<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Scratchpad on Kai Kunze</title><link>https://kaikunze.de/categories/scratchpad/</link><description>Recent content in Scratchpad on Kai Kunze</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 26 Jul 2012 00:00:00 +0000</lastBuildDate><atom:link href="https://kaikunze.de/categories/scratchpad/index.xml" rel="self" type="application/rss+xml"/><item><title>AAAI activity context workshop notes</title><link>https://kaikunze.de/2012/07/26/aaai-activity-context-workshop-notes/</link><pubDate>Thu, 26 Jul 2012 00:00:00 +0000</pubDate><guid>https://kaikunze.de/2012/07/26/aaai-activity-context-workshop-notes/</guid><description>&lt;p&gt;I enjoyed the AAAI context activity workshop a lot.&lt;/p&gt;&#10;&lt;p&gt;The keynote &lt;a href="https://web.archive.org/web/20220705182419/https://aaai.org/ocs/index.php/WS/AAAIW12/paper/view/5292/5556"&gt;How to make Face&#10;Recognition work (pdf)&lt;/a&gt;&#10;by &lt;a href="http://research.microsoft.com/en-us/um/people/akapoor/"&gt;Ashis Kapoor&lt;/a&gt;&#10;showed how to increase face recognition introducing very simple &amp;ldquo;context&amp;rdquo; constrains&#10;(two people in the same image cannot be the same person etc.).&#10;Very interesting work, I wonder how much better you can get introducing&#10;some more dynamic context recognition to the face recognition task.&lt;/p&gt;&#10;&lt;p&gt;&lt;a href="http://www.cs.ubc.ca/~murphy/"&gt;Gail Murphy&lt;/a&gt; gave the other keynote&#10;&lt;a href="http://www.aaai.org/ocs/index.php/WS/AAAIW12/paper/view/5302/5557"&gt;Task Context for Knowledge Workers (pdf)&lt;/a&gt;.&#10;She introduces context modelling for tasks in GTD scenarios.&#10;Also quite interesting, as completely complimentary to my work (no mobile&#10;clients, sensors etc.).&lt;/p&gt;</description></item></channel></rss>