Violence Detection in Videos Based on Fusing Visual and Audio Information.

Wen-Feng Pang Qian-Hua He Yongjian Hu Yan-Xiong Li

Published in: ICASSP (2021)

Keyphrases

visual data
information sources
information processing
visual information
visual cues
false positives
spatial information
multimedia
keywords
information extraction
object detection
contextual information
video database
cross modal