<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	>
<channel>
	<title>Comments on: Google Experiments With Next Generation Image Search</title>
	<atom:link href="http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/feed/" rel="self" type="application/rss+xml" />
	<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/</link>
	<description>Startup and Technology News</description>
	<pubDate>Wed, 09 Jul 2008 07:14:35 +0000</pubDate>
	<generator>http://wordpress.org/?v=2.5.1</generator>
		<item>
		<title>By: A few thoughts on image retrieval &#171;</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2398398</link>
		<dc:creator>A few thoughts on image retrieval &#171;</dc:creator>
		<pubDate>Sat, 05 Jul 2008 06:51:08 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2398398</guid>
		<description>[...] retrieval is a hot issue in information [...]</description>
		<content:encoded><![CDATA[<p>[...] retrieval is a hot issue in information [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: The &#60;Image&#62; is Out There at nonrational</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2397452</link>
		<dc:creator>The &#60;Image&#62; is Out There at nonrational</dc:creator>
		<pubDate>Fri, 04 Jul 2008 06:00:26 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2397452</guid>
		<description>[...] Search engines algorithms are classically s(text)→text. Several image search offerings perform very well at s(text)→images, but they rely on the words around the [...]</description>
		<content:encoded><![CDATA[<p>[...] Search engines algorithms are classically s(text)→text. Several image search offerings perform very well at s(text)→images, but they rely on the words around the [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: &#160; Google Experiments With Next Generation Image Search&#160;&#8212;&#160;Instant Web Meetings.COM - Video Conference, Collaboration, E Learning, Unified Communications</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2335422</link>
		<dc:creator>&#160; Google Experiments With Next Generation Image Search&#160;&#8212;&#160;Instant Web Meetings.COM - Video Conference, Collaboration, E Learning, Unified Communications</dc:creator>
		<pubDate>Thu, 29 May 2008 09:37:17 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2335422</guid>
		<description>[...] Google Experiments With Next Generation Image Search [...]</description>
		<content:encoded><![CDATA[<p>[...] Google Experiments With Next Generation Image Search [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Jiankan.info &#187; Blog Archive &#187; Google Scientists Apply A Ranking Algorithm To Images</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2299815</link>
		<dc:creator>Jiankan.info &#187; Blog Archive &#187; Google Scientists Apply A Ranking Algorithm To Images</dc:creator>
		<pubDate>Thu, 15 May 2008 23:54:15 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2299815</guid>
		<description>[...] excerpt from the article at TechCrunch Notably, the new image search technology doesn&#8217;t just index text associated with an image in [...]</description>
		<content:encoded><![CDATA[<p>[...] excerpt from the article at TechCrunch Notably, the new image search technology doesn&#8217;t just index text associated with an image in [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Google will use Image PageRank to improve image search</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2293618</link>
		<dc:creator>Google will use Image PageRank to improve image search</dc:creator>
		<pubDate>Tue, 13 May 2008 14:30:34 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2293618</guid>
		<description>[...] of Google image search future were uncovered recently by two Google scientists Yushi Jing&#160; and Shumeet Baluja. Google previous technology [...]</description>
		<content:encoded><![CDATA[<p>[...] of Google image search future were uncovered recently by two Google scientists Yushi Jing&nbsp; and Shumeet Baluja. Google previous technology [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Google Reformula Busca por Imagens &#171; Our Digital Life</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2284995</link>
		<dc:creator>Google Reformula Busca por Imagens &#171; Our Digital Life</dc:creator>
		<pubDate>Fri, 09 May 2008 14:31:05 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2284995</guid>
		<description>[...] exemplo citado em um artigo do TechCrunch é bem interessante. A busca atual funciona da mesma forma que um daltônico ou um cego buscaria [...]</description>
		<content:encoded><![CDATA[<p>[...] exemplo citado em um artigo do TechCrunch é bem interessante. A busca atual funciona da mesma forma que um daltônico ou um cego buscaria [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: ::::::::Zogntai::::::::</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2280365</link>
		<dc:creator>::::::::Zogntai::::::::</dc:creator>
		<pubDate>Wed, 07 May 2008 09:06:52 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2280365</guid>
		<description>&lt;strong&gt;画像検索 Powered by Google...&lt;/strong&gt;

グーグルがまた何か企んでいるらしい。...</description>
		<content:encoded><![CDATA[<p><strong>画像検索 Powered by Google&#8230;</strong></p>
<p>グーグルがまた何か企んでいるらしい。&#8230;</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Alexander Straub</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2277489</link>
		<dc:creator>Alexander Straub</dc:creator>
		<pubDate>Tue, 06 May 2008 21:16:27 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2277489</guid>
		<description>PIXSTA CEO - Alexander Straub - CALL for comments from users on http://www.pixsta.com {seesmic_video:{"url_thumbnail":{"value":"http://t.seesmic.com/thumbnail/vsxLdCIwTi_th1.jpg"}"title":{"value":"PIXSTA CEO - Alexander Straub - CALL for comments from users on http://www.pixsta.com&#160;"}"videoUri":{"value":"http://www.seesmic.com/video/sOdHjlEV12"}}}</description>
		<content:encoded><![CDATA[<p><span class='see_video_holder'><span id='see_sOdHjlEV12_preview'><a href='http://www.seesmic.com/video/sOdHjlEV12' target='_blank' class='see_link' >PIXSTA CEO - Alexander Straub - CALL for comments from users on </a><a href=</a><br /><span class='see_video_thumb' style='background-image:url(http://t.seesmic.com/thumbnail/vsxLdCIwTi_th1.jpg)'><span onclick="see_play_video('sOdHjlEV12',true)" class='seePlayOverlay'></span></span></a></span><span id='see_sOdHjlEV12_content' class='see_video_content'></span></span></p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Alexander Straub</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2277358</link>
		<dc:creator>Alexander Straub</dc:creator>
		<pubDate>Tue, 06 May 2008 20:46:17 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2277358</guid>
		<description>Great article from Mike about PIXSTA - PICTURE YOUR SEARCH company on TechCrunch UK 
http://uk.techcrunch.com/2008/05/02/pixstas-ad-network-for-fashion-is-all-about-image/

Clearly google is not the first company to make an inroad into the field. images.google.xx has still room for improvements and several start-ups have taken the lead as described in the comments above.

Maybe time for image to image search is emerging just NOW - I guess search is sill 10 blue underlined lines and could move from the DOS like experience within the next 10 years.</description>
		<content:encoded><![CDATA[<p>Great article from Mike about PIXSTA - PICTURE YOUR SEARCH company on TechCrunch UK<br />
<a href="http://uk.techcrunch.com/2008/05/02/pixstas-ad-network-for-fashion-is-all-about-image/" rel="nofollow">http://uk.techcrunch.com/2008/.....out-image/</a></p>
<p>Clearly google is not the first company to make an inroad into the field. images.google.xx has still room for improvements and several start-ups have taken the lead as described in the comments above.</p>
<p>Maybe time for image to image search is emerging just NOW - I guess search is sill 10 blue underlined lines and could move from the DOS like experience within the next 10 years.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Miles (SEM iCluck)</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2234077</link>
		<dc:creator>Miles (SEM iCluck)</dc:creator>
		<pubDate>Tue, 29 Apr 2008 20:00:25 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2234077</guid>
		<description>Google just has to replicate the other image searches - I do love the idea of relevance decided based upon their algorithm and potential patent though - Imagine if they give that technology to the public what type of mashups will come about and what type of communities will come into fruition =o)</description>
		<content:encoded><![CDATA[<p>Google just has to replicate the other image searches - I do love the idea of relevance decided based upon their algorithm and potential patent though - Imagine if they give that technology to the public what type of mashups will come about and what type of communities will come into fruition =o)</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Harry Wang</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2233319</link>
		<dc:creator>Harry Wang</dc:creator>
		<pubDate>Tue, 29 Apr 2008 15:02:11 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2233319</guid>
		<description>Let's see it implemented first.  Have not really seen great automated image detection/search anywhere sans Google Image Search which is image tagging dependent for the most part.

Harry "wants his image search accurate" Wang</description>
		<content:encoded><![CDATA[<p>Let&#8217;s see it implemented first.  Have not really seen great automated image detection/search anywhere sans Google Image Search which is image tagging dependent for the most part.</p>
<p>Harry &#8220;wants his image search accurate&#8221; Wang</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: reemst.com &#187; Blog Archive &#187; Google experiments with VisualRank</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2233254</link>
		<dc:creator>reemst.com &#187; Blog Archive &#187; Google experiments with VisualRank</dc:creator>
		<pubDate>Tue, 29 Apr 2008 14:27:06 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2233254</guid>
		<description>[...] of search terms for particular images. Google scientists now published a paper describing the next generation of image search. This eliminates the need of humans describing images, and uses computers to analyze the images. [...]</description>
		<content:encoded><![CDATA[<p>[...] of search terms for particular images. Google scientists now published a paper describing the next generation of image search. This eliminates the need of humans describing images, and uses computers to analyze the images. [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Google rinnova Image Search &#124; FDS</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2233125</link>
		<dc:creator>Google rinnova Image Search &#124; FDS</dc:creator>
		<pubDate>Tue, 29 Apr 2008 13:15:16 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2233125</guid>
		<description>[...] documento, intitolato PageRank for Product Image Search illustra un avanzato sistema di classificazione, che unisce tecnologie software per il riconoscimento delle immagini e nuovi metodi di [...]</description>
		<content:encoded><![CDATA[<p>[...] documento, intitolato PageRank for Product Image Search illustra un avanzato sistema di classificazione, che unisce tecnologie software per il riconoscimento delle immagini e nuovi metodi di [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: the new shelton wet/dry</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2232440</link>
		<dc:creator>the new shelton wet/dry</dc:creator>
		<pubDate>Tue, 29 Apr 2008 07:21:06 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2232440</guid>
		<description>[...] Google experiments with next generation Image Search. [...]</description>
		<content:encoded><![CDATA[<p>[...] Google experiments with next generation Image Search. [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Do You See What I See? &#124; Tropophilia</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2231986</link>
		<dc:creator>Do You See What I See? &#124; Tropophilia</dc:creator>
		<pubDate>Tue, 29 Apr 2008 04:15:15 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2231986</guid>
		<description>[...] that its computers be able to interpret and index images, in addition to text.  To date, as Mike Arrington explains, computers have not been so good at this: Today when we talk about search all we really mean is [...]</description>
		<content:encoded><![CDATA[<p>[...] that its computers be able to interpret and index images, in addition to text.  To date, as Mike Arrington explains, computers have not been so good at this: Today when we talk about search all we really mean is [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: michael mandel</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2231287</link>
		<dc:creator>michael mandel</dc:creator>
		<pubDate>Mon, 28 Apr 2008 22:17:51 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2231287</guid>
		<description>As part of the PhD research, I've been working on very related problems in content-based music search.  I just put a &lt;a href="http://majorminer.com/search" rel="nofollow"&gt; demo&lt;/a&gt; up of some of the searches we can do.  In particular, it uses data from a &lt;a href="http://majorminer.com" rel="nofollow"&gt; human computation game&lt;/a&gt; to train "autotaggers", i.e. models of what tags sound like.  It takes 20-30 good examples of a tag to train an autotagger, and we only have about 50 so far, but as more people play the game and more tags cross that threshold, we'll be able to train more autotaggers.</description>
		<content:encoded><![CDATA[<p>As part of the PhD research, I&#8217;ve been working on very related problems in content-based music search.  I just put a <a href="http://majorminer.com/search" rel="nofollow" onclick="javascript:pageTracker._trackPageview ('/outbound/majorminer.com');"> demo</a> up of some of the searches we can do.  In particular, it uses data from a <a href="http://majorminer.com" rel="nofollow" onclick="javascript:pageTracker._trackPageview ('/outbound/majorminer.com');"> human computation game</a> to train &#8220;autotaggers&#8221;, i.e. models of what tags sound like.  It takes 20-30 good examples of a tag to train an autotagger, and we only have about 50 so far, but as more people play the game and more tags cross that threshold, we&#8217;ll be able to train more autotaggers.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Pagerank para imágenes &#171; El rincón seo de Raquel</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2231273</link>
		<dc:creator>Pagerank para imágenes &#171; El rincón seo de Raquel</dc:creator>
		<pubDate>Mon, 28 Apr 2008 22:10:36 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2231273</guid>
		<description>[...] Fuente: Techcrunch [...]</description>
		<content:encoded><![CDATA[<p>[...] Fuente: Techcrunch [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Blern</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2231163</link>
		<dc:creator>Blern</dc:creator>
		<pubDate>Mon, 28 Apr 2008 21:24:25 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2231163</guid>
		<description>&lt;strong&gt;Blern Most Popular...&lt;/strong&gt;

This post has reached the Top 10 Most Popular list of blog and news articles on Blern.com...</description>
		<content:encoded><![CDATA[<p><strong>Blern Most Popular&#8230;</strong></p>
<p>This post has reached the Top 10 Most Popular list of blog and news articles on Blern.com&#8230;</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: CRS</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2231162</link>
		<dc:creator>CRS</dc:creator>
		<pubDate>Mon, 28 Apr 2008 21:23:24 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2231162</guid>
		<description>It's a good paper!

Dealing with generic images is a very challenging research problem. I am glad to see that Google is finally making the move. To give a bit of history to this forum - IBM's QBIC system was one of the pioneer systems back in early 1990 that can do query by image contents. Since then, more than thousands of research papers were published mainly on computer vision, image processing, information retrievals, machine learning, and some database indexing. 

To my observation, there are some approaches that have some degree of success, but none can claim a true victory. Over the past decade, we do see many “specialized” image/media search engines that can search large-scale image/media databases in seconds with high accuracy. These media range from medical radiology images and satellite images to genomic sequences and protein 3D structure. 

Two examples of powerful search could be “given a new patient's medical image, find cases with similar pathology visually and their follow up treatments.” “given an unknown protein 3D structure, find structures that are locally similar to the unknown structure so that we can predict potential functions of the new structure.”</description>
		<content:encoded><![CDATA[<p>It&#8217;s a good paper!</p>
<p>Dealing with generic images is a very challenging research problem. I am glad to see that Google is finally making the move. To give a bit of history to this forum - IBM&#8217;s QBIC system was one of the pioneer systems back in early 1990 that can do query by image contents. Since then, more than thousands of research papers were published mainly on computer vision, image processing, information retrievals, machine learning, and some database indexing. </p>
<p>To my observation, there are some approaches that have some degree of success, but none can claim a true victory. Over the past decade, we do see many “specialized” image/media search engines that can search large-scale image/media databases in seconds with high accuracy. These media range from medical radiology images and satellite images to genomic sequences and protein 3D structure. </p>
<p>Two examples of powerful search could be “given a new patient&#8217;s medical image, find cases with similar pathology visually and their follow up treatments.” “given an unknown protein 3D structure, find structures that are locally similar to the unknown structure so that we can predict potential functions of the new structure.”</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: david saintloth</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2231115</link>
		<dc:creator>david saintloth</dc:creator>
		<pubDate>Mon, 28 Apr 2008 21:00:49 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2231115</guid>
		<description>Re. 18 by Sumanth

Sumanth, that is the very technology photosynth , thanks for finding the link!</description>
		<content:encoded><![CDATA[<p>Re. 18 by Sumanth</p>
<p>Sumanth, that is the very technology photosynth , thanks for finding the link!</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Google Experiments With Next Generation Image Search</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2231082</link>
		<dc:creator>Google Experiments With Next Generation Image Search</dc:creator>
		<pubDate>Mon, 28 Apr 2008 20:45:46 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2231082</guid>
		<description>[...] Tech Crunch Two Google scientists presented a paper(pdf embedded below) at the World Wide Web Conference in Beijing last week that outlines their vision for the future of image search. [...]</description>
		<content:encoded><![CDATA[<p>[...] Tech Crunch Two Google scientists presented a paper(pdf embedded below) at the World Wide Web Conference in Beijing last week that outlines their vision for the future of image search. [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: PageRank Para Pesquisas de Imagem &#124; Web 2.0 Brasil</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2231077</link>
		<dc:creator>PageRank Para Pesquisas de Imagem &#124; Web 2.0 Brasil</dc:creator>
		<pubDate>Mon, 28 Apr 2008 20:44:59 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2231077</guid>
		<description>[...] Techcrunch [...]</description>
		<content:encoded><![CDATA[<p>[...] Techcrunch [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: April 28, 2008 &#124; next media update</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2230859</link>
		<dc:creator>April 28, 2008 &#124; next media update</dc:creator>
		<pubDate>Mon, 28 Apr 2008 19:30:39 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2230859</guid>
		<description>[...] Google Experiments with Next Generation Image Search TECHCRUNCH Two Google scientists presented a paper at the World Wide Web Conference in Beijing last week that outlines their vision for the future of image search. Notably, the new image search technology doesn&#8217;t just index text associated with an image in determining what&#8217;s in it. Google is now talking about using computers to analyze the stuff in photos, and using that to associate it in a ranked way with keyword queries. In effect, they&#8217;re talking about something similar to PageRank for images (but without the linking behavior). Source&#62; [...]</description>
		<content:encoded><![CDATA[<p>[...] Google Experiments with Next Generation Image Search TECHCRUNCH Two Google scientists presented a paper at the World Wide Web Conference in Beijing last week that outlines their vision for the future of image search. Notably, the new image search technology doesn&#8217;t just index text associated with an image in determining what&#8217;s in it. Google is now talking about using computers to analyze the stuff in photos, and using that to associate it in a ranked way with keyword queries. In effect, they&#8217;re talking about something similar to PageRank for images (but without the linking behavior). Source&gt; [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: New Ranking Methodology for Google Image Search : Natural Search Blog</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2230815</link>
		<dc:creator>New Ranking Methodology for Google Image Search : Natural Search Blog</dc:creator>
		<pubDate>Mon, 28 Apr 2008 19:13:24 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2230815</guid>
		<description>[...] the International World Wide Web Conference in Beijing this past Thursday, and the process was also reported at [...]</description>
		<content:encoded><![CDATA[<p>[...] the International World Wide Web Conference in Beijing this past Thursday, and the process was also reported at [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Peter Rothman</title>
		<link>http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2230545</link>
		<dc:creator>Peter Rothman</dc:creator>
		<pubDate>Mon, 28 Apr 2008 17:53:49 +0000</pubDate>
		<guid isPermaLink="false">http://www.techcrunch.com/2008/04/27/google-experiments-with-next-generation-image-search/#comment-2230545</guid>
		<description>Very interesting paper.  This approach is quite similar to work we are doing with facial images.</description>
		<content:encoded><![CDATA[<p>Very interesting paper.  This approach is quite similar to work we are doing with facial images.</p>
]]></content:encoded>
	</item>
</channel>
</rss>

<!-- Dynamic Page Served (once) in 0.098 seconds -->
<!-- Cached page served by WP-Cache -->
