一种基于反馈模糊图论的视频多语义标注算法

计算机科学 ›› 2013, Vol. 40 ›› Issue (12): 270-275.

一种基于反馈模糊图论的视频多语义标注算法

朱宇光,闫婷,张建明,杨雄,胡维礼

南京理工大学自动化学院南京210094;江苏大学计算机科学与通信工程学院镇江212013;江苏大学计算机科学与通信工程学院镇江212013;常州工学院计算机信息工程学院常州213002;南京理工大学自动化学院南京210094

出版日期:2018-11-16 发布日期:2018-11-16
基金资助:
本文受江苏省高校自然科学研究面上项目(11KJD520002),常州市科技计划项目(CC20120030)资助

Video Multi-semantic Annotation Algorithm Based on Feedback Fuzzy Graph Theory

ZHU Yu-guang,YAN Ting,ZHANG Jian-ming,YANG Xiong and HU Wei-li

Online:2018-11-16 Published:2018-11-16

摘要/Abstract

摘要： 为了弥补视频语义检索中视频底层特征与高层语义概念之间的“语义鸿沟”,提出了一种基于反馈模糊图论的视频多语义标注算法。该算法首先构造一个包括所有数据的时间和空间分布信息的小样本集,据此进行人工标注并将其作为训练集。然后将模糊算子引入图论中,将语义概念间的关系模糊化,以实现模糊推理。最后将标注完成的测试集中的样本加入到训练集中,以完成视频标注的反馈。实验结果表明,使用反馈的模糊图不仅可以很好地建立语义概念间的关系,还能提高视频标注的准确率,表现出良好的性能。

关键词: 视频标注,模糊图,多语义标注,语义鸿沟

Abstract: For bridging semantic gap between video low-level features and high-level semantic concepts in the semantic-based video retrieval system,the video multi-semantic annotation algorithm based on feedback fuzzy graph theory was proposed．First,a training set which includes most temporal and spatial distribution of the whole data is made up and it will achieve a satisfying performance even in the case of limited size of training set．Secondly,the fuzzy operators are applied to graph theory to achieve fuzzy reasoning by using fuzzy semantic．Last,in order to finish the feedback of video annotation,some temples from the testing set that have finished annotation are selected and added into the training set．Experimental results indicate that feedback fuzzy graph not only sets up the relationship between semantic concepts well,but also improves the precision of annotation and shows good performance.

Key words: Video annotation,Fuzzy graph,Multi-semantic annotation,Semantic gap

朱宇光,闫婷,张建明,杨雄,胡维礼. 一种基于反馈模糊图论的视频多语义标注算法[J]. 计算机科学, 2013, 40(12): 270-275. https://doi.org/

ZHU Yu-guang,YAN Ting,ZHANG Jian-ming,YANG Xiong and HU Wei-li. Video Multi-semantic Annotation Algorithm Based on Feedback Fuzzy Graph Theory[J]. Computer Science, 2013, 40(12): 270-275. https://doi.org/

参考文献

[1] Alexander G,Hauptmann．Lessons for the future from a decade of informedia video analysis research[J]．Image and Video Retrieval Lecture Notes in Computer Science,2005,8:1-10
[2] 黄树成,朱宇光,董逸生．基于半监督学习的数据流分类方法[J].计算机研究与发展,2007,44(z2):225-229
[3] Wang Meng,Hua Xian-sheng,Song Yan,et al．Automatic video annotation by semi-supervised learning with kernel density estimation[C]∥MULTIMEDIA’''06Proceedings of the 14th annual ACM international conference on Multimedia．2006:967-976
[4] Liu Jing,Li Ming-jing,Ma Wei-ying,et al．An adaptive graph model for automatic image annotation[C]∥MIR’06Procee-dings of the 8th ACM International Workshop on Multimedia Information Retrieval．2006:61-70
[5] Yeung M M,Yeo B L．Time-constrained and Clustering for segmentation of video into story units[C]∥Proceedings of the 13th International Conference on Pattern Recognition．Vienna,1996,3:375-380
[6] Tang Jin-hui,Hua Xian-sheng,Wang Meng,et al.CorrelativeLinear Neighborhood Propagation for video annotation[J]．IEEE transactions on systems,man,and cybernetics-part B:cybernetics,2009,39(2):409-416
[7] Wang Fei,Zhang Chang-shui.Label propagation through linear neighborhoods[J]．IEEE Transactions on Knowledge and Data Engineering,2008,20(1):55-67
[8] Saul L K,Roweis S T．Think globally,fit locally:unsupervised learning of low demnsional manifolds[J]．The Journal of Machine Learning Research,2003,4:119-155
[9] Zha Zheng-jun,Mei Tao,Wang Jing-dong,et al．Graph-basedsemi-supervised learning with multi-label[J]．Journal of Visual Communication and Image Representation,2009,20(2):97-103
[10] Jain R,Hong Ri-chang,Yan Shui-cheng,et al.Image Annotation By kNN-Sparse Graph-based Label Propagation Over Noisily-Tagged Web Images[J]．ACM Transactions on Intelligent Systems and Technology,2011,2(2):111-115
[11] Angelova R,Weikum G,et al．Graph-based Text Classification:Learn from your Neighbors [C]∥SIGIR’06Proceedings of the 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval．Seattle,2006:485-492
[12] Liu Qing-shan,Huang Yu-chi,Metaxas D N．Hypergraph with sampling for image retrieval [J]．Pattern Recognition,2011,44(10/11):2255-2262
[13] Wang Jing-dong,Zhao Ying-hai,Wu Xiu-qing,et al．A transductive multi-label learning approach for video concept detection [J]．Pattern Recognition,2011,44(10/11):2274-2286
[14] Tang Jin-hui,Hua Xian-sheng,Mei Tao,et al．Video annotation based on temporally consistent Gaussian random field [J]．Electronics Letters,2007,43(8):448-449
[15] Song Yan,Hua Xian-sheng,Dai Li-rong,et al．Semi-automatic video annotation based on active learning with multiple complementary predictors [C]∥Proceedings of the 7th ACM SIGMM international workshop on Multimedia information retrieval．Singapore,2005:97-104
[16] 袁正午,朱冠宇,丰江帆,等.基于支持向量机的视频语义场景分割算法研究[J].重庆邮电大学学报:自然科学版,2010,2(4):458-463

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed