VideoModerator: A Risk-aware Framework for Multimodal Video Moderation in E-Commerce

被引:13
|
作者
Tang, Tan [1 ,2 ]
Wu, Yanhong [1 ,2 ]
Yu, Lingyun [3 ]
Li, Yuhong [4 ]
Wu, Yingcai [1 ,2 ]
机构
[1] Zhejiang Univ, State Key Lab CAD&CG, Hangzhou, Peoples R China
[2] Zhejiang Lab, Hangzhou, Peoples R China
[3] Xian Jiaotong Liverpool Univ, Dept Comp, Xian, Peoples R China
[4] Alibaba Grp, Hangzhou, Peoples R China
关键词
Visualization; Task analysis; Visual analytics; Machine learning; Motion pictures; Feature extraction; Data mining; video moderation; video visualization; e-commerce livestreaming; VIOLENCE DETECTION; VISUAL ANALYTICS; VISUALIZATION; NETWORKS;
D O I
10.1109/TVCG.2021.3114781
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Video moderation, which refers to remove deviant or explicit content from e-commerce livestreams, has become prevalent owing to social and engaging features. However, this task is tedious and time consuming due to the difficulties associated with watching and reviewing multimodal video content, including video frames and audio clips. To ensure effective video moderation, we propose VideoModerator, a risk-aware framework that seamlessly integrates human knowledge with machine insights. This framework incorporates a set of advanced machine learning models to extract the risk-aware features from multimodal video content and discover potentially deviant videos. Moreover, this framework introduces an interactive visualization interface with three views, namely, a video view, a frame view, and an audio view. In the video view, we adopt a segmented timeline and highlight high-risk periods that may contain deviant information. In the frame view, we present a novel visual summarization method that combines risk-aware features and video context to enable quick video navigation. In the audio view, we employ a storyline-based design to provide a multi-faceted overview which can be used to explore audio content. Furthermore, we report the usage of VideoModerator through a case scenario and conduct experiments and a controlled user study to validate its effectiveness.
引用
收藏
页码:846 / 856
页数:11
相关论文
共 50 条
  • [31] LARAVEL: A PHP Framework for E-Commerce Website
    Yadav, Neha
    Rajpoot, Dharmveer Singh
    Dhakad, Shri Krishna
    2019 FIFTH INTERNATIONAL CONFERENCE ON IMAGE INFORMATION PROCESSING (ICIIP 2019), 2019, : 503 - 508
  • [32] A Framework for Quality Management of E-commerce Websites
    Kotian, Harshita
    Meshram, B. B.
    2017 INTERNATIONAL CONFERENCE ON NASCENT TECHNOLOGIES IN ENGINEERING (ICNTE-2017), 2017,
  • [33] A framework for E-commerce oriented recommendation systems
    Weng, L.-T. (l.weng@student.qut.edu.au), IEEE Systems, Man, and Cybernetics Society; Information Processing Society of Japan; Kagawa University (Institute of Electrical and Electronics Engineers Computer Society):
  • [34] IOT data Fusion framework for e-commerce
    Mahesh Kulkarni P.
    Nautiyal B.
    Kumar S.
    Medidha R.
    Rameshbhai Savaliya R.
    Eknath M.
    Measurement: Sensors, 2022, 24
  • [35] IBM launches secure E-commerce framework
    不详
    COMPUTER, 1997, 30 (03) : 19 - 20
  • [36] Customer Knowledge Management Framework in E-commerce
    Hashemi, Novin
    Hajiheydari, Nastaran
    E-BUSINESS, MANAGEMENT AND ECONOMICS (ICEME 2011), 2011, 25 : 129 - 133
  • [37] Towards a framework for operations management in e-commerce
    da Silveira, GJC
    INTERNATIONAL JOURNAL OF OPERATIONS & PRODUCTION MANAGEMENT, 2003, 23 (02) : 200 - 212
  • [38] The effectiveness of the balanced scorecard framework for e-commerce
    Mistry, JJ
    Pathak, BK
    MULTI-OBJECTIVE PROGRAMMING AND GOAL PROGRAMMING, 2003, : 375 - 381
  • [39] The framework for supporting knowledge collaboration in e-commerce
    Li, Dan
    Tang, Bingyong
    Proceedings of the 2005 Conference of System Dynamics and Management Science, Vol 1: SUSTAINABLE DEVELOPMENT OF ASIA PACIFIC, 2005, : 426 - 430
  • [40] Auto Content Moderation in C2C e-Commerce
    Ueta, Shunya
    Nagarajan, Suganprabu
    Sango, Mizuki
    PROCEEDINGS OF THE 2020 USENIX CONFERENCE ON OPERATIONAL MACHINE LEARNING (OPML '20), 2020, : 33 - 35