期刊文献+

视频场景中的暴力行为识别上的关键技术研究 被引量:1

下载PDF
导出
摘要 对于视频场景中的一些异常行为(暴力行为)识别技术,本文重点研究深度学习邻接层间的度量机制和跨层学习方法,建立深度暴力特征网络框架,以及研究基于改进的稀疏表达分类的检测框架,实现进一步提升识别能力并达到实际监控应用。
出处 《电脑知识与技术》 2021年第25期116-117,共2页 Computer Knowledge and Technology
  • 相关文献

参考文献1

二级参考文献14

  • 1郭武,戴礼荣,王仁华.采用UBM更新量作为支持向量机特征的说话人确认[J].清华大学学报(自然科学版),2008,48(S1):704-707. 被引量:4
  • 2Campbell W,Sturim D,Reynolds D.Support vector machinesusing GMM supervectors for speaker verification[J].SignalProcess Letters,2006,13(5):308-311.
  • 3Sarkar S,Rao K S.Speaker verification in noisy environmentusing GMM supervectors[C].2013 National Conferenceon Communications,2013:1-5.
  • 4Dehak N,Kenny P J,Dehak R,et al.Front-end factor analysisfor speaker verification[J].Audio,Speech,and LanguageProcessing,2011,19(4):788-798.
  • 5Kanagasundaram A,Deana D,Sridharan S,et al.I-vectorbased speaker recognition using advanced channel compensationtechniques[J].Computer Speech and Language,2014,28(1):121-140.
  • 6Naseem I,Togneri R,Bennamoun M.Sparse representationfor speaker identification[C].20th International Conferenceon Pattern Recognition(ICPR),2010:4460-4463.
  • 7Mohammadi M R,Fatemizadeh E,Mahoor M H.PCA-baseddictionary building for accurate facial expression recognitionvia sparse representation[J].Journal of Visual Communicationand Image,2014,25(5):1082-1092.
  • 8Haris B C,Sinha R.Speaker verification using sparse representationover KSVD learned dictionary[C].2012 NationalConference on Communications,2012:1-5.
  • 9Matejka P,Glembek O,Castaldo F,et al.Full-covarianceUBM and heavy-tailed PLDA in i-vector speaker verification[C].IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP),2011:4828-4831.
  • 10Scholkopf B.Platt J.Hofmann T.Sparse representation forsignal classification[C].Proceedings of the 2006 Conferenceon Advances in Neural Information ProcessingSystems.2007:609-616.

同被引文献4

引证文献1

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