<?xml version="1.0" encoding="utf-8" standalone="yes" ?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>运动增强 | ViLab</title>
    <link>https://vilab.team/tag/%E8%BF%90%E5%8A%A8%E5%A2%9E%E5%BC%BA/</link>
      <atom:link href="https://vilab.team/tag/%E8%BF%90%E5%8A%A8%E5%A2%9E%E5%BC%BA/index.xml" rel="self" type="application/rss+xml" />
    <description>运动增强</description>
    <generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Mon, 15 Jul 2024 00:00:00 +0000</lastBuildDate>
    <image>
      <url>https://vilab.team/media/icon_hu2896232876136423579.png</url>
      <title>运动增强</title>
      <link>https://vilab.team/tag/%E8%BF%90%E5%8A%A8%E5%A2%9E%E5%BC%BA/</link>
    </image>
    
    <item>
      <title>Estme: Event-driven spatio-temporal motion enhancement for micro-expression recognition</title>
      <link>https://vilab.team/publication/estme-event-driven-spatio-temporal-motion-enhancement-for-mi/</link>
      <pubDate>Mon, 15 Jul 2024 00:00:00 +0000</pubDate>
      <guid>https://vilab.team/publication/estme-event-driven-spatio-temporal-motion-enhancement-for-mi/</guid>
      <description>&lt;p&gt;本文针对微表情识别中动作幅度小、持续时间短、难以捕捉的问题，提出了一种事件驱动的时空运动增强网络。该方法引入事件相机捕获的高时间分辨率事件信号，设计事件增强运动提取模块以增强细微运动细节，并利用事件引导注意力模块聚焦特定区域的微小变化，从而获取更精确的空间特征。在合成和真实数据集上的实验结果表明，该方法在微表情识别任务上具有优越性能。&lt;/p&gt;
</description>
    </item>
    
  </channel>
</rss>
