基于张量表示的直推式多模态视频语义概念检测
DOI:
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

基金项目:

Supported by the National Natural Science Foundation of China under Grant Nos.60603096, 60533090 (国家自然科学基金); the National High-Tech Research and Development Plan of China under Grant No.2006AA010107 (国家高技术研究发展计划(863); the National Key Technology R&D Program of China under Grant No.2007BAH11B01 (国家科技支撑计划); the Program for Changjiang Scholars and Innovative Research Team in University of China under Grant Nos.IRT0652, PCSIRT (长江学者和创新团队发展计划)


Transductive Multi-Modality Video Semantic Concept Detection with Tensor Representation
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    提出了一种基于高阶张量表示的视频语义分析与理解框架.在此框架中,视频镜头首先被表示成由视频中所包含的文本、视觉和听觉等多模态数据构成的三阶张量;其次,基于此三阶张量表达及视频的时序关联共生特性设计了一种子空间嵌入降维方法,称为张量镜头;由于直推式学习从已知样本出发能对特定的未知样本进行学习和识别,最后在这个框架中提出了一种基于张量镜头的直推式支持张量机算法,它不仅保持了张量镜头所在的流形空间的本征结构,而且能够将训练集合外数据直接映射到流形子空间,同时充分利用未标记样本改善分类器的学习性能.实验结果表明,该方法能够有效地进行视频镜头的语义概念检测.

    Abstract:

    A higher-order tensor framework for video analysis and understanding is proposed in this paper. In this framework, image frame, audio and text are represented, which are the three modalities in video shots as data points by the 3rd-order tensor. Then a subspace embedding and dimension reduction method is proposed, which explicitly considers the manifold structure of the tensor space from temporal-sequenced associated co-occurring multimodal media data in video. It is called TensorShot approach. Transductive learning uses a large amount of unlabeled data together with the labeled data to build better classifiers. A transductive support tensor machines algorithm is proposed to train effective classifier. This algorithm preserves the intrinsic structure of the submanifold where tensorshots are sampled, and is also able to map out-of-sample data points directly. Moreover, the utilization of unlabeled data improves classification ability. Experimental results show that this method improves the performance of video semantic concept detection.

    参考文献
    相似文献
    引证文献
引用本文

吴 飞,刘亚楠,庄越挺.基于张量表示的直推式多模态视频语义概念检测.软件学报,2008,19(11):2853-2868

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2008-03-01
  • 最后修改日期:2008-08-26
  • 录用日期:
  • 在线发布日期:
  • 出版日期:
您是第位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京市海淀区中关村南四街4号,邮政编码:100190
电话:010-62562563 传真:010-62562533 Email:jos@iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号