首页> 外文OA文献 >Log-Euclidean bag of words for human action recognition
【2h】

Log-Euclidean bag of words for human action recognition

机译:对数欧几里得的单词包用于人类动作识别

代理获取
本网站仅为用户提供外文OA文献查询和代理获取服务,本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文,但由于OA文献来源多样且变更频繁,仍可能出现获取不到、文献不完整或与标题不符等情况,如果获取不到我们将提供退款服务。请知悉。

摘要

Representing videos by densely extracted local space-time features has recently become a popular approach for analysing actions. In this study, the authors tackle the problem of categorising human actions by devising bag of words (BoWs) models based on covariance matrices of spatiotemporal features, with the features formed from histograms of optical flow. Since covariance matrices form a special type of Riemannian manifold, the space of symmetric positive definite (SPD) matrices, non-Euclidean geometry should be taken into account while discriminating between covariance matrices. To this end, the authors propose to embed SPD manifolds to Euclidean spaces via a diffeomorphism and extend the BoW approach to its Riemannian version. The proposed BoW approach takes into account the manifold geometry of SPD matrices during the generation of the codebook and histograms. Experiments on challenging human action datasets show that the proposed method obtains notable improvements in discrimination accuracy, in comparison with several state-of-the-art methods.
机译:通过密集提取的本地时空特征表示视频最近已成为一种流行的分析动作的方法。在这项研究中,作者通过基于时空特征的协方差矩阵设计特征的词袋(BoWs)模型来解决人类行为的分类问题,特征是由光流直方图形成的。由于协方差矩阵形成一类特殊的黎曼流形,因此在区分协方差矩阵时应考虑对称正定(SPD)矩阵的空间,非欧几里得几何。为此,作者建议通过微分同构将SPD流形嵌入到欧氏空间中,并将BoW方法扩展到其黎曼形式。拟议的BoW方法在生成码本和直方图时考虑了SPD矩阵的流形几何形状。在具有挑战性的人类动作数据集上进行的实验表明,与几种最先进的方法相比,该方法在识别准确度上有显着提高。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
代理获取

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