...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Signal processing >Distinctive action sketch for human action recognition
【24h】

Distinctive action sketch for human action recognition

机译：人体动作识别的独特动作示意图

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

Highlights•We introduce sketch to the field of action recognition and propose a ranking based method to discover the most distinctive action sketches.•We present a novel approach of action representation based on four kinds of sketch pooling strategy.•Extensive experiments on two public human action datasets are conducted to demonstrate the effectiveness of the proposed method.AbstractRecent developments in the field of computer vision have led to a renewed interest in sketch correlated research. There have emerged considerable solid evidence which revealed the significance of sketch. However, there have been few profound discussions on sketch based action analysis so far. In this paper, we propose an approach to discover the most distinctive sketches for action recognition. The action sketches should satisfy two characteristics: sketchability and objectiveness. Primitive sketches are prepared according to the structured forests based fast edge detection. Meanwhile, we take advantage of Faster R-CNN to detect the persons in parallel. On completion of the two stages, the process of distinctive action sketch mining is carried out. After that, we present four kinds of sketch pooling methods to get a uniform representation for action videos. The experimental results show that the proposed method achieves impressive performance against several compared methods on two public datasets.
机译： 突出显示 • 我们将草图引入动作识别领域，并提出一种基于排名的方法来发现最独特的动作草图。 • 我们提出了一种新颖的动作表示方法基于四种草图池策略。 • 对两个公共人类行为数据集进行了广泛的实验，以证明该方法的有效性。 摘要 计算机视觉领域的最新发展引起了人们对素描相关研究的新兴趣。涌现出大量可靠的证据，揭示了草图的重要性。但是，到目前为止，关于基于草图的动作分析的讨论很少。在本文中，我们提出了一种方法来发现最独特的草图以进行动作识别。动作草图应满足两个特征：可草图性和客观性。根据基于结构化森林的快速边缘检测来准备原始草图。同时，我们利用Faster R-CNN并行检测人员。在这两个阶段完成之后，便进行了独特的动作草图挖掘过程。之后，我们提出了四种草图合并方法来获得动作视频的统一表示。实验结果表明，与在两个公共数据集上的几种比较方法相比，该方法取得了令人印象深刻的性能。

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