<?xml version="1.0" encoding="UTF-8"?>
 <rdf:RDF xmlns="http://purl.org/rss/1.0/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:cc="http://web.resource.org/cc/" xmlns:syn="http://purl.org/rss/1.0/modules/syndication/" xmlns:admin="http://webns.net/mvcb/">
  <channel rdf:about="http://pinboard.in">
    <title>Pinboard (Vaguery)</title>
    <link>https://pinboard.in/u:Vaguery/public/</link>
    <description>recent bookmarks from Vaguery</description>
    <items>
      <rdf:Seq>	<rdf:li rdf:resource="https://talk.objc.io/"/>
	<rdf:li rdf:resource="https://www.youtube.com/watch?v=5qNKolRwOkQ"/>
	<rdf:li rdf:resource="https://www.youtube.com/watch?v=NBdXCk58UxU"/>
	<rdf:li rdf:resource="https://www.youtube.com/user/Computerphile/videos"/>
	<rdf:li rdf:resource="https://owncast.online/about/"/>
	<rdf:li rdf:resource="https://www.youtube.com/channel/UCRvPS-dk5CHwUb090JJPQQQ"/>
	<rdf:li rdf:resource="https://www.youtube.com/watch?v=X83vac2uTUs"/>
	<rdf:li rdf:resource="https://www.jehsmith.com/1/2018/08/more-on-the-internet-of-snails.html"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1904.08755"/>
	<rdf:li rdf:resource="https://www.youtube.com/watch?v=I8LbkfSSR58"/>
	<rdf:li rdf:resource="https://developer.apple.com/videos/play/wwdc2019/718/"/>
	<rdf:li rdf:resource="https://shawnhesketh.com/create-screencasts/"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1804.09869"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1812.01717"/>
	<rdf:li rdf:resource="https://www.youtube.com/watch?v=Ic_5gRVTQ_k"/>
	<rdf:li rdf:resource="https://www.youtube.com/watch?v=K4ChzesrWKI&amp;list=PLPeStI124dee1ByfcDzRvPxKDNb0GQjmo"/>
	<rdf:li rdf:resource="https://www.youtube.com/channel/UCvp7jsbXjx2k8sGEkdtWCAw"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1704.08292"/>
	<rdf:li rdf:resource="https://vimeo.com/234305186"/>
	<rdf:li rdf:resource="https://www.youtube.com/user/numberphile"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1702.00824"/>
	<rdf:li rdf:resource="http://www.3quarksdaily.com/3quarksdaily/2017/02/the-nature-of-reality-a-dialogue-between-a-buddhist-scholar-alan-wallace-and-a-theoretical-physicist.html"/>
	<rdf:li rdf:resource="https://www.youtube.com/watch?v=Tcw7IvGJG9s"/>
	<rdf:li rdf:resource="https://www.youtube.com/watch?v=5q-BH-tvxEg"/>
	<rdf:li rdf:resource="https://www.youtube.com/watch?v=50-d_J0hKz0"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1612.08242"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1605.03718"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1605.03324"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1503.01224"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1502.05803"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1503.02727"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1503.00085"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1504.02518"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1405.7718"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1212.0935"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1506.08438"/>
	<rdf:li rdf:resource="https://vimeo.com/131823232"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1504.01942"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1412.1908"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1410.3744"/>
	<rdf:li rdf:resource="http://biorxiv.org/content/early/2014/11/07/011072"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1412.0439"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1403.7220"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1408.3526"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1403.0309"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1304.2999"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1402.6978"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1310.5541"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1401.4648"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1307.7306"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1309.6390"/>
	<rdf:li rdf:resource="http://vimeo.com/73444208"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1304.0869"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1303.2465"/>
	<rdf:li rdf:resource="http://arxiv.org/abs/1302.3446"/>
	<rdf:li rdf:resource="http://vimeo.com/17079380"/>
	<rdf:li rdf:resource="http://www.veer.com/ideas/our-fonts-our-friends/?vid6&amp;cid=em_1111_amr_1_font_all"/>
	<rdf:li rdf:resource="http://exilebibliophile.blogspot.com/2010/10/books-owning-them-loving-them.html"/>
	<rdf:li rdf:resource="http://net.tutsplus.com/articles/web-roundups/jquery-for-absolute-beginners-video-series/"/>
	<rdf:li rdf:resource="http://www.youtube.com/watch?v=uKfKtXYLG78"/>
	<rdf:li rdf:resource="http://www.groonk.net/blog/2011/05/watch-the-great-inception-charlie-chaplins-the-great-dictator-speech-mixed-with-hans-zimmers-inception-score/"/>
	<rdf:li rdf:resource="http://space1970.blogspot.com/2011/05/star-trek-animated-psa.html"/>
	<rdf:li rdf:resource="http://www.charlierose.com/view/interview/473"/>
	<rdf:li rdf:resource="http://www.telestream.net/screen-flow/overview.htm"/>
	<rdf:li rdf:resource="http://www.tor.com/blogs/2011/05/how-gaimans-q8in8q-is-exciting-the-sff-community?utm_source=Feedburner%3A+Frontpage+Partial+RSS+Feed&amp;utm_medium=feed&amp;utm_campaign=Feed%3A+Torcom%2FFrontpage_Partial+%28Tor.com+Frontpage+Partial+-+Blog+and+Stories%29"/>
	<rdf:li rdf:resource="http://gizmodo.com/5553765/are-cameras-the-new-guns"/>
	<rdf:li rdf:resource="http://www.clusterflock.org/2011/05/fifteen-uncoupled-simple-pendulums-of-monotonically-increasing-lengths-dance-together-to-produce-visual-traveling-waves-standing-waves-beating-and-seemingly-random-motion.html"/>
	<rdf:li rdf:resource="http://mashable.com/2010/03/26/non-profits-youtube/?utm_source=feedburner&amp;utm_medium=feed&amp;utm_campaign=Feed%3A+Mashable+(Mashable)"/>
	<rdf:li rdf:resource="http://www.funnyordie.co.uk/videos/0e4a1fa827/hitler-finds-out-about-another-downfall-parody?rel=player"/>
	<rdf:li rdf:resource="http://www.youtube.com/watch?v=9Q1gksqqhLU"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://talk.objc.io/">
    <title>Swift Talk - objc.io</title>
    <dc:date>2026-05-23T12:10:37+00:00</dc:date>
    <link>https://talk.objc.io/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Swift Talk
A weekly video series on Swift programming]]></description>
<dc:subject>swift programming-language software-development video to-watch training</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:1e2b9337fc8c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:swift"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:programming-language"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:software-development"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-watch"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:training"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.youtube.com/watch?v=5qNKolRwOkQ">
    <title>Lecture on Maximum Mean Discrepancy (MMD) - YouTube</title>
    <dc:date>2024-08-02T12:33:31+00:00</dc:date>
    <link>https://www.youtube.com/watch?v=5qNKolRwOkQ</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Lecture on MMD statistics for distribution comparisons.]]></description>
<dc:subject>statistics video lecture MMD discrepancy-theory distance metrics rather-interesting to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5adbd28f314d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:lecture"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:MMD"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:discrepancy-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:distance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.youtube.com/watch?v=NBdXCk58UxU">
    <title>How to do MultiCam in Zoom Meetings - YouTube</title>
    <dc:date>2021-05-19T11:25:41+00:00</dc:date>
    <link>https://www.youtube.com/watch?v=NBdXCk58UxU</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Trying to use two cameras in Zoom? This is a super-easy way to up your zoom meetings and do a MultiCamera setup. Using the tools built into Zoom.
]]></description>
<dc:subject>video web-meeting hardware how-to online-learning</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:77d54acbc2ba/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:web-meeting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hardware"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:how-to"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:online-learning"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.youtube.com/user/Computerphile/videos">
    <title>Computerphile - YouTube</title>
    <dc:date>2021-04-28T10:57:24+00:00</dc:date>
    <link>https://www.youtube.com/user/Computerphile/videos</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Computerphile]]></description>
<dc:subject>computer-science video to-watch rather-good</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:dabfbf84c220/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computer-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-watch"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-good"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://owncast.online/about/">
    <title>About | Owncast</title>
    <dc:date>2021-01-13T20:27:37+00:00</dc:date>
    <link>https://owncast.online/about/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In 2020 the world changed when everyone become stuck in their homes, looking for creative outlets to share their art, skills and themselves from inside their bedroom.

This created an explosion of live streaming on Facebook Live, YouTube Live, Instagram, and Twitch. These services provided everything they needed, an easy way to live stream to the world, and a chat for users to be a part of their community.

]]></description>
<dc:subject>federation open-source video streaming to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:61fa5c0894a1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:federation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:open-source"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:streaming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.youtube.com/channel/UCRvPS-dk5CHwUb090JJPQQQ">
    <title>Oregon State University - School of Writing, Literature and Film - YouTube</title>
    <dc:date>2020-09-18T21:24:23+00:00</dc:date>
    <link>https://www.youtube.com/channel/UCRvPS-dk5CHwUb090JJPQQQ</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[This Oregon State Guide to English Literary Terms provides students and teachers with free lessons on common literary devices. For a full transcript of each video and additional teaching resources for the literary terms we discuss, please visit the following site: https://liberalarts.oregonstate.edu/wlf/oregon-state-guide-english-literary-terms For dual language learning, we have begun to include Spanish as well as English subtitles for our videos. Our current dual-language videos are metaphor, hyperbole, satire, personification, figurative language, juxtaposition, genre, sonnet, stream of consciousness, irony, stanza, and imagery. If we can secure more funding for the translations, we'll add more. To assist literature teachers and students during the COVID-19 pandemic, we'll be posting more videos throughout 2020, so please subscribe to the channel to stay current with this project and like or comment on our videos to keep the conversation going!
]]></description>
<dc:subject>video pedagogy humanities short-definitions rather-interesting to-watch have-shared</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d9c906fb8b58/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:pedagogy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:humanities"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:short-definitions"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-watch"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:have-shared"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.youtube.com/watch?v=X83vac2uTUs">
    <title>Extraordinary Conics: The Most Difficult Math Problem I Ever Solved - YouTube</title>
    <dc:date>2020-07-07T10:37:00+00:00</dc:date>
    <link>https://www.youtube.com/watch?v=X83vac2uTUs</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[This is a real math problem I faced, and the process I went through to solve it.  Despite being a difficult problem, I tried to focus on the beautiful visuals and interesting discoveries I made about conic sections that I doubt anyone knows about.  While this isn't my typical style of video, there was a ton of coding that went into this (all open source) and an interactive app of this entire video.  Check them out below!
]]></description>
<dc:subject>mathematical-programming video mathematical-recreations rather-interesting on-several-levels to-try</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5700804fe968/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:mathematical-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:mathematical-recreations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:on-several-levels"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-try"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.jehsmith.com/1/2018/08/more-on-the-internet-of-snails.html">
    <title>More on the Internet of Snails - Justin Erik Halldór Smith</title>
    <dc:date>2020-03-19T15:57:42+00:00</dc:date>
    <link>https://www.jehsmith.com/1/2018/08/more-on-the-internet-of-snails.html</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[This is a talk I gave last year in Marseille, under circumstances that, to be honest, I'm still not sure I understand. You'll notice anyhow that the production values are unusually high. 

]]></description>
<dc:subject>philosophy philosophy-of-engineering to-watch video</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f99d9311b9b2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy-of-engineering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-watch"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1904.08755">
    <title>[1904.08755] 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks</title>
    <dc:date>2019-12-25T16:50:09+00:00</dc:date>
    <link>https://arxiv.org/abs/1904.08755</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In many robotics and VR/AR applications, 3D-videos are readily-available sources of input (a continuous sequence of depth images, or LIDAR scans). However, those 3D-videos are processed frame-by-frame either through 2D convnets or 3D perception algorithms. In this work, we propose 4-dimensional convolutional neural networks for spatio-temporal perception that can directly process such 3D-videos using high-dimensional convolutions. For this, we adopt sparse tensors and propose the generalized sparse convolution that encompasses all discrete convolutions. To implement the generalized sparse convolution, we create an open-source auto-differentiation library for sparse tensors that provides extensive functions for high-dimensional convolutional neural networks. We create 4D spatio-temporal convolutional neural networks using the library and validate them on various 3D semantic segmentation benchmarks and proposed 4D datasets for 3D-video perception. To overcome challenges in the 4D space, we propose the hybrid kernel, a special case of the generalized sparse convolution, and the trilateral-stationary conditional random field that enforces spatio-temporal consistency in the 7D space-time-chroma space. Experimentally, we show that convolutional neural networks with only generalized 3D sparse convolutions can outperform 2D or 2D-3D hybrid methods by a large margin. Also, we show that on 3D-videos, 4D spatio-temporal convolutional neural networks are robust to noise, outperform 3D convolutional neural networks and are faster than the 3D counterpart in some cases.
]]></description>
<dc:subject>image-processing video deep-learning representation time-series neural-networks to-write-about consider:genetic-programming consider:subsetting</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:07a50c05c722/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:genetic-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:subsetting"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.youtube.com/watch?v=I8LbkfSSR58">
    <title>Category Theory 1.1: Motivation and Philosophy - YouTube</title>
    <dc:date>2019-12-06T13:11:32+00:00</dc:date>
    <link>https://www.youtube.com/watch?v=I8LbkfSSR58</link>
    <dc:creator>Vaguery</dc:creator><dc:subject>category-theory video lectures to-watch maybe?</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b1faff1931f7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:category-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:lectures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-watch"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:maybe?"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://developer.apple.com/videos/play/wwdc2019/718/">
    <title>Introducing Accelerate for Swift - WWDC 2019 - Videos - Apple Developer</title>
    <dc:date>2019-11-03T19:56:38+00:00</dc:date>
    <link>https://developer.apple.com/videos/play/wwdc2019/718/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Introducing Accelerate for Swift
Accelerate framework provides hundreds of computational functions that are highly optimized to the system architecture your device is running on. Learn how to access all of these powerful functions directly in Swift. Understand how the power of vector programming can deliver incredible performance to your iOS, macOS, tvOS, and watchOS apps.
]]></description>
<dc:subject>swift library hardware-acceleration API to-understand to-use introduction video WWDC</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:084dbf9d1ce4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:swift"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:library"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hardware-acceleration"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:API"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-use"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:introduction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:WWDC"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://shawnhesketh.com/create-screencasts/">
    <title>How to Create Screencasts That Don't Suck - Shawn Hesketh</title>
    <dc:date>2019-04-06T15:10:57+00:00</dc:date>
    <link>https://shawnhesketh.com/create-screencasts/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Anyone can record a video of their screen and upload it to YouTube. But creating a compelling, high-quality screencast that people will actually watch and share… well, that’s a bit more challenging.

]]></description>
<dc:subject>screencasting video production engineering-tips to-read</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:99f108e3cca1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:screencasting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:production"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:engineering-tips"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-read"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1804.09869">
    <title>[1804.09869] Learning for Video Compression</title>
    <dc:date>2019-02-05T10:18:19+00:00</dc:date>
    <link>https://arxiv.org/abs/1804.09869</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[One key challenge to learning-based video compression is that motion predictive coding, a very effective tool for video compression, can hardly be trained into a neural network. In this paper we propose the concept of PixelMotionCNN (PMCNN) which includes motion extension and hybrid prediction networks. PMCNN can model spatiotemporal coherence to effectively perform predictive coding inside the learning network. On the basis of PMCNN, we further explore a learning-based framework for video compression with additional components of iterative analysis/synthesis, binarization, etc. Experimental results demonstrate the effectiveness of the proposed scheme. Although entropy coding and complex configurations are not employed in this paper, we still demonstrate superior performance compared with MPEG-2 and achieve comparable results with H.264 codec. The proposed learning-based scheme provides a possible new direction to further improve compression efficiency and functionalities of future video coding.
]]></description>
<dc:subject>video compression algorithms neural-networks models-as-compressed-forms representation consider:looking-to-see</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:97f50844f5bd/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:compression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models-as-compressed-forms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1812.01717">
    <title>[1812.01717] Towards Accurate Generative Models of Video: A New Metric &amp; Challenges</title>
    <dc:date>2018-12-09T11:58:09+00:00</dc:date>
    <link>https://arxiv.org/abs/1812.01717</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Recent advances in deep generative models have lead to remarkable progress in synthesizing high quality images. Following their successful application in image processing and representation learning, an important next step is to consider videos. Learning generative models of video is a much harder task, requiring a model to capture the temporal dynamics of a scene, in addition to the visual presentation of objects. Although recent attempts at formulating generative models of video have had some success, current progress is hampered by (1) the lack of qualitative metrics that consider visual quality, temporal coherence, and diversity of samples, and (2) the wide gap between purely synthetic video datasets and challenging real-world datasets in terms of complexity. To this extent we propose Fréchet Video Distance (FVD), a new metric for generative models of video based on FID, and StarCraft 2 Videos (SCV), a collection of progressively harder datasets that challenge the capabilities of the current iteration of generative models for video. We conduct a large-scale human study, which confirms that FVD correlates well with qualitative human judgment of generated videos, and provide initial benchmark results on SCV.
]]></description>
<dc:subject>metrics Frechet-distance generative-models representation rather-interesting video feature-construction to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:50eb14546576/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metrics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:Frechet-distance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generative-models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.youtube.com/watch?v=Ic_5gRVTQ_k">
    <title>&quot;Mapping Imaginary Cities&quot; by Mouse Reeve - YouTube</title>
    <dc:date>2018-12-09T11:54:22+00:00</dc:date>
    <link>https://www.youtube.com/watch?v=Ic_5gRVTQ_k</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[While the map is not the territory (to quote the semantician Alfred Korzybski), the map is still usually intended to correspond to one. But what about maps of nowhere at all? What can they represent and how can they be made?

Maps are a familiar part of daily life, with a deeply familiar and complex symbolic language, and a long history. They are also hugely varied in style and aesthetic, and often are works of art unto themselves. All this makes mapping a powerful creative tool for conveying ideas about a space, how it is used, and who inhabits it. But it also presents a mapmaker with what can feel like an overwhelming array of design choices and technical hurdles to overcome in order to create a generative map.

This talk will explore maps as a way to communicate about people and place in the context of fictional cities, and dive into algorithms and techniques for procedurally generating maps by building up topography, landscape, populations, and street plans.
Maps are a familiar part of daily life, with a deeply familiar and complex symbolic language, and a long history. They are also hugely varied in style and aesthetic, and often are works of art unto themselves. All this makes mapping a powerful creative tool for conveying ideas about a space, how it is used, and who inhabits it. But it also presents a mapmaker with what can feel like an overwhelming array of design choices and technical hurdles to overcome in order to create a generative map.

This talk will explore maps as a way to communicate about people and place in the context of fictional cities, and dive into algorithms and techniques for procedurally generating maps by building up topography, landscape, populations, and street plans.]]></description>
<dc:subject>video cartography strange-loop rather-interesting art generative-art generative-models the-mangle-in-practice learning-in-public algorithms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:4807d5a5897b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cartography"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:strange-loop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:art"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generative-art"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generative-models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:the-mangle-in-practice"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:learning-in-public"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.youtube.com/watch?v=K4ChzesrWKI&amp;list=PLPeStI124dee1ByfcDzRvPxKDNb0GQjmo">
    <title>Chapter 1.1: Introduction to logic - YouTube</title>
    <dc:date>2018-03-02T14:05:15+00:00</dc:date>
    <link>https://www.youtube.com/watch?v=K4ChzesrWKI&amp;list=PLPeStI124dee1ByfcDzRvPxKDNb0GQjmo</link>
    <dc:creator>Vaguery</dc:creator><dc:subject>philosophy lectures video to-watch</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d3feb33ca1de/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:lectures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-watch"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.youtube.com/channel/UCvp7jsbXjx2k8sGEkdtWCAw">
    <title>London Mathematical Society - YouTube - YouTube</title>
    <dc:date>2017-10-15T16:00:17+00:00</dc:date>
    <link>https://www.youtube.com/channel/UCvp7jsbXjx2k8sGEkdtWCAw</link>
    <dc:creator>Vaguery</dc:creator><dc:subject>video mathematics lectures to-watch</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:52c3416cc262/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:mathematics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:lectures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-watch"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1704.08292">
    <title>[1704.08292] Deep Cross-Modal Audio-Visual Generation</title>
    <dc:date>2017-10-11T00:39:22+00:00</dc:date>
    <link>https://arxiv.org/abs/1704.08292</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Cross-modal audio-visual perception has been a long-lasting topic in psychology and neurology, and various studies have discovered strong correlations in human perception of auditory and visual stimuli. Despite works in computational multimodal modeling, the problem of cross-modal audio-visual generation has not been systematically studied in the literature. In this paper, we make the first attempt to solve this cross-modal generation problem leveraging the power of deep generative adversarial training. Specifically, we use conditional generative adversarial networks to achieve cross-modal audio-visual generation of musical performances. We explore different encoding methods for audio and visual signals, and work on two scenarios: instrument-oriented generation and pose-oriented generation. Being the first to explore this new problem, we compose two new datasets with pairs of images and sounds of musical performances of different instruments. Our experiments using both classification and human evaluations demonstrate that our model has the ability to generate one modality, i.e., audio/visual, from the other modality, i.e., visual/audio, to a good extent. Our experiments on various design choices along with the datasets will facilitate future research in this new problem space.
]]></description>
<dc:subject>deep-learning neural-networks generative-art generative-models rather-interesting video computer-vision nudge-targets consider:rediscovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:7f7b50824ff2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generative-art"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generative-models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computer-vision"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:rediscovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://vimeo.com/234305186">
    <title>Foreplay keynote - Aral Balkan on Vimeo</title>
    <dc:date>2017-09-25T12:04:44+00:00</dc:date>
    <link>https://vimeo.com/234305186</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Foreplay keynote - Aral Balkan]]></description>
<dc:subject>security corporatism openness public-policy video keynote</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a1822ee229f1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:security"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:corporatism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:openness"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:public-policy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:keynote"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.youtube.com/user/numberphile">
    <title>Numberphile - YouTube</title>
    <dc:date>2017-09-25T12:02:34+00:00</dc:date>
    <link>https://www.youtube.com/user/numberphile</link>
    <dc:creator>Vaguery</dc:creator><dc:subject>video mathematical-recreations have-subscribed mathematics learning-by-watching rather-interesting</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b65b6c5318c5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:mathematical-recreations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:have-subscribed"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:mathematics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:learning-by-watching"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1702.00824">
    <title>[1702.00824] YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video</title>
    <dc:date>2017-05-07T11:52:27+00:00</dc:date>
    <link>https://arxiv.org/abs/1702.00824</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We introduce a new large-scale data set of video URLs with densely-sampled object bounding box annotations called YouTube-BoundingBoxes (YT-BB). The data set consists of approximately 380,000 video segments about 19s long, automatically selected to feature objects in natural settings without editing or post-processing, with a recording quality often akin to that of a hand-held cell phone camera. The objects represent a subset of the MS COCO label set. All video segments were human-annotated with high-precision classification labels and bounding boxes at 1 frame per second. The use of a cascade of increasingly precise human annotations ensures a label accuracy above 95% for every class and tight bounding boxes. Finally, we train and evaluate well-known deep network architectures and report baseline figures for per-frame classification and localization to provide a point of comparison for future work. We also demonstrate how the temporal contiguity of video can potentially be used to improve such inferences. Please see the PDF file to find the URL to download the data. We hope the availability of such large curated corpus will spur new advances in video object detection and tracking.
]]></description>
<dc:subject>training-data machine-learning video image-processing dataset supervised-learning</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a11f1fac8cf8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:training-data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:dataset"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:supervised-learning"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.3quarksdaily.com/3quarksdaily/2017/02/the-nature-of-reality-a-dialogue-between-a-buddhist-scholar-alan-wallace-and-a-theoretical-physicist.html">
    <title>3quarksdaily: The Nature of Reality: A Dialogue Between a Buddhist Scholar (Alan Wallace) and a Theoretical Physicist (Sean Carroll)</title>
    <dc:date>2017-02-24T14:54:40+00:00</dc:date>
    <link>http://www.3quarksdaily.com/3quarksdaily/2017/02/the-nature-of-reality-a-dialogue-between-a-buddhist-scholar-alan-wallace-and-a-theoretical-physicist.html</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[THE NATURE OF REALITY: A DIALOGUE BETWEEN A BUDDHIST SCHOLAR (ALAN WALLACE) AND A THEORETICAL PHYSICIST (SEAN CARROLL)

]]></description>
<dc:subject>philosophy philosophy-of-science conversation video</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a0f698b93822/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy-of-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:conversation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.youtube.com/watch?v=Tcw7IvGJG9s">
    <title>Machine with Roller Chain - Arthur Ganson - YouTube</title>
    <dc:date>2017-02-16T14:31:34+00:00</dc:date>
    <link>https://www.youtube.com/watch?v=Tcw7IvGJG9s</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A simple exploration of the organic nature and complexity of roller chain. The shapes and patterns most likely will never repeat. Often, heavy industrial materials have a 'softer side' that is not revealed if they are used only as intended.
]]></description>
<dc:subject>conceptual-art mechanics engineering-design art video</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:fbac14cea995/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:conceptual-art"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:mechanics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:engineering-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:art"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.youtube.com/watch?v=5q-BH-tvxEg">
    <title>Machine with Concrete - Arthur Ganson - YouTube</title>
    <dc:date>2017-02-16T14:30:09+00:00</dc:date>
    <link>https://www.youtube.com/watch?v=5q-BH-tvxEg</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[This machine was inspired by dreaming about gear ratios and considering the unexpected implications of exponential powers.

Each worm/worm gear pair reduces the speed of the motor by 1/50th. Since there are 12 pairs of gears, the final speed reduction is calculated by (1/50)12. The implications are quite large. With the motor turning around 200 revolutions per minute, it will take well over two trillion years before the final gear makes but one turn. Given the truth of this situation, it is possible to do anything at all with the final gear, even embed it in concrete.
]]></description>
<dc:subject>conceptual-art video engineering-design amusing via:ronjeffries mechanics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:c02f23fa0750/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:conceptual-art"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:engineering-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:amusing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:ronjeffries"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:mechanics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.youtube.com/watch?v=50-d_J0hKz0">
    <title>Manuel Delanda, &quot;Deleuze and the Use of the Genetic Algorithm in Architecture&quot; - YouTube</title>
    <dc:date>2017-02-12T14:32:11+00:00</dc:date>
    <link>https://www.youtube.com/watch?v=50-d_J0hKz0</link>
    <dc:creator>Vaguery</dc:creator><dc:subject>philosophy generative-art philosophy-of-engineering lecture video</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:61b176341454/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generative-art"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:philosophy-of-engineering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:lecture"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1612.08242">
    <title>[1612.08242] YOLO9000: Better, Faster, Stronger</title>
    <dc:date>2017-02-07T11:49:30+00:00</dc:date>
    <link>https://arxiv.org/abs/1612.08242</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We introduce YOLO9000, a state-of-the-art, real-time object detection system that can detect over 9000 object categories. First we propose various improvements to the YOLO detection method, both novel and drawn from prior work. The improved model, YOLOv2, is state-of-the-art on standard detection tasks like PASCAL VOC and COCO. At 67 FPS, YOLOv2 gets 76.8 mAP on VOC 2007. At 40 FPS, YOLOv2 gets 78.6 mAP, outperforming state-of-the-art methods like Faster RCNN with ResNet and SSD while still running significantly faster. Finally we propose a method to jointly train on object detection and classification. Using this method we train YOLO9000 simultaneously on the COCO detection dataset and the ImageNet classification dataset. Our joint training allows YOLO9000 to predict detections for object classes that don't have labelled detection data. We validate our approach on the ImageNet detection task. YOLO9000 gets 19.7 mAP on the ImageNet detection validation set despite only having detection data for 44 of the 200 classes. On the 156 classes not in COCO, YOLO9000 gets 16.0 mAP. But YOLO can detect more than just 200 classes; it predicts detections for more than 9000 different object categories. And it still runs in real-time.
]]></description>
<dc:subject>deep-learning horse-races machine-learning image-segmentation image-analysis video nudge-targets consider:feature-discovery consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:9f322773f0c7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:horse-races"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-segmentation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1605.03718">
    <title>[1605.03718] Improved Image Boundaries for Better Video Segmentation</title>
    <dc:date>2016-07-04T00:34:35+00:00</dc:date>
    <link>http://arxiv.org/abs/1605.03718</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Graph-based video segmentation methods rely on superpixels as starting point. While most previous work has focused on the construction of the graph edges and weights as well as solving the graph partitioning problem, this paper focuses on better superpixels for video segmentation. We demonstrate by a comparative analysis that superpixels extracted from boundaries perform best, and show that boundary estimation can be significantly improved via image and time domain cues. With superpixels generated from our better boundaries we observe consistent improvement for two video segmentation methods in two different datasets.
]]></description>
<dc:subject>image-processing algorithms image-segmentation video nudge-targets consider:representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:2d60ba10fbf8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-segmentation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1605.03324">
    <title>[1605.03324] Unsupervised Semantic Action Discovery from Video Collections</title>
    <dc:date>2016-05-14T13:15:30+00:00</dc:date>
    <link>http://arxiv.org/abs/1605.03324</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Human communication takes many forms, including speech, text and instructional videos. It typically has an underlying structure, with a starting point, ending, and certain objective steps between them. In this paper, we consider instructional videos where there are tens of millions of them on the Internet. 
We propose a method for parsing a video into such semantic steps in an unsupervised way. Our method is capable of providing a semantic "storyline" of the video composed of its objective steps. We accomplish this using both visual and language cues in a joint generative model. Our method can also provide a textual description for each of the identified semantic steps and video segments. We evaluate our method on a large number of complex YouTube videos and show that our method discovers semantically correct instructions for a variety of tasks.
]]></description>
<dc:subject>video image-processing deep-learning image-segmentation image-analysis search-engines algorithms nudge-targets machine-learning</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:589abf310a54/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-segmentation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:search-engines"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1503.01224">
    <title>[1503.01224] Temporal Pyramid Pooling Based Convolutional Neural Networks for Action Recognition</title>
    <dc:date>2015-11-24T11:41:31+00:00</dc:date>
    <link>http://arxiv.org/abs/1503.01224</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Encouraged by the success of Convolutional Neural Networks (CNNs) in image classification, recently much effort is spent on applying CNNs to video based action recognition problems. One challenge is that video contains a varying number of frames which is incompatible to the standard input format of CNNs. Existing methods handle this issue either by directly sampling a fixed number of frames or bypassing this issue by introducing a 3D convolutional layer which conducts convolution in spatial-temporal domain. 
To solve this issue, here we propose a novel network structure which allows an arbitrary number of frames as the network input. The key of our solution is to introduce a module consisting of an encoding layer and a temporal pyramid pooling layer. The encoding layer maps the activation from previous layers to a feature vector suitable for pooling while the temporal pyramid pooling layer converts multiple frame-level activations into a fixed-length video-level representation. In addition, we adopt a feature concatenation layer which combines appearance information and motion information. Compared with the frame sampling strategy, our method avoids the risk of missing any important frames. Compared with the 3D convolutional method which requires a huge video dataset for network training, our model can be learned on a small target dataset because we can leverage the off-the-shelf image-level CNN for model parameter initialization. Experiments on two challenging datasets, Hollywood2 and HMDB51, demonstrate that our method achieves superior performance over state-of-the-art methods while requiring much fewer training data.
]]></description>
<dc:subject>computer-vision image-processing video deep-learning algorithms classification nudge-targets artificial-intelligence</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:813e2fc7207f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computer-vision"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:classification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:artificial-intelligence"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1502.05803">
    <title>[1502.05803] Visual object tracking performance measures revisited</title>
    <dc:date>2015-11-13T14:20:26+00:00</dc:date>
    <link>http://arxiv.org/abs/1502.05803</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The problem of visual tracking evaluation is sporting a large variety of performance measures, and largely suffers from lack of consensus about which measures should be used in experiments. This makes the cross-paper tracker comparison difficult. Furthermore, as some measures may be less effective than others, the tracking results may be skewed or biased towards particular tracking aspects. In this paper we revisit the popular performance measures and tracker performance visualizations and analyze them theoretically and experimentally. We show that several measures are equivalent from the point of information they provide for tracker comparison and, crucially, that some are more brittle than the others. Based on our analysis we narrow down the set of potential measures to only two complementary ones, describing accuracy and robustness, thus pushing towards homogenization of the tracker evaluation methodology. These two measures can be intuitively interpreted and visualized and have been employed by the recent Visual Object Tracking (VOT) challenges as the foundation for the evaluation methodology.
]]></description>
<dc:subject>image-processing video object-tracking performance-measure horse-races nudge-targets rather-interesting consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f6ff68f9fd8b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:object-tracking"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:horse-races"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1503.02727">
    <title>[1503.02727] Video Compressive Sensing for Spatial Multiplexing Cameras using Motion-Flow Models</title>
    <dc:date>2015-11-11T12:07:18+00:00</dc:date>
    <link>http://arxiv.org/abs/1503.02727</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Spatial multiplexing cameras (SMCs) acquire a (typically static) scene through a series of coded projections using a spatial light modulator (e.g., a digital micro-mirror device) and a few optical sensors. This approach finds use in imaging applications where full-frame sensors are either too expensive (e.g., for short-wave infrared wavelengths) or unavailable. Existing SMC systems reconstruct static scenes using techniques from compressive sensing (CS). For videos, however, existing acquisition and recovery methods deliver poor quality. In this paper, we propose the CS multi-scale video (CS-MUVI) sensing and recovery framework for high-quality video acquisition and recovery using SMCs. Our framework features novel sensing matrices that enable the efficient computation of a low-resolution video preview, while enabling high-resolution video recovery using convex optimization. To further improve the quality of the reconstructed videos, we extract optical-flow estimates from the low-resolution previews and impose them as constraints in the recovery procedure. We demonstrate the efficacy of our CS-MUVI framework for a host of synthetic and real measured SMC video data, and we show that high-quality videos can be recovered at roughly 60× compression.
]]></description>
<dc:subject>video image-processing compressed-sensing rather-interesting representation approximation nudge-targets consider:representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:feeced05a5b4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:compressed-sensing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1503.00085">
    <title>[1503.00085] A Fast Sub-Pixel Motion Estimation Algorithm for H.264/AVC Video Coding</title>
    <dc:date>2015-11-01T13:27:06+00:00</dc:date>
    <link>http://arxiv.org/abs/1503.00085</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Motion Estimation (ME) is one of the most time-consuming parts in video coding. The use of multiple partition sizes in H.264/AVC makes it even more complicated when compared to ME in conventional video coding standards. It is important to develop fast and effective sub-pixel ME algorithms since (a) The computation overhead by sub-pixel ME has become relatively significant while the complexity of integer-pixel search has been greatly reduced by fast algorithms, and (b) Reducing sub-pixel search points can greatly save the computation for sub-pixel interpolation. In this paper, a novel fast sub-pixel ME algorithm is proposed which performs a 'rough' sub-pixel search before the partition selection, and performs a 'precise' sub-pixel search for the best partition. By reducing the searching load for the large number of non-best partitions, the computation complexity for sub-pixel search can be greatly decreased. Experimental results show that our method can reduce the sub-pixel search points by more than 50% compared to existing fast sub-pixel ME methods with negligible quality degradation.
]]></description>
<dc:subject>video algorithms computational-complexity horse-races performance-measure nudge-targets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:e192fcfd7a75/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computational-complexity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:horse-races"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1504.02518">
    <title>[1504.02518] Unsupervised Feature Learning from Temporal Data</title>
    <dc:date>2015-09-05T17:30:45+00:00</dc:date>
    <link>http://arxiv.org/abs/1504.02518</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Current state-of-the-art classification and detection algorithms rely on supervised training. In this work we study unsupervised feature learning in the context of temporally coherent video data. We focus on feature learning from unlabeled video data, using the assumption that adjacent video frames contain semantically similar information. This assumption is exploited to train a convolutional pooling auto-encoder regularized by slowness and sparsity. We establish a connection between slow feature learning to metric learning and show that the trained encoder can be used to define a more temporally and semantically coherent metric.
]]></description>
<dc:subject>unsupervised-learning online-learning feature-extraction video image-processing rather-interesting algorithms machine-learning nudge-targets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:fda15bb3bc6f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:unsupervised-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:online-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-extraction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1405.7718">
    <title>[1405.7718] Deformation corrected compressed sensing (DC-CS): a novel framework for accelerated dynamic MRI</title>
    <dc:date>2015-08-23T10:46:36+00:00</dc:date>
    <link>http://arxiv.org/abs/1405.7718</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We propose a novel deformation corrected compressed sensing (DC-CS) framework to recover dynamic magnetic resonance images from undersampled measurements. We introduce a generalized formulation that is capable of handling a wide class of sparsity/compactness priors on the deformation corrected dynamic signal. In this work, we consider example compactness priors such as sparsity in temporal Fourier domain, sparsity in temporal finite difference domain, and nuclear norm penalty to exploit low rank structure. Using variable splitting, we decouple the complex optimization problem to simpler and well understood sub problems; the resulting algorithm alternates between simple steps of shrinkage based denoising, deformable registration, and a quadratic optimization step. Additionally, we employ efficient continuation strategies to minimize the risk of convergence to local minima. The proposed formulation contrasts with existing DC-CS schemes that are customized for free breathing cardiac cine applications, and other schemes that rely on fully sampled reference frames or navigator signals to estimate the deformation parameters. The efficient decoupling enabled by the proposed scheme allows its application to a wide range of applications including contrast enhanced dynamic MRI. Through experiments on numerical phantom and in vivo myocardial perfusion MRI datasets, we demonstrate the utility of the proposed DC-CS scheme in providing robust reconstructions with reduced motion artifacts over classical compressed sensing schemes that utilize the compact priors on the original deformation un-corrected signal.
]]></description>
<dc:subject>compressed-sensing inference tomography statistics algorithms video nudge-targets consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:3e5b6f55fd5a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:compressed-sensing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:tomography"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1212.0935">
    <title>[1212.0935] Computing Consensus Curves</title>
    <dc:date>2015-07-26T12:35:52+00:00</dc:date>
    <link>http://arxiv.org/abs/1212.0935</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We consider the problem of extracting accurate average ant trajectories from many (possibly inaccurate) input trajectories contributed by citizen scientists. Although there are many generic software tools for motion tracking and specific ones for insect tracking, even untrained humans are much better at this task, provided a robust method to computing the average trajectories. We implemented and tested several local (one ant at a time) and global (all ants together) method. Our best performing algorithm uses a novel global method, based on finding edge-disjoint paths in an ant-interaction graph constructed from the input trajectories. The underlying optimization problem is a new and interesting variant of network flow. Even though the problem is NP-hard, we implemented two heuristics, which work very well in practice, outperforming all other approaches, including the best automated system.
]]></description>
<dc:subject>computational-geometry video image-processing inference rather-interesting approximation pattern-discovery nudge-targets algorithms ants</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:652a883fa09b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computational-geometry"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:pattern-discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:ants"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1506.08438">
    <title>[1506.08438] Unsupervised Semantic Parsing of Video Collections</title>
    <dc:date>2015-07-13T11:25:40+00:00</dc:date>
    <link>http://arxiv.org/abs/1506.08438</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Human communication typically has an underlying structure. This is reflected in the fact that in many user generated videos, a starting point, ending, and certain objective steps between these two can be identified. In this paper, we propose a method for parsing a video into such semantic steps in an unsupervised way. The proposed method is capable of providing a semantic "storyline" of the video composed of its objective steps. We accomplish this using both visual and language cues in a joint generative model. The proposed method can also provide a textual description for each of the identified semantic steps and video segments. We evaluate this method on a large number of complex YouTube videos and show results of unprecedented quality for this intricate and impactful problem.
]]></description>
<dc:subject>unsupervised-learning clustering video image-processing semantic-web machine-learning algorithms nudge-targets rather-interesting</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:4004cfb4104c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:unsupervised-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:semantic-web"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://vimeo.com/131823232">
    <title>AADRL Spyropoulos Design Lab on Vimeo</title>
    <dc:date>2015-06-27T14:32:14+00:00</dc:date>
    <link>https://vimeo.com/131823232</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA["Research from the AADRL Spyropoulos Design Lab exploring an architecture that is self-aware, self-structured and self-assembles. The research explores high population of mobility agents that evolve an architecture that moves beyond the fixed and finite towards a behavioural model of interactive human and machine ecologies."]]></description>
<dc:subject>theodorespyropoulos 2015 architecture self-assembling self-aware robotics video via:robertogreco self-organization emergent-design biological-engineering</dc:subject>
<dc:identifier>https://pinboard.in/u:Vaguery/b:7ee083454fda/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:theodorespyropoulos"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:2015"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:architecture"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:self-assembling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:self-aware"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:robotics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:robertogreco"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:self-organization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:emergent-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:biological-engineering"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1504.01942">
    <title>[1504.01942] MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking</title>
    <dc:date>2015-04-10T14:48:00+00:00</dc:date>
    <link>http://arxiv.org/abs/1504.01942</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In the recent past, the computer vision community has developed centralized benchmarks for the performance evaluation of a variety of tasks, including generic object and pedestrian detection, 3D reconstruction, optical flow, single-object short-term tracking, and stereo estimation. Despite potential pitfalls of such benchmarks, they have proved to be extremely helpful to advance the state of the art in the respective area. Interestingly, there has been rather limited work on the standardization of quantitative benchmarks for multiple target tracking. One of the few exceptions is the well-known PETS dataset, targeted primarily at surveillance applications. Despite being widely used, it is often applied inconsistently, for example involving using different subsets of the available data, different ways of training the models, or differing evaluation scripts. This paper describes our work toward a novel multiple object tracking benchmark aimed to address such issues. We discuss the challenges of creating such a framework, collecting existing and new data, gathering state-of-the-art methods to be tested on the datasets, and finally creating a unified evaluation system. With MOTChallenge we aim to pave the way toward a unified evaluation framework for a more meaningful quantification of multi-target tracking.
]]></description>
<dc:subject>video image-processing image-segmentation machine-learning challenge nudge-targets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:1e7f1321d17b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-segmentation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:challenge"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1412.1908">
    <title>[1412.1908] Person Re-identification by Saliency Learning</title>
    <dc:date>2015-02-01T12:57:29+00:00</dc:date>
    <link>http://arxiv.org/abs/1412.1908</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Human eyes can recognize person identities based on small salient regions, i.e. human saliency is distinctive and reliable in pedestrian matching across disjoint camera views. However, such valuable information is often hidden when computing similarities of pedestrian images with existing approaches. Inspired by our user study result of human perception on human saliency, we propose a novel perspective for person re-identification based on learning human saliency and matching saliency distribution. The proposed saliency learning and matching framework consists of four steps: (1) To handle misalignment caused by drastic viewpoint change and pose variations, we apply adjacency constrained patch matching to build dense correspondence between image pairs. (2) We propose two alternative methods, i.e. K-Nearest Neighbors and One-class SVM, to estimate a saliency score for each image patch, through which distinctive features stand out without using identity labels in the training procedure. (3) saliency matching is proposed based on patch matching. Matching patches with inconsistent saliency brings penalty, and images of the same identity are recognized by minimizing the saliency matching cost. (4) Furthermore, saliency matching is tightly integrated with patch matching in a unified structural RankSVM learning framework. The effectiveness of our approach is validated on the VIPeR dataset and the CUHK01 dataset. Our approach outperforms the state-of-the-art person re-identification methods on both datasets.
]]></description>
<dc:subject>image-segmentation image-analysis video saliency deep-learning algorithms machine-learning nudge-targets SMH-at-people-who-always-use-linear-algebra-JEEZ</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d4f4a5340afb/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-segmentation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:saliency"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:SMH-at-people-who-always-use-linear-algebra-JEEZ"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1410.3744">
    <title>[1410.3744] Refined Particle Swarm Intelligence Method for Abrupt Motion Tracking</title>
    <dc:date>2014-12-21T14:57:57+00:00</dc:date>
    <link>http://arxiv.org/abs/1410.3744</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Conventional tracking solutions are not feasible in handling abrupt motion as they are based on smooth motion assumption or an accurate motion model. Abrupt motion is not subject to motion continuity and smoothness. To assuage this, we deem tracking as an optimisation problem and propose a novel abrupt motion tracker that based on swarm intelligence - the SwaTrack. Unlike existing swarm-based filtering methods, we first of all introduce an optimised swarm-based sampling strategy to tradeoff between the exploration and exploitation of the search space in search for the optimal proposal distribution. Secondly, we propose Dynamic Acceleration Parameters (DAP) allow on the fly tuning of the best mean and variance of the distribution for sampling. Such innovating idea of combining these strategies in an ingenious way in the PSO framework to handle the abrupt motion, which so far no existing works are found. Experimental results in both quantitative and qualitative had shown the effectiveness of the proposed method in tracking abrupt motions.
]]></description>
<dc:subject>motion-tracking video image-analysis machine-learning metaheuristics PSO nudge-targets algorithms rather-interesting</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:c3a246818e18/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:motion-tracking"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:PSO"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://biorxiv.org/content/early/2014/11/07/011072">
    <title>Bemovi, software for extracting BEhaviour and MOrphology from VIdeos. | bioRxiv</title>
    <dc:date>2014-12-18T13:32:26+00:00</dc:date>
    <link>http://biorxiv.org/content/early/2014/11/07/011072</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[1. Microbes are critical components of ecosystems and vital to the services they provide. The essential role of microbes is due to high levels of functional diversity, which are, however, not always mirrored in morphological differentiation hampering their taxonomic identification. In addition, the small size of microbes hinders the measurement of morphological and behavioural traits at the individual level, as well as interactions between individuals. 2. Recent advances in microbial community genetics and genomics, flow cytometry and digital image analysis are promising approaches, however they miss out on a very important aspect of populations and communities: the behaviour of individuals. Video analysis complements these methods by providing in addition to abundance and trait measurements, detailed behavioural information, capturing dynamic processes such as movement, and hence has the potential to describe the interactions between individuals. 3. We introduce bemovi, a package using R–the statistical computing environment–and the free image analysis software ImageJ. Bemovi is an automated digital video processing and analysis work flow to extract abundance and morphological and movement data for numerous individuals on a video, hence characterizing a population or community by multiple traits. Through a set of functions, bemovi identifies individuals present in a video and reconstruct their movement trajectories through space and time, merges measurements from all treated videos into a single database to which information on experimental conditions is added, readily available for further analysis in R. 4. We illustrate the validity, precision and accuracy of the method for experimental multi-species communities of protists in aquatic microcosms. We show the high correspondence between manual and automatic counts of individuals and illustrate how simultaneous time series of abundance, morphology and behaviour are constructed. We demonstrate how the data from videos can be used in combination with supervised machine learning algorithms to automatically classify individuals according to the species they belong to, and that information on movement behaviour can substantially improve the predictive ability and helps to distinguish morphologically similar species. In principle, bemovi should be able to extract from videos information about other types of organism, including microbes, so long as the individuals move relatively fast compared to their background.

]]></description>
<dc:subject>microbiology video image-analysis machine-learning statistics algorithms nudge-targets rather-interesting</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5f4b15de2f15/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:microbiology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1412.0439">
    <title>[1412.0439] Fuzzy human motion analysis: A review</title>
    <dc:date>2014-12-08T21:46:28+00:00</dc:date>
    <link>http://arxiv.org/abs/1412.0439</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Human Motion Analysis (HMA) is currently one of the most popularly active research domains as such significant research interests are motivated by a number of real world applications such as video surveillance, sports analysis, healthcare monitoring and so on. However, most of these real world applications face high levels of uncertainties that can affect the operations of such applications. Hence, the fuzzy set theory has been applied and showed great success in the recent past. In this paper, we aim at reviewing the fuzzy set oriented approaches for HMA, individuating how the fuzzy set may improve the HMA, envisaging and delineating the future perspectives. To the best of our knowledge, there is not found a single survey in the current literature that has discussed and reviewed fuzzy approaches towards the HMA. For ease of understanding, we conceptually classify the human motion into three broad levels: Low-Level (LoL), Mid-Level (MiL), and High-Level (HiL) HMA.
]]></description>
<dc:subject>fuzzy image-processing image-segmentation video motion-analysis surveillance inference machine-learning algorithms nudge-targets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:2f6010497a83/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:fuzzy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-segmentation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:motion-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:surveillance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1403.7220">
    <title>[1403.7220] Modeling and experimentation with asymmetric rigid bodies: a variation on disks and inclines</title>
    <dc:date>2014-11-28T21:46:17+00:00</dc:date>
    <link>http://arxiv.org/abs/1403.7220</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We study the ascending motion of a disk rolling on an incline when its center of mass lies outside the disk axis. The problem is suitable as laboratory project for a first course in mechanics at the undergraduate level and goes beyond typical textbook problems about bi-dimensional rigid body motions. We develop a theoretical model for the disk motion based on mechanical energy conservation and compare its predictions with experimental data obtained by digital video recording. Using readily available resources, a very satisfactory agreement is obtained between the model and the experimental observations. These results complement previous ones that have been reported in the literature for similar systems.
]]></description>
<dc:subject>physics experiment kinematics quite-nice video nudge-targets low-hanging-fruit consider:eureqa-approach</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5cd378563645/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:experiment"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:kinematics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:quite-nice"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:low-hanging-fruit"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:eureqa-approach"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1408.3526">
    <title>[1408.3526] Parallel software implementation of recursive multidimensional digital filters for point-target detection in cluttered infrared scenes</title>
    <dc:date>2014-11-27T17:56:08+00:00</dc:date>
    <link>http://arxiv.org/abs/1408.3526</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A technique for the enhancement of point targets in clutter is described. The local 3-D spectrum at each pixel is estimated recursively. An optical flow-field for the textured background is then generated using the 3-D autocorrelation function and the local velocity estimates are used to apply high-pass velocity-selective spatiotemporal filters, with finite impulse responses (FIRs), to subtract the background clutter signal, leaving the foreground target signal, plus noise. Parallel software implementations using a multicore central processing unit (CPU) and a graphical processing unit (GPU) are investigated.
]]></description>
<dc:subject>image-processing video signal-processing algorithms nudge-targets parallel</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b95d99634902/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:signal-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:parallel"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1403.0309">
    <title>[1403.0309] Object Tracking via Non-Euclidean Geometry: A Grassmann Approach</title>
    <dc:date>2014-11-19T12:22:22+00:00</dc:date>
    <link>http://arxiv.org/abs/1403.0309</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A robust visual tracking system requires an object appearance model that is able to handle occlusion, pose, and illumination variations in the video stream. This can be difficult to accomplish when the model is trained using only a single image. In this paper, we first propose a tracking approach based on affine subspaces (constructed from several images) which are able to accommodate the abovementioned variations. We use affine subspaces not only to represent the object, but also the candidate areas that the object may occupy. We furthermore propose a novel approach to measure affine subspace-to-subspace distance via the use of non-Euclidean geometry of Grassmann manifolds. The tracking problem is then considered as an inference task in a Markov Chain Monte Carlo framework via particle filtering. Quantitative evaluation on challenging video sequences indicates that the proposed approach obtains considerably better performance than several recent state-of-the-art methods such as Tracking-Learning-Detection and MILtrack.
]]></description>
<dc:subject>image-processing image-segmentation object-tracking video nudge-targets algorithms representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:34027d124696/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-segmentation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:object-tracking"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1304.2999">
    <title>[1304.2999] A New Approach To Two-View Motion Segmentation Using Global Dimension Minimization</title>
    <dc:date>2014-08-20T10:35:45+00:00</dc:date>
    <link>http://arxiv.org/abs/1304.2999</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We present a new approach to rigid-body motion segmentation from two views. We use a previously developed nonlinear embedding of two-view point correspondences into a 9-dimensional space and identify the different motions by segmenting lower-dimensional subspaces. In order to overcome nonuniform distributions along the subspaces, whose dimensions are unknown, we suggest the novel concept of global dimension and its minimization for clustering subspaces with some theoretical motivation. We propose a fast projected gradient algorithm for minimizing global dimension and thus segmenting motions from 2-views. We develop an outlier detection framework around the proposed method, and we present state-of-the-art results on outlier-free and outlier-corrupted two-view data for segmenting motion.
]]></description>
<dc:subject>video image-processing image-segmentation motion-detection algorithms nudge-targets consider:stress-testing rather-interesting</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:1d9fb62e3a78/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-segmentation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:motion-detection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:stress-testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1402.6978">
    <title>[1402.6978] Fundamental Limits of Video Coding: A Closed-form Characterization of Rate Distortion Region from First Principles</title>
    <dc:date>2014-07-06T12:27:29+00:00</dc:date>
    <link>http://arxiv.org/abs/1402.6978</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Classical motion-compensated video coding methods have been standardized by MPEG over the years and video codecs have become integral parts of media entertainment applications. Despite the ubiquitous use of video coding techniques, it is interesting to note that a closed form rate-distortion characterization for video coding is not available in the literature. In this paper, we develop a simple, yet, fundamental characterization of rate-distortion region in video coding based on information-theoretic first principles. The concept of conditional motion estimation is used to derive the closedform expression for rate-distortion region without losing its generality. Conditional motion estimation offers an elegant means to analyze the rate-distortion trade-offs and demonstrates the viability of achieving the bounds derived. The concept involves classifying image regions into active and inactive based on the amount of motion activity. By appropriately modeling the residuals corresponding to active and inactive regions, a closed form expression for rate-distortion function is derived in terms of motion activity and spatio-temporal correlation that commonly exist in video content. Experiments on real video clips using H.264 codec are presented to demonstrate the practicality and validity of the proposed rate-distortion analysis.
]]></description>
<dc:subject>video compression coding-theory algorithms nudge-targets representation rather-interesting</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f82f0a869882/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:compression"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:coding-theory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1310.5541">
    <title>[1310.5541] Piecewise Constant Sequential Importance Sampling for Fast Particle Filtering</title>
    <dc:date>2014-04-15T20:29:34+00:00</dc:date>
    <link>http://arxiv.org/abs/1310.5541</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Particle filters are key algorithms for object tracking under non-linear, non-Gaussian dynamics. The high computational cost of particle filters, however, hampers their applicability in cases where the likelihood model is costly to evaluate, or where large numbers of particles are required to represent the posterior. We introduce the approximate sequential importance sampling/resampling (ASIR) algorithm, which aims at reducing the cost of traditional particle filters by approximating the likelihood with a mixture of uniform distributions over pre-defined cells or bins. The particles in each bin are represented by a dummy particle at the center of mass of the original particle distribution and with a state vector that is the average of the states of all particles in the same bin. The likelihood is only evaluated for the dummy particles, and the resulting weight is identically assigned to all particles in the bin. We derive upper bounds on the approximation error of the so-obtained piecewise constant function representation, and analyze how bin size affects tracking accuracy and runtime. Further, we show numerically that the ASIR approximation error converges to that of sequential importance sampling/resampling (SIR) as the bin size is decreased. We present a set of numerical experiments from the field of biological image processing and tracking that demonstrate ASIR's capabilities. Overall, we consider ASIR a promising candidate for simple, fast particle filtering in generic applications.
]]></description>
<dc:subject>image-analysis image-processing algorithms inference video nudge-targets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ab3e37abe882/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1401.4648">
    <title>[1401.4648] Visual Tracking using Particle Swarm Optimization</title>
    <dc:date>2014-04-03T11:52:18+00:00</dc:date>
    <link>http://arxiv.org/abs/1401.4648</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The problem of robust extraction of visual odometry from a sequence of images obtained by an eye in hand camera configuration is addressed. A novel approach toward solving planar template based tracking is proposed which performs a non-linear image alignment for successful retrieval of camera transformations. In order to obtain global optimum a bio-metaheuristic is used for optimization of similarity among the planar regions. The proposed method is validated on image sequences with real as well as synthetic transformations and found to be resilient to intensity variations. A comparative analysis of the various similarity measures as well as various state-of-art methods reveal that the algorithm succeeds in tracking the planar regions robustly and has good potential to be used in real applications.
]]></description>
<dc:subject>particle-swarm metaheuristics video image-processing tracking algorithms nudge-targets</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:acb0e1f32b05/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:particle-swarm"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaheuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:tracking"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1307.7306">
    <title>[1307.7306] Kronecker Sum Decompositions of Space-Time Data</title>
    <dc:date>2014-02-26T21:36:11+00:00</dc:date>
    <link>http://arxiv.org/abs/1307.7306</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this paper we consider the use of the space vs. time Kronecker product decomposition in the estimation of covariance matrices for spatio-temporal data. This decomposition imposes lower dimensional structure on the estimated covariance matrix, thus reducing the number of samples required for estimation. To allow a smooth tradeoff between the reduction in the number of parameters (to reduce estimation variance) and the accuracy of the covariance approximation (affecting estimation bias), we introduce a diagonally loaded modification of the sum of kronecker products representation [1]. We derive a Cramer-Rao bound (CRB) on the minimum attainable mean squared predictor coefficient estimation error for unbiased estimators of Kronecker structured covariance matrices. We illustrate the accuracy of the diagonally loaded Kronecker sum decomposition by applying it to video data of human activity.
]]></description>
<dc:subject>image-analysis video algorithms prediction nudge-targets consider:representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b64c7bbe5d6a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:prediction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1309.6390">
    <title>[1309.6390] Contextually learnt detection of unusual motion-based behaviour in crowded public spaces</title>
    <dc:date>2013-11-03T12:21:42+00:00</dc:date>
    <link>http://arxiv.org/abs/1309.6390</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this paper we are interested in analyzing behaviour in crowded public places at the level of holistic motion. Our aim is to learn, without user input, strong scene priors or labelled data, the scope of "normal behaviour" for a particular scene and thus alert to novelty in unseen footage. The first contribution is a low-level motion model based on what we term tracklet primitives, which are scene-specific elementary motions. We propose a clustering-based algorithm for tracklet estimation from local approximations to tracks of appearance features. This is followed by two methods for motion novelty inference from tracklet primitives: (a) we describe an approach based on a non-hierarchial ensemble of Markov chains as a means of capturing behavioural characteristics at different scales, and (b) a more flexible alternative which exhibits a higher generalizing power by accounting for constraints introduced by intentionality and goal-oriented planning of human motion in a particular scene. Evaluated on a 2h long video of a busy city marketplace, both algorithms are shown to be successful at inferring unusual behaviour, the latter model achieving better performance for novelties at a larger spatial scale.
]]></description>
<dc:subject>video image-processing anomaly-detection nudge-targets algorithms</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:6cad0e02906a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:anomaly-detection"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://vimeo.com/73444208">
    <title>Gerry Leonidas on The Newest New Typography on Vimeo</title>
    <dc:date>2013-09-02T21:27:26+00:00</dc:date>
    <link>http://vimeo.com/73444208</link>
    <dc:creator>Vaguery</dc:creator><dc:subject>video via:mymarkup typography web-design coding semantic-layout page-layout book-design mobile-web</dc:subject>
<dc:identifier>https://pinboard.in/u:Vaguery/b:35047b1f9dbd/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:mymarkup"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:typography"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:web-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:coding"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:semantic-layout"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:page-layout"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:book-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:mobile-web"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1304.0869">
    <title>[1304.0869] Patch-based Probabilistic Image Quality Assessment for Face Selection and Improved Video-based Face Recognition</title>
    <dc:date>2013-04-24T22:14:45+00:00</dc:date>
    <link>http://arxiv.org/abs/1304.0869</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In video based face recognition, face images are typically captured over multiple frames in uncontrolled conditions, where head pose, illumination, shadowing, motion blur and focus change over the sequence. Additionally, inaccuracies in face localisation can also introduce scale and alignment variations. Using all face images, including images of poor quality, can actually degrade face recognition performance. While one solution it to use only the "best" subset of images, current face selection techniques are incapable of simultaneously handling all of the abovementioned issues. We propose an efficient patch-based face image quality assessment algorithm which quantifies the similarity of a face image to a probabilistic face model, representing an "ideal" face. Image characteristics that affect recognition are taken into account, including variations in geometric alignment (shift, rotation and scale), sharpness, head pose and cast shadows. Experiments on FERET and PIE datasets show that the proposed algorithm is able to identify images which are simultaneously the most frontal, aligned, sharp and well illuminated. Further experiments on a new video surveillance dataset (termed ChokePoint) show that the proposed method provides better face subsets than existing face selection techniques, leading to significant improvements in recognition accuracy.
]]></description>
<dc:subject>image-processing face-recognition algorithms nudge-targets video</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:70ed09daaf5a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:face-recognition"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1303.2465">
    <title>[1303.2465] A Low-Complexity Algorithm for Static Background Estimation from Cluttered Image Sequences in Surveillance Contexts</title>
    <dc:date>2013-04-08T20:19:06+00:00</dc:date>
    <link>http://arxiv.org/abs/1303.2465</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[For the purposes of foreground estimation, the true background model is unavailable in many practical circumstances and needs to be estimated from cluttered image sequences. We propose a sequential technique for static background estimation in such conditions, with low computational and memory requirements. Image sequences are analysed on a block-by-block basis. For each block location a representative set is maintained which contains distinct blocks obtained along its temporal line. The background estimation is carried out in a Markov Random Field framework, where the optimal labelling solution is computed using iterated conditional modes. The clique potentials are computed based on the combined frequency response of the candidate block and its neighbourhood. It is assumed that the most appropriate block results in the smoothest response, indirectly enforcing the spatial continuity of structures within a scene. Experiments on real-life surveillance videos demonstrate that the proposed method obtains considerably better background estimates (both qualitatively and quantitatively) than median filtering and the recently proposed "intervals of stable intensity" method. Further experiments on the Wallflower dataset suggest that the combination of the proposed method with a foreground segmentation algorithm results in improved foreground segmentation.]]></description>
<dc:subject>image-processing image-segmentation video nudge-targets algorithms suitable-for-a-new-DSL</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:c45ab1f222e4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-segmentation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:suitable-for-a-new-DSL"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://arxiv.org/abs/1302.3446">
    <title>[1302.3446] Adaptive Temporal Compressive Sensing for Video</title>
    <dc:date>2013-03-24T22:52:09+00:00</dc:date>
    <link>http://arxiv.org/abs/1302.3446</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[This paper introduces the concept of adaptive temporal compressive sensing (CS) for video. We propose a CS algorithm to adapt the compression ratio based on the scene's temporal complexity, computed from the compressed data, without compromising the quality of the reconstructed video. The temporal adaptivity is manifested by manipulating the integration time of the camera, opening the possibility to real-time implementation. The proposed algorithm is a generalized temporal CS approach that can be incorporated with a diverse set of existing hardware systems.]]></description>
<dc:subject>compressive-sensing algorithms image-processing image-segmentation nudge-targets video</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:cb58cc9ce1d9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:compressive-sensing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-segmentation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://vimeo.com/17079380">
    <title>Tim Brown - More Perfect Typography on Vimeo</title>
    <dc:date>2012-07-29T11:04:15+00:00</dc:date>
    <link>http://vimeo.com/17079380</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[At long last, designers can use real fonts on the web. But what now? Where do we go from here? Tim Brown has been studying type on the web for seven years, and has lots of ideas to share. In this talk, Tim will guide you through using typographic tools and perspectives that will change the way you design websites. Typography is an ancient art and craft; we are merely its latest practitioners. By looking to our tradition for guidance, we might once more attain our finest typographic achievements in this new medium.
]]></description>
<dc:subject>via:trek typography graphic-design typeface video</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:0a17c4a81bd8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:trek"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:typography"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:graphic-design"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:typeface"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.veer.com/ideas/our-fonts-our-friends/?vid6&amp;cid=em_1111_amr_1_font_all">
    <title>Veer Presents Our Fonts, Our Friends</title>
    <dc:date>2011-12-11T12:55:53+00:00</dc:date>
    <link>http://www.veer.com/ideas/our-fonts-our-friends/?vid6&amp;cid=em_1111_amr_1_font_all</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA["Some fonts dazzle, some fonts delight. And some are full of extra characters and features you can unleash – if you know how to use them. Learn all about OpenType fonts in the newest animated short, and then see them in action in the latest tutorial."]]></description>
<dc:subject>typography video tutorial introduction opentype</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:4fc4b42ccf29/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:typography"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:tutorial"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:introduction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:opentype"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://exilebibliophile.blogspot.com/2010/10/books-owning-them-loving-them.html">
    <title>The Exile Bibliophile: Books: Owning them, Loving them</title>
    <dc:date>2011-08-29T13:13:51+00:00</dc:date>
    <link>http://exilebibliophile.blogspot.com/2010/10/books-owning-them-loving-them.html</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA["So, I recently discovered Stacked Up: Writers Show off their Shelves, which is exactly what it sounds like. Short interviews with writers and some of their books. Just wonderful, though a bit too NYCentric to be truly invigorating. I just don't get that worked up over THE BIG DEAL that is NYC. Give me space, keep your crowds! But, NYC is where a LOT of writers live, so I can't be too cranky about it. Hopefully the Stacked Up folks will one day be able to get off the little island and out into the real world. Anyway, go enjoy these things Book Folk-- you're not alone."]]></description>
<dc:subject>books bibliomania bookshelves another-tag-involving-the-word-books authorship writing-culture video</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:85c4e42c272c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:books"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bibliomania"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:bookshelves"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:another-tag-involving-the-word-books"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:authorship"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:writing-culture"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://net.tutsplus.com/articles/web-roundups/jquery-for-absolute-beginners-video-series/">
    <title>jQuery for Absolute Beginners: The Complete Series | Nettuts+</title>
    <dc:date>2011-06-10T15:10:27+00:00</dc:date>
    <link>http://net.tutsplus.com/articles/web-roundups/jquery-for-absolute-beginners-video-series/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA["Hi everyone! Today, I posted the final screencast in my “jQuery for Absolute Beginners” series on the ThemeForest Blog. If you’re unfamiliar – over the course of about a month, I posted fifteen video tutorials that teach you EXACTLY how to use the jQuery library. We start by downloading the library and eventually work our way up to creating an AJAX style-switcher. I’m very proud of this series; possibly more than any other that I’ve done for Envato."]]></description>
<dc:subject>javascript jQuery tutorial podcast video</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ad0dce4b43f5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:javascript"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:jQuery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:tutorial"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:podcast"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.youtube.com/watch?v=uKfKtXYLG78">
    <title>YouTube - Erlang: The Movie</title>
    <dc:date>2011-05-30T15:21:25+00:00</dc:date>
    <link>http://www.youtube.com/watch?v=uKfKtXYLG78</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA["This is a short video about Erlang, the functional programming language."]]></description>
<dc:subject>amusing geek programming-language video</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:05d4523f51b2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:amusing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:geek"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:programming-language"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.groonk.net/blog/2011/05/watch-the-great-inception-charlie-chaplins-the-great-dictator-speech-mixed-with-hans-zimmers-inception-score/">
    <title>GROONK[dot]NET ಠ_ಠ » Watch: The Great Inception, Charlie Chaplin’s THE GREAT DICTATOR Speech Mixed with Hans Zimmer’s INCEPTION Score</title>
    <dc:date>2011-05-30T13:00:32+00:00</dc:date>
    <link>http://www.groonk.net/blog/2011/05/watch-the-great-inception-charlie-chaplins-the-great-dictator-speech-mixed-with-hans-zimmers-inception-score/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA["What a lovely mix. If you have not seen Chaplin’s THE GREAT DICTATOR you would do well to get right on that. It’s really a wonderful film."]]></description>
<dc:subject>mashup video stirring-speeches-with-soundtracks</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:7d8048dfa75f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:mashup"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:stirring-speeches-with-soundtracks"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://space1970.blogspot.com/2011/05/star-trek-animated-psa.html">
    <title>space1970: STAR TREK Animated PSA</title>
    <dc:date>2011-05-26T13:12:47+00:00</dc:date>
    <link>http://space1970.blogspot.com/2011/05/star-trek-animated-psa.html</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA["This is a genuine YouTube rarity: a Star Trek public service announcement produced by Filmation Studios for the Keep America Beautiful anti-pollution campaign, from the early 1970s. Featuring the voices of William Shatner, Leonard Nimoy and George Takei."]]></description>
<dc:subject>nostalgia video crowdsourcing-isn't-new public-service-announcement</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:2b6c29ab0ac3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nostalgia"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:crowdsourcing-isn't-new"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:public-service-announcement"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.charlierose.com/view/interview/473">
    <title>Charlie Rose - A conversation with anarchist David Graeber about anthropology</title>
    <dc:date>2011-05-18T21:30:03+00:00</dc:date>
    <link>http://www.charlierose.com/view/interview/473</link>
    <dc:creator>Vaguery</dc:creator><dc:subject>anarchism David-Graeber Charlie-Rose interview video</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b640594dca44/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:anarchism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:David-Graeber"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:Charlie-Rose"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:interview"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.telestream.net/screen-flow/overview.htm">
    <title>Screencasting Software - ScreenFlow Overview - Telestream</title>
    <dc:date>2011-05-17T14:35:38+00:00</dc:date>
    <link>http://www.telestream.net/screen-flow/overview.htm</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA["With Telestream ScreenFlow screencasting software, you can capture the contents of your entire monitor at the same time as you capture your video camera, microphone and computer's audio. Simple but powerful editing tools enable you to create incredible screencasts in no time.The finished result is a QuickTime or Windows Media movie, ready for publishing to your Web site or blog."]]></description>
<dc:subject>screencasting video software MacOS</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d89f3491d846/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:screencasting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:software"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:MacOS"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.tor.com/blogs/2011/05/how-gaimans-q8in8q-is-exciting-the-sff-community?utm_source=Feedburner%3A+Frontpage+Partial+RSS+Feed&amp;utm_medium=feed&amp;utm_campaign=Feed%3A+Torcom%2FFrontpage_Partial+%28Tor.com+Frontpage+Partial+-+Blog+and+Stories%29">
    <title>How Gaiman&amp;rsquo;s &amp;ldquo;8in8&amp;rdquo; is Exciting SFF Fans | tor.com | Science fiction and fantasy | Blog posts</title>
    <dc:date>2011-05-15T12:57:13+00:00</dc:date>
    <link>http://www.tor.com/blogs/2011/05/how-gaimans-q8in8q-is-exciting-the-sff-community?utm_source=Feedburner%3A+Frontpage+Partial+RSS+Feed&amp;utm_medium=feed&amp;utm_campaign=Feed%3A+Torcom%2FFrontpage_Partial+%28Tor.com+Frontpage+Partial+-+Blog+and+Stories%29</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The group ended up recording a 6 song album, “Nighty Night,” in the space of 12 hours. You can listen to the full record streaming on Amanda Palmer’s site.

The Creative Commons-released material and somewhat egalitarian nature of the project has led to the online SFF and rock communities picking up the music and using it to craft their own original works. Below the cut, we list the coolest videos that have grown out of the project so far!

]]></description>
<dc:subject>collaboration creative-commons sustainability creativity mashup video skiffy</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:271e05951b8f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:collaboration"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:creative-commons"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:sustainability"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:creativity"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:mashup"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:skiffy"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://gizmodo.com/5553765/are-cameras-the-new-guns">
    <title>Are Cameras the New Guns? - Gizmodo</title>
    <dc:date>2011-05-15T12:31:48+00:00</dc:date>
    <link>http://gizmodo.com/5553765/are-cameras-the-new-guns</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In 2001, when Michael Hyde was arrested for criminally violating the state's electronic surveillance law - aka recording a police encounter - the Massachusetts Supreme Judicial Court upheld his conviction 4-2. In dissent, Chief Justice Margaret Marshall stated, "Citizens have a particularly important role to play when the official conduct at issue is that of the police. Their role cannot be performed if citizens must fear criminal reprisals…." (Note: In some states it is the audio alone that makes the recording illegal.)]]></description>
<dc:subject>Bushism freedom police video privacy first-thing-we-do</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:746996bd6bc3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:Bushism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:freedom"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:police"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:privacy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:first-thing-we-do"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.clusterflock.org/2011/05/fifteen-uncoupled-simple-pendulums-of-monotonically-increasing-lengths-dance-together-to-produce-visual-traveling-waves-standing-waves-beating-and-seemingly-random-motion.html">
    <title>Fifteen uncoupled simple pendulums of monotonically increasing lengths dance together to produce visual traveling waves, standing waves, beating, and (seemingly) random motion | clusterflock</title>
    <dc:date>2011-05-14T15:16:06+00:00</dc:date>
    <link>http://www.clusterflock.org/2011/05/fifteen-uncoupled-simple-pendulums-of-monotonically-increasing-lengths-dance-together-to-produce-visual-traveling-waves-standing-waves-beating-and-seemingly-random-motion.html</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[watch]]></description>
<dc:subject>physics demonstration video simple-harmonic-motion</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:691c2a39eac8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:physics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:demonstration"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:simple-harmonic-motion"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://mashable.com/2010/03/26/non-profits-youtube/?utm_source=feedburner&amp;utm_medium=feed&amp;utm_campaign=Feed%3A+Mashable+(Mashable)">
    <title>5 Ways Non-Profits Can Increase Engagement With YouTube</title>
    <dc:date>2010-03-30T13:13:50+00:00</dc:date>
    <link>http://mashable.com/2010/03/26/non-profits-youtube/?utm_source=feedburner&amp;utm_medium=feed&amp;utm_campaign=Feed%3A+Mashable+(Mashable)</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA["The YouTube Nonprofit Program provides for extra benefits like branding capabilities, increased uploading capacity, and call-to-action overlays. Non-profits can use the call-to-action feature to drive sign-ups, donations, website traffic, and any other response in which users take action. This feature was effectively used by the World Food Programme to raise $36,000 on World Food Day with this video.…"
]]></description>
<dc:subject>nonprofit video marketing fundraising youtube tips workantile-exchange nudge</dc:subject>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b624e57b46da/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nonprofit"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:marketing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:fundraising"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:youtube"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:tips"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:workantile-exchange"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.funnyordie.co.uk/videos/0e4a1fa827/hitler-finds-out-about-another-downfall-parody?rel=player">
    <title>Hitler finds out about another Downfall parody from dawsonbros - Video</title>
    <dc:date>2009-09-07T22:01:37+00:00</dc:date>
    <link>http://www.funnyordie.co.uk/videos/0e4a1fa827/hitler-finds-out-about-another-downfall-parody?rel=player</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[via: innumerable sources
]]></description>
<dc:subject>video metaparody</dc:subject>
<dc:identifier>https://pinboard.in/u:Vaguery/b:66aad18221f0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaparody"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.youtube.com/watch?v=9Q1gksqqhLU">
    <title>YouTube - Shocking 1950's Commercial!</title>
    <dc:date>2009-08-27T16:13:10+00:00</dc:date>
    <link>http://www.youtube.com/watch?v=9Q1gksqqhLU</link>
    <dc:creator>Vaguery</dc:creator><dc:subject>nanohistory video commercial benchmarking social-networks</dc:subject>
<dc:identifier>https://pinboard.in/u:Vaguery/b:048cb05ac341/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nanohistory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:video"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:commercial"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:benchmarking"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:social-networks"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>