<?xml version="1.0" encoding="utf-8" standalone="yes" ?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Yue Li | ViLab</title>
    <link>https://vilab.team/author/yue-li/</link>
      <atom:link href="https://vilab.team/author/yue-li/index.xml" rel="self" type="application/rss+xml" />
    <description>Yue Li</description>
    <generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Sun, 16 Jun 2024 00:00:00 +0000</lastBuildDate>
    <image>
      <url>https://vilab.team/media/icon_hu2896232876136423579.png</url>
      <title>Yue Li</title>
      <link>https://vilab.team/author/yue-li/</link>
    </image>
    
    <item>
      <title>Event-assisted low-light video object segmentation</title>
      <link>https://vilab.team/publication/event-assisted-low-light-video-object-segmentation/</link>
      <pubDate>Sun, 16 Jun 2024 00:00:00 +0000</pubDate>
      <guid>https://vilab.team/publication/event-assisted-low-light-video-object-segmentation/</guid>
      <description>&lt;p&gt;本文针对低光照条件下视频目标分割（VOS）性能严重下降的问题，提出一种利用事件相机数据辅助分割的新框架。该方法包含两个关键模块：自适应跨模态融合（ACMF）模块，用于提取并融合图像与事件模态特征以抑制噪声干扰；事件引导记忆匹配（EGMM）模块，用于修正低光下查询帧与记忆帧之间的相似度计算误差。实验表明，该方法在合成和真实低光数据集上均能显著提升分割精度，生成更准确的目标掩码。&lt;/p&gt;
</description>
    </item>
    
  </channel>
</rss>
