Efficient misbehaving user detection in online video chat services

Hanqiang Cheng, Yu Li Liang, Xinyu Xing, Xue Liu, Richard Han, Qin Lv, Shivakant Mishra

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

Online video chat services, such as Chatroulette, Omegle, and vChatter are becoming increasingly popular and have attracted millions of users. One critical problem encoun- tered in such applications is the presence of misbehaving users (\ashers") and obscene content. Automatically filtering out obscene content from these systems in an eficient manner poses a difficult challenge. This paper presents a novel Fine-Grained Cascaded (FGC) classification solution that significantly speeds up the compute-intensive process of classifying misbehaving users by dividing image feature ex- traction into multiple stages and flltering out easily classified images in earlier stages, thus saving unnecessary computation costs of feature extraction in later stages. Our work is further enhanced by integrating new webcam-related con- textual information (illumination and color) into the classification process, and a 2-stage soft margin SVM algorithm for combining multiple features. Evaluation results using real-world data set obtained from Chatroulette show that the proposed FGC based classification solution significantly outperforms state-of-the-art techniques.

Original languageEnglish (US)
Title of host publicationWSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining
Pages23-32
Number of pages10
DOIs
StatePublished - Mar 15 2012
Event5th ACM International Conference on Web Search and Data Mining, WSDM 2012 - Seattle, WA, United States
Duration: Feb 8 2012Feb 12 2012

Other

Other5th ACM International Conference on Web Search and Data Mining, WSDM 2012
CountryUnited States
CitySeattle, WA
Period2/8/122/12/12

Fingerprint

Feature extraction
Lighting
Color
Costs

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

Cite this

Cheng, H., Liang, Y. L., Xing, X., Liu, X., Han, R., Lv, Q., & Mishra, S. (2012). Efficient misbehaving user detection in online video chat services. In WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining (pp. 23-32) https://doi.org/10.1145/2124295.2124301
Cheng, Hanqiang ; Liang, Yu Li ; Xing, Xinyu ; Liu, Xue ; Han, Richard ; Lv, Qin ; Mishra, Shivakant. / Efficient misbehaving user detection in online video chat services. WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining. 2012. pp. 23-32
@inproceedings{84c51a8451f44868bbe3e4a68c20a919,
title = "Efficient misbehaving user detection in online video chat services",
abstract = "Online video chat services, such as Chatroulette, Omegle, and vChatter are becoming increasingly popular and have attracted millions of users. One critical problem encoun- tered in such applications is the presence of misbehaving users (\ashers{"}) and obscene content. Automatically filtering out obscene content from these systems in an eficient manner poses a difficult challenge. This paper presents a novel Fine-Grained Cascaded (FGC) classification solution that significantly speeds up the compute-intensive process of classifying misbehaving users by dividing image feature ex- traction into multiple stages and flltering out easily classified images in earlier stages, thus saving unnecessary computation costs of feature extraction in later stages. Our work is further enhanced by integrating new webcam-related con- textual information (illumination and color) into the classification process, and a 2-stage soft margin SVM algorithm for combining multiple features. Evaluation results using real-world data set obtained from Chatroulette show that the proposed FGC based classification solution significantly outperforms state-of-the-art techniques.",
author = "Hanqiang Cheng and Liang, {Yu Li} and Xinyu Xing and Xue Liu and Richard Han and Qin Lv and Shivakant Mishra",
year = "2012",
month = "3",
day = "15",
doi = "10.1145/2124295.2124301",
language = "English (US)",
isbn = "9781450307475",
pages = "23--32",
booktitle = "WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining",

}

Cheng, H, Liang, YL, Xing, X, Liu, X, Han, R, Lv, Q & Mishra, S 2012, Efficient misbehaving user detection in online video chat services. in WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining. pp. 23-32, 5th ACM International Conference on Web Search and Data Mining, WSDM 2012, Seattle, WA, United States, 2/8/12. https://doi.org/10.1145/2124295.2124301

Efficient misbehaving user detection in online video chat services. / Cheng, Hanqiang; Liang, Yu Li; Xing, Xinyu; Liu, Xue; Han, Richard; Lv, Qin; Mishra, Shivakant.

WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining. 2012. p. 23-32.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Efficient misbehaving user detection in online video chat services

AU - Cheng, Hanqiang

AU - Liang, Yu Li

AU - Xing, Xinyu

AU - Liu, Xue

AU - Han, Richard

AU - Lv, Qin

AU - Mishra, Shivakant

PY - 2012/3/15

Y1 - 2012/3/15

N2 - Online video chat services, such as Chatroulette, Omegle, and vChatter are becoming increasingly popular and have attracted millions of users. One critical problem encoun- tered in such applications is the presence of misbehaving users (\ashers") and obscene content. Automatically filtering out obscene content from these systems in an eficient manner poses a difficult challenge. This paper presents a novel Fine-Grained Cascaded (FGC) classification solution that significantly speeds up the compute-intensive process of classifying misbehaving users by dividing image feature ex- traction into multiple stages and flltering out easily classified images in earlier stages, thus saving unnecessary computation costs of feature extraction in later stages. Our work is further enhanced by integrating new webcam-related con- textual information (illumination and color) into the classification process, and a 2-stage soft margin SVM algorithm for combining multiple features. Evaluation results using real-world data set obtained from Chatroulette show that the proposed FGC based classification solution significantly outperforms state-of-the-art techniques.

AB - Online video chat services, such as Chatroulette, Omegle, and vChatter are becoming increasingly popular and have attracted millions of users. One critical problem encoun- tered in such applications is the presence of misbehaving users (\ashers") and obscene content. Automatically filtering out obscene content from these systems in an eficient manner poses a difficult challenge. This paper presents a novel Fine-Grained Cascaded (FGC) classification solution that significantly speeds up the compute-intensive process of classifying misbehaving users by dividing image feature ex- traction into multiple stages and flltering out easily classified images in earlier stages, thus saving unnecessary computation costs of feature extraction in later stages. Our work is further enhanced by integrating new webcam-related con- textual information (illumination and color) into the classification process, and a 2-stage soft margin SVM algorithm for combining multiple features. Evaluation results using real-world data set obtained from Chatroulette show that the proposed FGC based classification solution significantly outperforms state-of-the-art techniques.

UR - http://www.scopus.com/inward/record.url?scp=84863283882&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863283882&partnerID=8YFLogxK

U2 - 10.1145/2124295.2124301

DO - 10.1145/2124295.2124301

M3 - Conference contribution

SN - 9781450307475

SP - 23

EP - 32

BT - WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining

ER -

Cheng H, Liang YL, Xing X, Liu X, Han R, Lv Q et al. Efficient misbehaving user detection in online video chat services. In WSDM 2012 - Proceedings of the 5th ACM International Conference on Web Search and Data Mining. 2012. p. 23-32 https://doi.org/10.1145/2124295.2124301