...
首页> 外文期刊>Journal of visual communication & image representation >Learning discriminative motion feature for enhancing multi-modal action recognition
【24h】

Learning discriminative motion feature for enhancing multi-modal action recognition

机译:学习辨别运动功能,用于增强多模态动作识别

获取原文
获取原文并翻译 | 示例
           

摘要

Video action recognition is an important topic in computer vision tasks. Most of the existing methods use CNN-based models, and multiple modalities of image features are captured from the videos, such as static frames, dynamic images, and optical flow features. However, these mainstream features contain much static information including object and background information, where the motion information of the action itself is not distinguished and strengthened. In this work, a new kind of motion feature is proposed without static information for video action recognition. We propose a quantization of motion network based on the bag-of feature method to learn significant and discriminative motion features. In the learned feature map, the object and background information is filtered out, even if the background is moving in the video. Therefore, the motion feature is complementary to the static image feature and the static information in the dynamic image and optical flow. A multi-stream classifier is built with the proposed motion feature and other features, and the performance of action recognition is enhanced comparing to other state-of-the-art methods.
机译:视频动作识别是计算机视觉任务中的一个重要主题。现有的大多数方法使用基于CNN的模型,并且从诸如静态帧,动态图像和光流特征的视频捕获多种图像特征模式。然而,这些主流特征包含许多静态信息,包括对象和背景信息,其中动作本身的运动信息不是区分和加强。在这项工作中,提出了一种新的运动特征,而没有用于视频动作识别的静态信息。我们提出了基于袋特征方法的运动网络的量化,以学习显着和辨别的运动特征。在学习的特征映射中,即使背景在视频中移动,也会过滤出对象和背景信息。因此,运动特征与动态图像和光流中的静态图像特征和静态信息互补。使用所提出的运动特征和其他功能构建多流分类器,并且与其他最先进的方法相比,可以增强动作识别性能。

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