<?xml version="1.0" encoding="utf-8" standalone="yes" ?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>概率模型 | ViLab</title>
    <link>https://vilab.team/tag/%E6%A6%82%E7%8E%87%E6%A8%A1%E5%9E%8B/</link>
      <atom:link href="https://vilab.team/tag/%E6%A6%82%E7%8E%87%E6%A8%A1%E5%9E%8B/index.xml" rel="self" type="application/rss+xml" />
    <description>概率模型</description>
    <generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Wed, 01 Jan 2020 00:00:00 +0000</lastBuildDate>
    <image>
      <url>https://vilab.team/media/icon_hu2896232876136423579.png</url>
      <title>概率模型</title>
      <link>https://vilab.team/tag/%E6%A6%82%E7%8E%87%E6%A8%A1%E5%9E%8B/</link>
    </image>
    
    <item>
      <title>Spatiotemporal fusion in 3D CNNs: A probabilistic view</title>
      <link>https://vilab.team/publication/spatiotemporal-fusion-in-3d-cnns-a-probabilistic-view/</link>
      <pubDate>Wed, 01 Jan 2020 00:00:00 +0000</pubDate>
      <guid>https://vilab.team/publication/spatiotemporal-fusion-in-3d-cnns-a-probabilistic-view/</guid>
      <description>&lt;p&gt;本文从概率视角重新审视三维卷积神经网络中的时空融合机制，提出了一种统一的概率建模框架，以刻画空间与时间信息在卷积过程中的交互关系。通过将时空融合视为潜在变量条件下的概率推断问题，该方法能够更有效地捕捉视频数据中的动态依赖，并提升模型在动作识别等视频理解任务上的表现。&lt;/p&gt;
</description>
    </item>
    
  </channel>
</rss>
