J4 ›› 2015, Vol. 42 ›› Issue (4): 81-87.doi: 10.3969/j.issn.1001-2400.2015.04.014

• 研究论文 • 上一篇    下一篇

HCRF和网络文本的精彩事件自动检测定位

同鸣;王硕;丁力伟;王纲   

  1. (西安电子科技大学 电子工程学院,陕西 西安  710071)
  • 收稿日期:2014-04-15 出版日期:2015-08-20 发布日期:2015-10-12
  • 通讯作者: 同鸣
  • 作者简介:同鸣(1963-),女,教授,博士,E-mail:mtong@xidian.edu.cn.
  • 基金资助:

    国家自然科学基金资助项目(61072110);陕西省重点难题攻关资助项目(2013KTZB03-03-03)

Wonderful events automatic detection and location of the HCRF  and webcast text

TONG Ming;WANG Shuo;DING Liwei;WANG Gang   

  1. (School of Electronic Engineering, Xidian Univ., Xi'an  710071, China)
  • Received:2014-04-15 Online:2015-08-20 Published:2015-10-12
  • Contact: TONG Ming

摘要:

利用隐条件随机场(HCRF)在表达和识别语义事件方面的强大功能,并结合网络直播文本信息,提出了一种新的精彩事件自动检测框架.首先,通过对网络直播文本进行分析处理,获得每种精彩事件对应的关键词组合; 其次,对待检测的网络直播文本进行分类,获得每个精彩事件发生的时间标签;然后,构建用于提出的语义镜头标注的HCRF模型,实现多种语义镜头的同时标注,得到视频语义镜头标签序列; 最后,结合多模态语义线索,在小规模训练样本的情况下,有效建立了精彩事件检测与定位的HCRF模型.文中基于视频底层特征、多模态语义线索及精彩语义事件之间的映射关系,从结构语义的多个维度挖掘了精彩事件的内在规律,准确实现了精彩事件的自动检测、定位与分割.实验结果证明了该模型的有效性.

关键词: 视频语义分析, 事件检测, 网络文本, 隐条件随机场, 语义镜头标注

Abstract:

Based on the powerful function of the hidden conditional random fields (HCRF) model in the expression and identification of semantic events and combining the webcast text information, a new framework for wonderful events automatic detection is put forward. Firstly, by analyzing and processing the webcast text,  keyword combinations corresponding to each exciting event are obtained. Secondly, by classifying the webcast text to be detected, the happening time labels of each wonderful event are obtained. Thirdly, an HCRF model for semantic shot annotation is built to realize the semantic annotation of multiple types of semantic shots simultaneously, and the semantic shot sequence of the video clip is obtained. Finally, combining the multi-modal semantic clues, an HCRF model for the wonderful events detection and localization is effectively built in the case of small-scale training samples. Based on the mapping relationship among video low-level features, the multi-modal semantic clues and the wonderful semantic events, the inherent patterns of the wonderful events are excavated deeply in the multiple dimensions of the semantic structure, and then the wonderful events automatic detection, localization and segmentation are precisely achieved. Experiments show the effectiveness of this model.

Key words: video semantic analysis, event detection, webcast text, hidden conditional random field (HCRF), semantic shots annotation

中图分类号: 

  • TP391