• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Machine Vision and Applications >Selection of negative samples and two-stage combination of multiple features for action detection in thousands of videos
【24h】

Selection of negative samples and two-stage combination of multiple features for action detection in thousands of videos

机译：阴性样本的选择以及多种功能的两阶段组合，可在数千个视频中进行动作检测

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this paper, a system is presented that can detect 48 human actions in realistic videos, ranging from simple actions such as 'walk'to complex actions such as 'exchange'. We propose a method that gives a major contribution in performance. The reason for this major improvement is related to a different approach on three themes: sample selection, two-stage classification, and the combination of multiple features. First, we show that the sampling can be improved by smart selection of the negatives. Second, we show that exploiting all 48 actions'posteriors by two-stage classification greatly improves its detection. Third, we show how low-level motion and high-level object features should be combined. These three yield a performance improvement of a factor 2.37 for human action detection in the visint.org test set of 1,294 realistic videos. In addition, we demonstrate that selective sampling and the two-stage setup improve on standard bag-of-feature methods on the UT-interaction dataset, and our method outperforms state-of-the-art for the IXMAS dataset.
机译：在本文中，提出了一种系统，该系统可以检测现实视频中的48种人类动作，范围从简单的动作（例如“走”）到复杂的动作（例如“交流”）。我们提出了一种对性能做出重大贡献的方法。进行此重大改进的原因与针对三个主题的不同方法有关：样本选择，两阶段分类以及多种功能的组合。首先，我们表明可以通过明智地选择底片来改善采样效果。其次，我们表明通过两阶段分类来利用所有48个动作的后验可以大大提高其检测率。第三，我们展示了低级运动和高级对象特征应该如何结合。在visint.org测试视频集（共1,294个）中，这三项操作的性能提高了2.37倍，可用于人类动作检测。此外，我们证明了选择性采样和两阶段设置相对于UT交互数据集上的标准特征袋方法有所改进，并且我们的方法优于IXMAS数据集的最新技术。

著录项

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