Sorry, you need to enable JavaScript to visit this website.

Bimodal Codebooks Based Adult Video Detection

Citation Author(s):
Submitted by:
Yizhi Liu
Last updated:
12 November 2017 - 4:59am
Document Type:
Presentation Slides
Document Year:
2017
Event:
Paper Code:
1158
 

Multi-modality based adult video detection is an effective approach of filtering pornography. However, existing methods lack accurate representation methods of multi-modality semantics. Addressing at the issue, we propose a novel method of bimodal codebooks based adult video detection. Firstly, the audio codebook is created by periodicity analysis from the labeled audio segments. Secondly, the visual codebook is generated by detecting regions-of-interest (ROI) on the basis of saliency analysis. Furthermore, we combine the two codebooks to represent the co-occurrence semantics of bimodal signals. The results show that our approach outperforms some state-of-the-art methods.

up
0 users have voted: