
multiple modalities
feature vectors
image annotation
cross modal
feature extraction
audio features
uni modal