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

facebooktwittermailshare

Bimodal Codebooks Based Adult Video Detection

Abstract: 

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:

Paper Details

Authors:
Submitted On:
12 November 2017 - 4:59am
Short Link:
Type:
Presentation Slides
Event:
Paper Code:
1158
Document Year:
2017
Cite

Document Files

GlobalSIP 2017 1158 - Bimodal Codebooks Based Adult Video Detection.pdf

(17 downloads)

Keywords

Additional Categories

Subscribe

[1] , "Bimodal Codebooks Based Adult Video Detection", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2310. Accessed: Jan. 22, 2018.
@article{2310-17,
url = {http://sigport.org/2310},
author = { },
publisher = {IEEE SigPort},
title = {Bimodal Codebooks Based Adult Video Detection},
year = {2017} }
TY - EJOUR
T1 - Bimodal Codebooks Based Adult Video Detection
AU -
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2310
ER -
. (2017). Bimodal Codebooks Based Adult Video Detection. IEEE SigPort. http://sigport.org/2310
, 2017. Bimodal Codebooks Based Adult Video Detection. Available at: http://sigport.org/2310.
. (2017). "Bimodal Codebooks Based Adult Video Detection." Web.
1. . Bimodal Codebooks Based Adult Video Detection [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2310