期刊文献+

基于视觉词模糊权重的视频语义标注

Video Semantic Annotation Based on Visual Word Fuzzy Weighting
下载PDF
导出
摘要 针对视觉词袋模型的量化误差与视觉词含糊性,提出一种基于视觉词模糊权重的视频语义标注方案。该方案在训练样本集的预聚类基础上,逐个聚类训练单类支持向量机OC-SVM。根据样本特征与聚类超球球心的距离函数及聚类超球的空间分布确定视觉词映射及权重,以提高视觉词的表达力、区别力。实验结果表明,基于该方案的视频语义标注精度分别比TF方案和VWA方案提高34%和16%。 This paper proposes a formulation of visual word weighting scheme Fuzzy Weighting Scheme(FWS) aiming at the Bag of Visual Word(BoVW) model vector quantization loss and visual word ambiguity. Based on K-Nearest Neighhors(KNN) pre-clustering results, One-Class Support Vector Machine(OC-SVM) on each clustering samples subset is trained. Visual words corresponding to a single local visual feature vector are determined according to the spatial distribution information of clustering-hyperspheres and fuzzy weights are evaluated according to the distance function between sample feature and center of clustering-hypersphere. FWS is designed to boost the visual word expressiveness and discriminativeness. Experimental results show that the scheme outperforms TF scheme and VWA scheme by 34% and 16% respectively on video semantic annotation precision.
作者 霍华 赵刚
出处 《计算机工程》 CAS CSCD 2012年第13期131-133,共3页 Computer Engineering
基金 国家自然科学基金资助项目(60743008) 河南省国际科技合作计划基金资助项目(104300510063)
关键词 视频语义标注 视觉词袋模型 模糊权重方案 单类支持向量机 聚类超球 模糊隶属度 video semantic annotation Bag of Visual Word(BoVW) model Fuzzy Weighting Scheme(FWS) One-Class Support Vector Machine (OC-SVM) clustering hypersphere fuzzy membership degree
  • 相关文献

参考文献8

  • 1Ding Guiguang,Zhang Lu,Li Xiao.Video Annotation Based onAdaptive Annular Spatial Partition Scheme[J].IEICE ElectronicsExpress,2010,7(1):7-12.
  • 2程蕾,吴秀清.局部特征几何结构用于目标识别[J].计算机工程与应用,2010,46(26):191-193. 被引量:3
  • 3Sivic J.Video Google:A Text Retrieval Approach to ObjectMatching in Videos[C]//Proc.of International Conference onComputer Vision.[S.l.]:IEEE Press,2003.
  • 4Yang Jun,Jiang Yugang,Hauptmann A G.Evaluating Bag-of-visual-words Representations in Scene Classification[C]//Proc.ofACM SIGMM International Workshop on Multimedia InformationRetrieval.[S.1.]:ACM Press,2007.
  • 5Jiang Yugang,Ngo C W,Yang Jun.Towards Optimal Bag-of-features for Object Categorization and Semantic VideoRetrieval[C]//Proc.of the 6th ACM International Conference onImage and Video Retrieval.[S.1.]:ACM Press,2007.
  • 6Jan C,van Gemert,Veenman C J,et al.Visual Word Ambiguity[J].IEEE Trans.on Pattern Analysis and Machine Intelligence,2009,32(7):1271-1283.
  • 7Tax D M J,Duin R P W.Support Vector Data Description[J].Machine Learning Research,2004,54(1):45-56.
  • 8Chang Chih-Chung,Lin Chih-Jen.LIBSVM-a Library for SupportVector Machines[EB/OL].[2009-04-01].http://www.csie.ntu.edu.tw/~cjlin/.

二级参考文献8

  • 1Lowe D.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision, 2004,60 (2) : 91-110.
  • 2Bay H,Tuytelaars T,van Gool L.SURF:Speeded up robust features[C]//European Conference on Computer Vision, Graz, Austria, 2006 : 404-417.
  • 3Csurka G, Dance C, Lixin F, et al.Visual categorization with bags of keypoints[C]//European Conference on Computer Vision,Prague,Czech Republic,2004: 59-74.
  • 4Nister D, Stewenius H.Scalable recognition with a vocabulary tree[C]//IEEE Proceedings of the International Conference on Computer Vision and Pattern Recognition, 2006: 2161-2168.
  • 5Fergus R, Perona P, Zisserman A.Weakly supervised scale-invariant learning of models for visual recognition[J].Intemational Journal of Computer Vision, 2007,71 (3) : 273-303.
  • 6Fergus R,Perona P,Zisserman A.A sparse object category model for efficient learning and exhaustive reeognition[C]//IEEE Proceedings of the International Conference on Computer Vision and Pattern Recognition,2005:380-387.
  • 7Fergus R,Perona P,Zisserman A.Object class recognition by unsupervised scale-invariant leaming[C]//IEEE Proceedings of the International Conference on Computer Vision and Pattern Recognition, 2003 : 264-271.
  • 8Mikolajcayk K,Schmid C.A performance evaluation of local descriptors[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2005,27(10) : 1615-1630.

共引文献2

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部