<?xml version="1.0" encoding="utf-8" standalone="yes" ?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Shien Ke | ViLab</title>
    <link>https://vilab.team/author/shien-ke/</link>
      <atom:link href="https://vilab.team/author/shien-ke/index.xml" rel="self" type="application/rss+xml" />
    <description>Shien Ke</description>
    <generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Mon, 29 Jun 2026 00:00:00 +0000</lastBuildDate>
    <image>
      <url>https://vilab.team/media/icon_hu2896232876136423579.png</url>
      <title>Shien Ke</title>
      <link>https://vilab.team/author/shien-ke/</link>
    </image>
    
    <item>
      <title>Token-Wise Attention-Guided Semantic Quality Assessment for Compressed Visual Features</title>
      <link>https://vilab.team/publication/token-wise-attention-guided-semantic-quality-assessment-for-/</link>
      <pubDate>Mon, 29 Jun 2026 00:00:00 +0000</pubDate>
      <guid>https://vilab.team/publication/token-wise-attention-guided-semantic-quality-assessment-for-/</guid>
      <description>&lt;p&gt;本文针对协作与分布式智能系统中压缩中间特征的语义质量评估问题，提出了一种基于Token级注意力引导的评估方法。该方法利用原始与重建Token之间的内在对应关系，在Token层面进行质量度量，以减少跨Token干扰；同时通过注意力机制区分不同Token对下游任务的重要性，从而更准确地反映压缩特征的语义效用。实验表明，该方法在多种特征编解码器上均优于传统相似性度量，具有良好的鲁棒性。&lt;/p&gt;
</description>
    </item>
    
  </channel>
</rss>
