Weakly-Supervised Violence Detection in Movies with Audio and Video Based Co-training

被引：0

作者：

Lin, Jian ^{[1
]}

Wang, Weiqiang ^{[1
]}

机构：

[1] Chinese Acad Sci, Grad Univ, Beijing, Peoples R China

来源：

ADVANCES IN MULTIMEDIA INFORMATION PROCESSING - PCM 2009 | 2009年 / 5879卷

关键词：

Violence; Weakly-supervised; pLSA; Audio; Video; Co-training;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this work, we present a novel method to detect violent shots in movies The detection process is split into two views the audio and video views From the audio-view. a weakly-supervised method is exploited to improve the Classification performance And from the video-view, WC use a classifier to detect violent shots Finally, the auditory and visual classifiers are combined in a co-training way The experimental results on several movies with violent contents preliminarily show the effectiveness of our method

引用

页码：930 / 935

页数：6

共 12 条

[1]

AKITA Y, 2004, 8 INT C SPOK LANG PR, P1045

[2]

Cai L., 2003, P 26 ANN INT ACM SIG, P182

[3] A flexible framework for key audio effects detection and auditory context inference [J].

Cai, R ;

Lu, L ;

Hanjalic, A ;

Zhang, HJ ;

Cai, LH .

IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2006, 14 (03) :1026-1039

[4]

Cheng Wen-Huang, 2003, P 5 ACM SIGMM INT WO, P109, DOI DOI 10.1145/973264.973282

[5]

Datta A, 2002, INT C PATT RECOG, P433, DOI 10.1109/ICPR.2002.1044748

[6]

Nam J, 1998, 1998 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING - PROCEEDINGS, VOL 1, P353, DOI 10.1109/ICIP.1998.723496

[7]

Ng Vincent., 2003, Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, P94, DOI DOI 10.3115/1073445.1073468

[8]

SARKAR A, 2001, P 2 ANN M NAACL

[9]

SWANSON MD, 1997, IEEE INT C IM PROC, V2, P676

[10]

Vasconcelos N, 1997, INTERNATIONAL CONFERENCE ON IMAGE PROCESSING - PROCEEDINGS, VOL I, P25, DOI 10.1109/ICIP.1997.647375

← 1 2 →