1. School of Information Management, Nanjing University, Nanjing 210093, China;
2. School of Economics and Management, Nanjing University of Science and Technology, Nanjing 210094, China;
3. Department of Information Management, Peking University, Beijing 100871, China
Abstract：This article introduces a classification experiment which is based on UNC's Open Video project. In this experiment, the authors focus on the respective effects of different types of key frame collection, and compare the contribution of various features and their combination in details. Furthermore,the result shows that combination of visual and text features can achieve the best mining accuracy, and keywords and descriptions have different influence on the mining effect.
陈芬, 赖茂生. 多特征视频分类挖掘实验研究[J]. 现代图书情报技术, 2012, 28(5): 76-80.
Chen Fen, Lai Maosheng. Video Classification Using Multiple Features. New Technology of Library and Information Service, 2012, 28(5): 76-80.
[1] Fischer S, Lienhart R, Effelsberg W. Automatic Recognition of Film Genres[C]. In:Proceedings of the 3rd ACM International Conference on Multimedia,San Francisco, CA, USA.1995:295-304.[2] Chang S F, Ellis D, Jiang W,et al. Large-Scale Multimodal Semantic Concept Detection for Consumer Video[C]. In: Proceedings of the International Workshop on Workshop on Multimedia Information Retrieval,Augsburg, Bavaria, Germany.2007:255-264.[3] Chen S C, Shyu M L, Chen M, et al. A Decision Tree-based Multimodal Data Mining Framework for Soccer Goal[C]. In: Proceedings of the IEEE International Conference on Multimedia and Expo. 2004:265-268.[4] Pan J Y, Faloutsos C.VideoCube: A Novel Tool for Video Mining and Classification[C]. In:Proceedings of the 5th International Conference on Asian Digital Libraries (ICADL 2002). 2002:194-205.[5] Yang L J, Liu J M, Yang X K,et al. Multi-Modality Web Video Categorization[C]. In:Proceedings of the International Workshop on Multimedia Information Retrieval(MIR'07),Augsburg, Bavaria, Germany.2007:265-274.[6] Rasheed Z, Sheikh Y, Shah M. On the Use of Computable Features for Film Classification[J]. IEEE Transactions on Circuits and System for Video Technology, 2005,15(1): 52-64.[7] Yuan X, Lai W, Mei T,et al. Automatic Video Genre Categorization Using Hierarchical SVM[C].In: Proceedings of 2006 IEEE International Conference on Image Processing,Atlanta, USA.2006:2905-2908.[8] Open Video Digital Library Project[OL].[2012-02-10]. http://www.open-video.org/index.php.[9] MERIT[OL]. [2012-02-10]. http://lamp.cfar.umd.edu/media/research/MERIT/.[10] Wikipedia.Cohen's Kappa Coefficient[EB/OL].[2012-02-10]. http://en.wikipedia.org/wiki/Cohen%27s_kappa.[11] Text Transformation and Classification Accuracy[OL]. [2012-02-10]. http://www.ils.unc.edu/~cablake/ inls890_f06/.[12] The Banana Tree.Stop Word List[EB/OL].[2012-02-10]. http://www.thebananatree.org/stoplist.html.
