• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International conference on graphic and image processing >Multi-dimension Feature Fusion for Action Recognition
【24h】

Multi-dimension Feature Fusion for Action Recognition

机译：用于动作识别的多维特征融合

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

摘要

Typical human actions last several seconds and exhibit characteristic spatio-temporal structure. The challenge for action recognition is to capture and fuse the multi-dimension information in video data. In order to take into account these characteristics simultaneously, we present a novel method that fuses multiple dimensional features, such as chromatic images, depth and optical flow fields. We built our model based on the multi-stream deep convolutional networks with the help of temporal segment networks and extract discriminative spatial and temporal features by fusing ConvNets towers multi-dimension, in which different feature weights are assigned in order to take full advantage of this multi-dimension information. Our architecture is trained and evaluated on the currently largest and most challenging benchmark NTU RGB-D dataset. The experiments demonstrate that the performance of our method outperforms the state-of-the-art methods.
机译：典型的人类动作持续几秒钟，并展现出独特的时空结构。动作识别的挑战是捕获和融合视频数据中的多维信息。为了同时考虑这些特性，我们提出了一种融合多维特征（例如彩色图像，深度和光流场）的新颖方法。我们借助时域分段网络在多流深度卷积网络的基础上构建模型，并通过融合ConvNets塔的多维维度来提取判别性时空特征，其中分配了不同的特征权重以充分利用此优势多维信息。我们的体系结构是在当前最大，最具挑战性的基准NTU RGB-D数据集上进行训练和评估的。实验表明，我们方法的性能优于最新方法。

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