...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Multimedia Tools and Applications >Supervised spatio-temporal kernel descriptor for human action recognition from RGB-depth videos
【24h】

Supervised spatio-temporal kernel descriptor for human action recognition from RGB-depth videos

机译：受监督的时空内核描述符，用于从RGB深度视频中识别人类动作

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

One of the most challenging tasks in computer vision is human action recognition. The recent development of depth sensors has created new opportunities in this field of research. In this paper, a novel supervised spatio-temporal kernel descriptor (SSTKDes) is proposed from RGB-depth videos to establish a discriminative and compact feature representation of actions. To enhance the descriptive and discriminative ability of the descriptor, extracted primary kernel-based features are transformed into a new space by exploiting a supervised training strategy; i.e., large margin nearest neighbor (LMNN). The LMNN highly reduces the error of a nearest neighbor classifier by minimizing the intra-class variations and maximizing the inter-class distances. Subsequently, the efficient match kernel (EMK) is used to abstract the mid-level kernel features for a more efficient classification. The proposed approach is evaluated on five public benchmark datasets. The experimental evaluations demonstrate that the proposed method achieves superior performance to the state-of-the-art methods.
机译：人类动作识别是计算机视觉中最具挑战性的任务之一。深度传感器的最新发展为该研究领域创造了新的机遇。本文从RGB深度视频中提出了一种新颖的监督时空内核描述符（SSTKDes），以建立可区分且紧凑的动作特征表示。为了增强描述符的描述性和判别能力，通过采用监督训练策略，将提取的基于核的主要特征转换为新的空间。即大边距最近邻居（LMNN）。 LMNN通过最小化类内差异和最大化类间距离，极大地减少了最近邻居分类器的误差。随后，有效匹配内核（EMK）用于抽象中级内核功能，以实现更有效的分类。在五个公共基准数据集上对提出的方法进行了评估。实验评估表明，所提出的方法具有优于最新方法的性能。

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