首页> 外文会议>20th European conference on artificial intelligence >Improving Video Activity Recognition using Object Recognition and Text Mining
【24h】

Improving Video Activity Recognition using Object Recognition and Text Mining

机译:使用对象识别和文本挖掘改进视频活动识别

获取原文
获取原文并翻译 | 示例

摘要

Recognizing activities in real-world videos is a challenging AI problem. We present a novel combination of standard activity classification, object recognition, and text mining to learn effective activity recognizers without ever explicitly labeling training videos. We cluster verbs used to describe videos to automatically discover classes of activities and produce a labeled training set. This labeled data is then used to train an activity classifier based on spatio-temporal features. Next, text mining is employed to learn the correlations between these verbs and related objects. This knowledge is then used together with the outputs of an off-the-shelf object recognizer and the trained activity classifier to produce an improved activity recognizer. Experiments on a corpus of YouTube videos demonstrate the effectiveness of the overall approach.
机译:识别真实视频中的活动是一个具有挑战性的AI问题。我们提出了标准活动分类,对象识别和文本挖掘的新颖组合,以学习有效的活动识别器,而无需明确标记培训视频。我们将用于描述视频的动词聚类,以自动发现活动类别并产生标记的训练集。然后,该标记的数据用于基于时空特征来训练活动分类器。接下来,采用文本挖掘来学习这些动词和相关对象之间的相关性。然后,将这些知识与现成的对象识别器和受过训练的活动分类器的输出一起使用,以产生改进的活动识别器。 YouTube视频库的实验证明了整体方法的有效性。

著录项

  • 来源
  • 会议地点 Montpellier(FR)
  • 作者单位

    Department of Computer Science, The University of Texas at Austin, 1616 Guadalupe, Suite 2.408, Austin, TX 78701, USA;

    Department of Computer Science, The University of Texas at Austin, 1616 Guadalupe, Suite 2.408, Austin, TX 78701, USA;

  • 会议组织
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号