• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IAPR TC3 Workshop on pattern recognition of social signals in human-computer-interaction >Hierarchical Bayesian Multiple Kernel Learning Based Feature Fusion for Action Recognition
【24h】

Hierarchical Bayesian Multiple Kernel Learning Based Feature Fusion for Action Recognition

机译：基于层次贝叶斯多核学习的特征融合的动作识别

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Human action recognition is an area with increasing significance and has attracted much research attention over these years. Fusing multiple features is intuitively an appropriate way to better recognize actions in videos, as single type of features is not able to capture the visual characteristics sufficiently. However, most of the existing fusion methods used for action recognition fail to measure the contributions of different features and may not guarantee the performance improvement over the individual features. In this paper, we propose a new Hierarchical Bayesian Multiple Kernel Learning (HB-MKL) model to effectively fuse diverse types of features for action recognition. The model is able to adaptively evaluate the optimal weights of the base kernels constructed from different features to form a composite kernel. We evaluate the effectiveness of our method with the complementary features capturing both appearance and motion information from the videos on challenging human action datasets, and the experimental results demonstrate the potential of HB-MKL for action recognition.
机译：人体动作识别是一个越来越重要的领域，近年来引起了很多研究关注。直观地融合多个功能是更好地识别视频中动作的一种适当方法，因为单一类型的功能无法充分捕捉视觉特征。但是，用于动作识别的大多数现有融合方法无法衡量不同特征的贡献，并且可能无法保证对单个特征的性能改进。在本文中，我们提出了一种新的多层贝叶斯多核学习（HB-MKL）模型，以有效地融合各种类型的功能以进行动作识别。该模型能够自适应地评估由不同特征构成的基础内核的最佳权重，以形成复合内核。我们使用具有挑战性的人类动作数据集上的视频捕获外观和动作信息的互补功能，评估了我们方法的有效性，实验结果证明了HB-MKL在动作识别方面的潜力。

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