diff options
Diffstat (limited to 'site/public')
49 files changed, 183 insertions, 2239 deletions
diff --git a/site/public/about/assets/LICENSE/index.html b/site/public/about/assets/LICENSE/index.html index e73a8d77..bfc3d80e 100644 --- a/site/public/about/assets/LICENSE/index.html +++ b/site/public/about/assets/LICENSE/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-"> diff --git a/site/public/about/attribution/index.html b/site/public/about/attribution/index.html index 3afb30b2..acd862f1 100644 --- a/site/public/about/attribution/index.html +++ b/site/public/about/attribution/index.html @@ -49,15 +49,16 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-about"> - <section><h1>Legal</h1> + <section><h1>Attribution</h1> <section class="about-menu"> <ul> <li><a href="/about/">About</a></li> -<li><a href="/about/press/">Press</a></li> +<li><a href="/about/news/">News</a></li> <li><a class="current" href="/about/attribution/">Attribution</a></li> <li><a href="/about/legal/">Legal / Privacy</a></li> </ul> @@ -71,17 +72,17 @@ url = {https://megapixels.cc/}, urldate = {2019-04-18} } -</pre><p>If you redistribute any data from this site, you must also include this <a href="assets/megapixels_license.pdf">license</a> in PDF format</p> +</pre><p>If you redistribute any data from this site, you must also include this <a href="/assets/legal/megapixels_license.pdf">license</a> in PDF format</p> <p>The MegaPixel dataset is made available under the Open Data Commons Attribution License (<a href="https://opendatacommons.org/licenses/by/1.0/">https://opendatacommons.org/licenses/by/1.0/</a>) and for academic use only.</p> <p>READABLE SUMMARY OF Open Data Commons Attribution License</p> +<p>As long as you:</p> +<blockquote><p>Attribute: You must attribute any public use of the database, or works produced from the database, in the manner specified in the license. For any use or redistribution of the database, or works produced from it, you must make clear to others the license of the database and keep intact any notices on the original database.</p> +</blockquote> <p>You are free:</p> <blockquote><p>To Share: To copy, distribute and use the dataset To Create: To produce works from the dataset To Adapt: To modify, transform and build upon the database</p> </blockquote> -<p>As long as you:</p> -<blockquote><p>Attribute: You must attribute any public use of the database, or works produced from the database, in the manner specified in the license. For any use or redistribution of the database, or works produced from it, you must make clear to others the license of the database and keep intact any notices on the original database.</p> -</blockquote> </section> </div> diff --git a/site/public/about/index.html b/site/public/about/index.html index 2c008504..32947b63 100644 --- a/site/public/about/index.html +++ b/site/public/about/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-about"> @@ -57,7 +58,7 @@ <section class="about-menu"> <ul> <li><a class="current" href="/about/">About</a></li> -<li><a href="/about/press/">Press</a></li> +<li><a href="/about/news/">News</a></li> <li><a href="/about/attribution/">Attribution</a></li> <li><a href="/about/legal/">Legal / Privacy</a></li> </ul> diff --git a/site/public/about/legal/index.html b/site/public/about/legal/index.html index 28300043..ff6add38 100644 --- a/site/public/about/legal/index.html +++ b/site/public/about/legal/index.html @@ -49,15 +49,16 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-about"> - <section><h1>Legal</h1> + <section><h1>Legal and Privacy</h1> <section class="about-menu"> <ul> <li><a href="/about/">About</a></li> -<li><a href="/about/press/">Press</a></li> +<li><a href="/about/news/">News</a></li> <li><a href="/about/attribution/">Attribution</a></li> <li><a class="current" href="/about/legal/">Legal / Privacy</a></li> </ul> diff --git a/site/public/about/news/index.html b/site/public/about/news/index.html new file mode 100644 index 00000000..88d754cf --- /dev/null +++ b/site/public/about/news/index.html @@ -0,0 +1,112 @@ +<!doctype html> +<html> +<head> + <title>MegaPixels: MegaPixels News, Press and Recent Events</title> + <meta charset="utf-8" /> + <meta name="author" content="Adam Harvey" /> + <meta name="description" content="MegaPixels News, Press and Recent Events" /> + <meta property="og:title" content="MegaPixels: MegaPixels News, Press and Recent Events"/> + <meta property="og:type" content="website"/> + <meta property="og:image" content="https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/msceleb/assets/background.jpg" /> + <meta property="og:url" content="https://megapixels.cc/about/"/> + <meta property="og:site_name" content="MegaPixels" /> + <meta name="referrer" content="no-referrer" /> + <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=no"/> + <meta name="apple-mobile-web-app-status-bar-style" content="black"> + <meta name="apple-mobile-web-app-capable" content="yes"> + + <link rel="apple-touch-icon" sizes="57x57" href="/assets/img/favicon/apple-icon-57x57.png"> + <link rel="apple-touch-icon" sizes="60x60" href="/assets/img/favicon/apple-icon-60x60.png"> + <link rel="apple-touch-icon" sizes="72x72" href="/assets/img/favicon/apple-icon-72x72.png"> + <link rel="apple-touch-icon" sizes="76x76" href="/assets/img/favicon/apple-icon-76x76.png"> + <link rel="apple-touch-icon" sizes="114x114" href="/assets/img/favicon/apple-icon-114x114.png"> + <link rel="apple-touch-icon" sizes="120x120" href="/assets/img/favicon/apple-icon-120x120.png"> + <link rel="apple-touch-icon" sizes="144x144" href="/assets/img/favicon/apple-icon-144x144.png"> + <link rel="apple-touch-icon" sizes="152x152" href="/assets/img/favicon/apple-icon-152x152.png"> + <link rel="apple-touch-icon" sizes="180x180" href="/assets/img/favicon/apple-icon-180x180.png"> + <link rel="icon" type="image/png" sizes="192x192" href="/assets/img/favicon/android-icon-192x192.png"> + <link rel="icon" type="image/png" sizes="32x32" href="/assets/img/favicon/favicon-32x32.png"> + <link rel="icon" type="image/png" sizes="96x96" href="/assets/img/favicon/favicon-96x96.png"> + <link rel="icon" type="image/png" sizes="16x16" href="/assets/img/favicon/favicon-16x16.png"> + <link rel="manifest" href="/assets/img/favicon/manifest.json"> + <meta name="msapplication-TileColor" content="#ffffff"> + <meta name="msapplication-TileImage" content="/ms-icon-144x144.png"> + <meta name="theme-color" content="#ffffff"> + + <link rel='stylesheet' href='/assets/css/fonts.css' /> + <link rel='stylesheet' href='/assets/css/css.css' /> + <link rel='stylesheet' href='/assets/css/leaflet.css' /> + <link rel='stylesheet' href='/assets/css/applets.css' /> + <link rel='stylesheet' href='/assets/css/mobile.css' /> +</head> +<body> + <header> + <a class='slogan' href="/"> + <div class='logo'></div> + <div class='site_name'>MegaPixels</div> + + </a> + <div class='links'> + <a href="/datasets/">Datasets</a> + <a href="/about/">About</a> + <a href="/about/news">News</a> + </div> + </header> + <div class="content content-about"> + + <section><h1>News</h1> +<section class="about-menu"> +<ul> +<li><a href="/about/">About</a></li> +<li><a class="current" href="/about/news/">News</a></li> +<li><a href="/about/attribution/">Attribution</a></li> +<li><a href="/about/legal/">Legal / Privacy</a></li> +</ul> +</section><p>Since launching MegaPixels in April 2019, several of the datasets mentioned have disappeared and one surveillance workshop was canceled. Below is a list of responses, reactions, and press:</p> +<h5>June 2019</h5> +<ul> +<li>June 6: Financial Times covers the abrupt disappearance of four facial recognition datasets: <a href="https://www.ft.com/content/7d3e0d6a-87a0-11e9-a028-86cea8523dc2">Microsoft quietly deletes largest public face recognition data set</a> by Madhumita Murgia</li> +<li>June 2: A person tracking surveillance workshop at CVPR (<a href="https://reid-mct.github.io/2019/">reid-mct.github.io/2019</a>) has been canceled due to the <a href="/datasets/duke_mtmc">Duke MTMC dataset</a> no longer being available: "Due to some unforeseen circumstances, the test data has not been available. The multi-target multi-camera tracking and person re-identification challenge is canceled. We sincerely apologize for any inconvenience caused."</li> +<li>June 2: The <a href="/datasets/duke_mtmc">Duke MTMC dataset</a> website (<a href="http://vision.cs.duke.edu/DukeMTMC">vision.cs.duke.edu/DukeMTMC</a>) has abruptly gone blank. An archive from April 18 is still available on the Wayback Machine (<a href="https://web.archive.org/web/20190418085103/http://vision.cs.duke.edu/DukeMTMC/">web.archive.org/web/20190418085103/http://vision.cs.duke.edu/DukeMTMC/</a>)</li> +<li>June 1: The <a href="/datasets/brainwash">Brainwash</a> face/head dataset has been taken down by its author at <a href="https://exhibits.stanford.edu/data/catalog/sx925dc9385">exhibits.stanford.edu/data/catalog/sx925dc9385</a>. "This data was removed from access at the request of the depositor."</li> +<li>June 1: The <a href="/dataset/uccs">UCCS dataset page</a> has been updated with a response from the author to clarify that he did not provide any face data to government agencies. Funding was for technology transfer. This site never mentioned that he did provide data to government agencies, only that his work benefited their objectives.</li> +</ul> +<h5>May 2019</h5> +<ul> +<li>May 31: Semantic Scholar appears to be censoring citations used in this project. Two of the citations linking the <a href="/datasets/brainwash">Brainwash</a> dataset to research from the National University of Defense Technology (NUDT) in China have disabled. <a href="https://www.semanticscholar.org/paper/A-Replacement-Algorithm-of-Non-Maximum-Suppression-Zhao-Wang/591a4bfa6380c9fcd5f3ae690e3ac5c09b7bf37b">NUDT citation 1</a>, <a href="https://www.semanticscholar.org/paper/Localized-region-context-and-object-feature-fusion-Li-Dou/b02d31c640b0a31fb18c4f170d841d8e21ffb66c">NUDT citation 2</a>, and the <a href="https://www.semanticscholar.org/paper/End-to-End-People-Detection-in-Crowded-Scenes-Stewart-Andriluka/1bd1645a629f1b612960ab9bba276afd4cf7c666">original paper</a> show that the NUDT citation has been censored (see the references section on Semantic Scholar pages)</li> +<li>May 28: The <a href="/datasets/msceleb">Microsoft Celeb</a> (MS-Celeb-1M) face dataset website is now 404 and all the download links were deactivated. It appears that someone at Microsoft Research has shuttered access to the MS Celeb dataset. Yet it remains available, as of writing this, on <a href="https://ibug.doc.ic.ac.uk/resources/lightweight-face-recognition-challenge-workshop/">Imperial College London's website</a> and on <a href="https://msropendata.com/datasets/98fdfc70-85ee-5288-a69f-d859bbe9c737">https://msropendata.com/datasets/98fdfc70-85ee-5288-a69f-d859bbe9c737</a></li> +<li>May 29, 2019: Stories about the <a href="/datasets/uccs">UnConstrained College Students Dataset</a> appeared on <a href="https://www.engadget.com/2019/05/28/uccs-facial-recognition-study-students/">Engadget</a>, <a href="https://www.apnews.com/003bec760eae4d8085265af9e5175254">AP News</a>, <a href="https://www.nytimes.com/aponline/2019/05/28/us/ap-us-facial-recognition.html">New York Times</a>, <a href="https://www.usnews.com/news/best-states/colorado/articles/2019-05-28/colorado-campus-photographed-for-facial-recognition-research">US News</a>, <a href="https://www.dailydot.com/layer8/college-students-secret-face-recognition-project/">Daily Dot</a>, <a href="https://www.washingtonpost.com/business/technology/colorado-students-photographed-for-facial-recognition-study/2019/05/28/0838be48-8165-11e9-b585-e36b16a531aa_story.html">Washington Post</a>, <a href="https://www.msn.com/en-us/news/politics/colorado-students-unknowingly-photographed-for-facial-recognition-study/ar-AAC2Zkv">MSN</a>, <a href="https://iapp.org/news/a/students-photographed-for-facial-recognition-study/">International Association of Privacy Professionals</a>, <a href="https://www.youtube.com/watch?v=61NPPD6Mhys">The Denver Channel</a>, <a href="https://www.dailymail.co.uk/sciencetech/article-7079865/Spy-cameras-imaged-1-700-unwitting-subjects-facial-recognition-study-funded-U-S-government.html">Daily Mail</a>, <a href="https://nypost.com/2019/05/29/college-students-secretly-photographed-for-facial-recognition-study/">New York Post</a>, <a href="https://news.yahoo.com/colorado-students-photographed-facial-recognition-162127139.html">Yahoo! News</a></li> +<li>May 27, 2019: Denver Post writes about the UCCS dataset: <a href="https://www.denverpost.com/2019/05/27/cu-colorado-springs-facial-recognition-research/">CU Colorado Springs students secretly photographed for government-backed facial-recognition research</a></li> +<li>May 22, 2019: Interview with CS Indy about the UCCS dataset <a href="https://www.csindy.com/coloradosprings/uccs-secretly-photographed-students-to-advance-facial-recognition-technology/Content?oid=19664437">UCCS secretly photographed students to advance facial recognition technology</a> by J. Adrian Stanley</li> +</ul> +<h5>April 2019</h5> +<ul> +<li>April 20: Washington Post Editorial Board responds to Financial Times article based on data surfaced in MegaPixels project: <a href="https://www.washingtonpost.com/opinions/microsoft-worked-with-a-chinese-military-university-on-ai-does-that-make-sense/2019/04/21/a0fb82c6-5d59-11e9-842d-7d3ed7eb3957_story.html">Opinion | Microsoft worked with a Chinese military university on AI. Does that make sense?</a></li> +<li>April 19: Financial Times feature on MegaPixels project: <a href="https://www.ft.com/content/cf19b956-60a2-11e9-b285-3acd5d43599e">Who's Using Your Face</a> by Madhumita Murgia</li> +<li>April 19: MegaPixels data cited by report in Financial Times: <a href="https://www.ft.com/content/41be9878-61d9-11e9-b285-3acd5d43599e">Western AI researchers partnered with Chinese surveillance firm</a> by Madhumita Murgia</li> +<li>April 10: <a href="https://www.ft.com/content/9378e7ee-5ae6-11e9-9dde-7aedca0a081a">Microsoft worked with Chinese military university on artificial intelligence</a> based on data surfaced in <a href="/datasets/msceleb">MS Celeb dataset</a></li> +</ul> +<h5>2018</h5> +<ul> +<li>Aug 22: HRT Transgender dataset on Verge.com: <a href="https://www.theverge.com/2017/8/22/16180080/transgender-youtubers-ai-facial-recognition-dataset">Transgender YouTubers had their videos grabbed to train facial recognition software</a> by James Vincent</li> +</ul> +</section> + + </div> + <footer> + <ul class="footer-left"> + <li><a href="/">MegaPixels.cc</a></li> + <li><a href="/datasets/">Datasets</a></li> + <li><a href="/about/">About</a></li> + <li><a href="/about/press/">Press</a></li> + <li><a href="/about/legal/">Legal and Privacy</a></li> + </ul> + <ul class="footer-right"> + <li>MegaPixels ©2017-19 <a href="https://ahprojects.com">Adam R. Harvey</a></li> + <li>Made with support from <a href="https://mozilla.org">Mozilla</a></li> + </ul> + </footer> +</body> + +<script src="/assets/js/dist/index.js"></script> +</html>
\ No newline at end of file diff --git a/site/public/about/press/index.html b/site/public/about/press/index.html deleted file mode 100644 index 9dce4deb..00000000 --- a/site/public/about/press/index.html +++ /dev/null @@ -1,100 +0,0 @@ -<!doctype html> -<html> -<head> - <title>MegaPixels: MegaPixels Press and News</title> - <meta charset="utf-8" /> - <meta name="author" content="Adam Harvey" /> - <meta name="description" content="MegaPixels Press and News" /> - <meta property="og:title" content="MegaPixels: MegaPixels Press and News"/> - <meta property="og:type" content="website"/> - <meta property="og:image" content="https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/msceleb/assets/background.jpg" /> - <meta property="og:url" content="https://megapixels.cc/about/"/> - <meta property="og:site_name" content="MegaPixels" /> - <meta name="referrer" content="no-referrer" /> - <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=no"/> - <meta name="apple-mobile-web-app-status-bar-style" content="black"> - <meta name="apple-mobile-web-app-capable" content="yes"> - - <link rel="apple-touch-icon" sizes="57x57" href="/assets/img/favicon/apple-icon-57x57.png"> - <link rel="apple-touch-icon" sizes="60x60" href="/assets/img/favicon/apple-icon-60x60.png"> - <link rel="apple-touch-icon" sizes="72x72" href="/assets/img/favicon/apple-icon-72x72.png"> - <link rel="apple-touch-icon" sizes="76x76" href="/assets/img/favicon/apple-icon-76x76.png"> - <link rel="apple-touch-icon" sizes="114x114" href="/assets/img/favicon/apple-icon-114x114.png"> - <link rel="apple-touch-icon" sizes="120x120" href="/assets/img/favicon/apple-icon-120x120.png"> - <link rel="apple-touch-icon" sizes="144x144" href="/assets/img/favicon/apple-icon-144x144.png"> - <link rel="apple-touch-icon" sizes="152x152" href="/assets/img/favicon/apple-icon-152x152.png"> - <link rel="apple-touch-icon" sizes="180x180" href="/assets/img/favicon/apple-icon-180x180.png"> - <link rel="icon" type="image/png" sizes="192x192" href="/assets/img/favicon/android-icon-192x192.png"> - <link rel="icon" type="image/png" sizes="32x32" href="/assets/img/favicon/favicon-32x32.png"> - <link rel="icon" type="image/png" sizes="96x96" href="/assets/img/favicon/favicon-96x96.png"> - <link rel="icon" type="image/png" sizes="16x16" href="/assets/img/favicon/favicon-16x16.png"> - <link rel="manifest" href="/assets/img/favicon/manifest.json"> - <meta name="msapplication-TileColor" content="#ffffff"> - <meta name="msapplication-TileImage" content="/ms-icon-144x144.png"> - <meta name="theme-color" content="#ffffff"> - - <link rel='stylesheet' href='/assets/css/fonts.css' /> - <link rel='stylesheet' href='/assets/css/css.css' /> - <link rel='stylesheet' href='/assets/css/leaflet.css' /> - <link rel='stylesheet' href='/assets/css/applets.css' /> - <link rel='stylesheet' href='/assets/css/mobile.css' /> -</head> -<body> - <header> - <a class='slogan' href="/"> - <div class='logo'></div> - <div class='site_name'>MegaPixels</div> - - </a> - <div class='links'> - <a href="/datasets/">Datasets</a> - <a href="/about/">About</a> - </div> - </header> - <div class="content content-about"> - - <section><h1>Press</h1> -<section class="about-menu"> -<ul> -<li><a href="/about/">About</a></li> -<li><a class="current" href="/about/press/">Press</a></li> -<li><a href="/about/attribution/">Attribution</a></li> -<li><a href="/about/legal/">Legal / Privacy</a></li> -</ul> -</section><h5>In the News</h5> -<ul> -<li>May 29, 2019: UnConstrained College Students Dataset on <a href="https://www.engadget.com/2019/05/28/uccs-facial-recognition-study-students/">Engadget</a>, <a href="https://www.apnews.com/003bec760eae4d8085265af9e5175254">AP News</a>, <a href="https://www.nytimes.com/aponline/2019/05/28/us/ap-us-facial-recognition.html">New York Times</a>, <a href="https://www.usnews.com/news/best-states/colorado/articles/2019-05-28/colorado-campus-photographed-for-facial-recognition-research">US News</a>, <a href="https://www.dailydot.com/layer8/college-students-secret-face-recognition-project/">Daily Dot</a>, <a href="https://www.washingtonpost.com/business/technology/colorado-students-photographed-for-facial-recognition-study/2019/05/28/0838be48-8165-11e9-b585-e36b16a531aa_story.html">Washington Post</a>, <a href="https://www.msn.com/en-us/news/politics/colorado-students-unknowingly-photographed-for-facial-recognition-study/ar-AAC2Zkv">MSN</a>, <a href="https://iapp.org/news/a/students-photographed-for-facial-recognition-study/">International Association of Privacy Professionals</a>, <a href="https://www.youtube.com/watch?v=61NPPD6Mhys">The Denver Channel</a>, <a href="https://www.dailymail.co.uk/sciencetech/article-7079865/Spy-cameras-imaged-1-700-unwitting-subjects-facial-recognition-study-funded-U-S-government.html">Daily Mail</a>, <a href="https://nypost.com/2019/05/29/college-students-secretly-photographed-for-facial-recognition-study/">New York Post</a>, <a href="https://news.yahoo.com/colorado-students-photographed-facial-recognition-162127139.html">Yahoo! News</a></li> -<li>May 27, 2019: <a href="https://www.denverpost.com/2019/05/27/cu-colorado-springs-facial-recognition-research/">CU Colorado Springs students secretly photographed for government-backed facial-recognition research</a></li> -<li>May 22, 2019: <a href="https://www.csindy.com/coloradosprings/uccs-secretly-photographed-students-to-advance-facial-recognition-technology/Content?oid=19664437">UCCS secretly photographed students to advance facial recognition technology</a> by J. Adrian Stanley</li> -<li>April 19, 2019: <a href="https://www.ft.com/content/cf19b956-60a2-11e9-b285-3acd5d43599e">Who's Using Your Face</a> by Madhumita Murgia for FT.com</li> -</ul> -<h5>Cited by</h5> -<ul> -<li>April 19, 2019: <a href="https://www.ft.com/content/41be9878-61d9-11e9-b285-3acd5d43599e">Western AI researchers partnered with Chinese surveillance firm</a> by Madhumita Murgia for FT.com</li> -</ul> -<h5>Related</h5> -<ul> -<li>April 20: Washington Post Editorial Board <a href="https://www.washingtonpost.com/opinions/microsoft-worked-with-a-chinese-military-university-on-ai-does-that-make-sense/2019/04/21/a0fb82c6-5d59-11e9-842d-7d3ed7eb3957_story.html">Opinion | Microsoft worked with a Chinese military university on AI. Does that make sense?</a></li> -<li>April 10, 2019: <a href="https://www.ft.com/content/9378e7ee-5ae6-11e9-9dde-7aedca0a081a">Microsoft worked with Chinese military university on artificial intelligence</a> based on data surfaced in <a href="/datasets/msceleb">MS Celeb dataset</a></li> -<li>Aug 22, 2018: <a href="https://www.theverge.com/2017/8/22/16180080/transgender-youtubers-ai-facial-recognition-dataset">Transgender YouTubers had their videos grabbed to train facial recognition software</a> by James Vincent</li> -</ul> -</section> - - </div> - <footer> - <ul class="footer-left"> - <li><a href="/">MegaPixels.cc</a></li> - <li><a href="/datasets/">Datasets</a></li> - <li><a href="/about/">About</a></li> - <li><a href="/about/press/">Press</a></li> - <li><a href="/about/legal/">Legal and Privacy</a></li> - </ul> - <ul class="footer-right"> - <li>MegaPixels ©2017-19 <a href="https://ahprojects.com">Adam R. Harvey</a></li> - <li>Made with support from <a href="https://mozilla.org">Mozilla</a></li> - </ul> - </footer> -</body> - -<script src="/assets/js/dist/index.js"></script> -</html>
\ No newline at end of file diff --git a/site/public/about/updates/index.html b/site/public/about/updates/index.html deleted file mode 100644 index 6796e579..00000000 --- a/site/public/about/updates/index.html +++ /dev/null @@ -1,97 +0,0 @@ -<!doctype html> -<html> -<head> - <title>MegaPixels: MegaPixels Site Updates</title> - <meta charset="utf-8" /> - <meta name="author" content="Adam Harvey" /> - <meta name="description" content="MegaPixels Site Updates" /> - <meta property="og:title" content="MegaPixels: MegaPixels Site Updates"/> - <meta property="og:type" content="website"/> - <meta property="og:image" content="https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/msceleb/assets/background.jpg" /> - <meta property="og:url" content="https://megapixels.cc/about/"/> - <meta property="og:site_name" content="MegaPixels" /> - <meta name="referrer" content="no-referrer" /> - <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=no"/> - <meta name="apple-mobile-web-app-status-bar-style" content="black"> - <meta name="apple-mobile-web-app-capable" content="yes"> - - <link rel="apple-touch-icon" sizes="57x57" href="/assets/img/favicon/apple-icon-57x57.png"> - <link rel="apple-touch-icon" sizes="60x60" href="/assets/img/favicon/apple-icon-60x60.png"> - <link rel="apple-touch-icon" sizes="72x72" href="/assets/img/favicon/apple-icon-72x72.png"> - <link rel="apple-touch-icon" sizes="76x76" href="/assets/img/favicon/apple-icon-76x76.png"> - <link rel="apple-touch-icon" sizes="114x114" href="/assets/img/favicon/apple-icon-114x114.png"> - <link rel="apple-touch-icon" sizes="120x120" href="/assets/img/favicon/apple-icon-120x120.png"> - <link rel="apple-touch-icon" sizes="144x144" href="/assets/img/favicon/apple-icon-144x144.png"> - <link rel="apple-touch-icon" sizes="152x152" href="/assets/img/favicon/apple-icon-152x152.png"> - <link rel="apple-touch-icon" sizes="180x180" href="/assets/img/favicon/apple-icon-180x180.png"> - <link rel="icon" type="image/png" sizes="192x192" href="/assets/img/favicon/android-icon-192x192.png"> - <link rel="icon" type="image/png" sizes="32x32" href="/assets/img/favicon/favicon-32x32.png"> - <link rel="icon" type="image/png" sizes="96x96" href="/assets/img/favicon/favicon-96x96.png"> - <link rel="icon" type="image/png" sizes="16x16" href="/assets/img/favicon/favicon-16x16.png"> - <link rel="manifest" href="/assets/img/favicon/manifest.json"> - <meta name="msapplication-TileColor" content="#ffffff"> - <meta name="msapplication-TileImage" content="/ms-icon-144x144.png"> - <meta name="theme-color" content="#ffffff"> - - <link rel='stylesheet' href='/assets/css/fonts.css' /> - <link rel='stylesheet' href='/assets/css/css.css' /> - <link rel='stylesheet' href='/assets/css/leaflet.css' /> - <link rel='stylesheet' href='/assets/css/applets.css' /> - <link rel='stylesheet' href='/assets/css/mobile.css' /> -</head> -<body> - <header> - <a class='slogan' href="/"> - <div class='logo'></div> - <div class='site_name'>MegaPixels</div> - - </a> - <div class='links'> - <a href="/datasets/">Datasets</a> - <a href="/about/">About</a> - </div> - </header> - <div class="content content-about"> - - <section><h1>Updates and Responses</h1> -<section class="about-menu"> -<ul> -<li><a href="/about/">About</a></li> -<li><a class="current" href="/about/updates/">Updates</a></li> -<li><a href="/about/press/">Press</a></li> -<li><a href="/about/attribution/">Attribution</a></li> -<li><a href="/about/legal/">Legal / Privacy</a></li> -</ul> -</section><p>Since publishing this project, several of datasets have disappeared. Below is a chronical of recents events related to the datasets on this site.</p> -<p>June 2019</p> -<ul> -<li>June 2: The Duke MTMC main webpage was deactivated and the entire dataset seems to be no longer available from Duke</li> -<li>June 2: The has been <a href="https://reid-mct.github.io/2019/">https://reid-mct.github.io/2019/</a></li> -<li>June 1: The Brainwash face/head dataset has been taken down by its author after posting it about it</li> -</ul> -<p>May 2019</p> -<ul> -<li>May 31: Semantic Scholar appears to be censoring citations used in this project. Two of the citations linking the Brainwash dataset to a military research in China have been intentionally disabled.</li> -<li>May 28: The Microsoft Celeb (MS Celeb) face dataset website is now 404 and all the download links are deactivated. It appears that Microsoft Reserach has shuttered access to their MS Celeb dataset. Yet it remains available, as of June 2, on <a href="https://ibug.doc.ic.ac.uk/resources/lightweight-face-recognition-challenge-workshop/">Imperial College London's website</a></li> -<li></li> -</ul> -</section> - - </div> - <footer> - <ul class="footer-left"> - <li><a href="/">MegaPixels.cc</a></li> - <li><a href="/datasets/">Datasets</a></li> - <li><a href="/about/">About</a></li> - <li><a href="/about/press/">Press</a></li> - <li><a href="/about/legal/">Legal and Privacy</a></li> - </ul> - <ul class="footer-right"> - <li>MegaPixels ©2017-19 <a href="https://ahprojects.com">Adam R. Harvey</a></li> - <li>Made with support from <a href="https://mozilla.org">Mozilla</a></li> - </ul> - </footer> -</body> - -<script src="/assets/js/dist/index.js"></script> -</html>
\ No newline at end of file diff --git a/site/public/assets b/site/public/assets index bae68598..ec2e4be2 120000 --- a/site/public/assets +++ b/site/public/assets @@ -1 +1 @@ -../assets/
\ No newline at end of file +../assets
\ No newline at end of file diff --git a/site/public/datasets/50_people_one_question/index.html b/site/public/datasets/50_people_one_question/index.html deleted file mode 100644 index bc879799..00000000 --- a/site/public/datasets/50_people_one_question/index.html +++ /dev/null @@ -1,115 +0,0 @@ -<!doctype html> -<html> -<head> - <title>MegaPixels</title> - <meta charset="utf-8" /> - <meta name="author" content="Adam Harvey" /> - <meta name="description" content="People One Question is a dataset of people from an online video series on YouTube and Vimeo used for building facial recogntion algorithms" /> - <meta name="referrer" content="no-referrer" /> - <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes" /> - <link rel='stylesheet' href='/assets/css/fonts.css' /> - <link rel='stylesheet' href='/assets/css/css.css' /> - <link rel='stylesheet' href='/assets/css/leaflet.css' /> - <link rel='stylesheet' href='/assets/css/applets.css' /> - <link rel='stylesheet' href='/assets/css/mobile .css' /> -</head> -<body> - <header> - <a class='slogan' href="/"> - <div class='logo'></div> - <div class='site_name'>MegaPixels</div> - <div class='page_name'>50 People One Question Dataset</div> - </a> - <div class='links'> - <a href="/datasets/">Datasets</a> - <a href="/about/">About</a> - </div> - </header> - <div class="content content-dataset"> - - <section class='intro_section' style='background-image: url(https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/50_people_one_question/assets/background.jpg)'><div class='inner'><div class='hero_desc'><span class='bgpad'><span style="color:#ffaa00">People One Question</span> is a dataset of people from an online video series on YouTube and Vimeo used for building facial recogntion algorithms</span></div><div class='hero_subdesc'><span class='bgpad'>People One Question dataset includes ... -</span></div></div></section><section><h2>50 People 1 Question</h2> -</section><section><div class='right-sidebar'><div class='meta'> - <div class='gray'>Published</div> - <div>2013</div> - </div><div class='meta'> - <div class='gray'>Videos</div> - <div>33 </div> - </div><div class='meta'> - <div class='gray'>Purpose</div> - <div>Facial landmark estimation</div> - </div><div class='meta'> - <div class='gray'>Website</div> - <div><a href='http://www.vision.caltech.edu/~dhall/projects/MergingPoseEstimates/' target='_blank' rel='nofollow noopener'>caltech.edu</a></div> - </div></div><p>[ page under development ]</p> -</section><section> - <h3>Who used 50 People One Question Dataset?</h3> - - <p> - This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. - </p> - - </section> - -<section class="applet_container"> -<!-- <div style="position: absolute;top: 0px;right: -55px;width: 180px;font-size: 14px;">Labeled Faces in the Wild Dataset<br><span class="numc" style="font-size: 11px;">20 citations</span> -</div> --> - <div class="applet" data-payload="{"command": "chart"}"></div> -</section> - -<section class="applet_container"> - <div class="applet" data-payload="{"command": "piechart"}"></div> -</section> - -<section> - - <h3>Biometric Trade Routes</h3> - - <p> - To help understand how 50 People One Question Dataset has been used around the world by commercial, military, and academic organizations; existing publicly available research citing 50 People One Question was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. - </p> - - </section> - -<section class="applet_container fullwidth"> - <div class="applet" data-payload="{"command": "map"}"></div> -</section> - -<div class="caption"> - <ul class="map-legend"> - <li class="edu">Academic</li> - <li class="com">Commercial</li> - <li class="gov">Military / Government</li> - </ul> - <div class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</div > -</div> - - -<section class="applet_container"> - - <h3>Dataset Citations</h3> - <p> - The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. If you use our data, please <a href="/about/attribution">cite our work</a>. - </p> - - <div class="applet" data-payload="{"command": "citations"}"></div> -</section> - - </div> - <footer> - <ul class="footer-left"> - <li><a href="/">MegaPixels.cc</a></li> - <li><a href="/datasets/">Datasets</a></li> - <li><a href="/about/">About</a></li> - <li><a href="/about/press/">Press</a></li> - <li><a href="/about/legal/">Legal and Privacy</a></li> - </ul> - <ul class="footer-right"> - <li>MegaPixels ©2017-19 <a href="https://ahprojects.com">Adam R. Harvey</a></li> - <li>Made with support from <a href="https://mozilla.org">Mozilla</a></li> - </ul> - </footer> -</body> - -<script src="/assets/js/dist/index.js"></script> -</html>
\ No newline at end of file diff --git a/site/public/datasets/afad/index.html b/site/public/datasets/afad/index.html deleted file mode 100644 index f5a04251..00000000 --- a/site/public/datasets/afad/index.html +++ /dev/null @@ -1,128 +0,0 @@ -<!doctype html> -<html> -<head> - <title>MegaPixels</title> - <meta charset="utf-8" /> - <meta name="author" content="Adam Harvey" /> - <meta name="description" content="AFAD: Asian Face Age Dataset" /> - <meta name="referrer" content="no-referrer" /> - <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes" /> - <link rel='stylesheet' href='/assets/css/fonts.css' /> - <link rel='stylesheet' href='/assets/css/css.css' /> - <link rel='stylesheet' href='/assets/css/leaflet.css' /> - <link rel='stylesheet' href='/assets/css/applets.css' /> - <link rel='stylesheet' href='/assets/css/mobile .css' /> -</head> -<body> - <header> - <a class='slogan' href="/"> - <div class='logo'></div> - <div class='site_name'>MegaPixels</div> - <div class='page_name'>Asian Face Age Dataset</div> - </a> - <div class='links'> - <a href="/datasets/">Datasets</a> - <a href="/about/">About</a> - </div> - </header> - <div class="content content-"> - - <section><h2>Asian Face Age Dataset</h2> -</section><section><div class='right-sidebar'><div class='meta'> - <div class='gray'>Published</div> - <div>2017</div> - </div><div class='meta'> - <div class='gray'>Images</div> - <div>164,432 </div> - </div><div class='meta'> - <div class='gray'>Purpose</div> - <div>age estimation on Asian Faces</div> - </div><div class='meta'> - <div class='gray'>Funded by</div> - <div>NSFC, the Fundamental Research Funds for the Central Universities, the Program for Changjiang Scholars and Innovative Research Team in University of China, the Shaanxi Innovative Research Team for Key Science and Technology, and China Postdoctoral Science Foundation</div> - </div><div class='meta'> - <div class='gray'>Website</div> - <div><a href='https://afad-dataset.github.io/' target='_blank' rel='nofollow noopener'>github.io</a></div> - </div></div><p>[ page under development ]</p> -</section><section> - <h3>Who used Asian Face Age Dataset?</h3> - - <p> - This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. - </p> - - </section> - -<section class="applet_container"> -<!-- <div style="position: absolute;top: 0px;right: -55px;width: 180px;font-size: 14px;">Labeled Faces in the Wild Dataset<br><span class="numc" style="font-size: 11px;">20 citations</span> -</div> --> - <div class="applet" data-payload="{"command": "chart"}"></div> -</section> - -<section class="applet_container"> - <div class="applet" data-payload="{"command": "piechart"}"></div> -</section> - -<section> - - <h3>Biometric Trade Routes</h3> - - <p> - To help understand how Asian Face Age Dataset has been used around the world by commercial, military, and academic organizations; existing publicly available research citing The Asian Face Age Dataset was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. - </p> - - </section> - -<section class="applet_container fullwidth"> - <div class="applet" data-payload="{"command": "map"}"></div> -</section> - -<div class="caption"> - <ul class="map-legend"> - <li class="edu">Academic</li> - <li class="com">Commercial</li> - <li class="gov">Military / Government</li> - </ul> - <div class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</div > -</div> - - -<section class="applet_container"> - - <h3>Dataset Citations</h3> - <p> - The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. If you use our data, please <a href="/about/attribution">cite our work</a>. - </p> - - <div class="applet" data-payload="{"command": "citations"}"></div> -</section><section><h2>(ignore) research notes</h2> -<blockquote><p>The Asian Face Age Dataset (AFAD) is a new dataset proposed for evaluating the performance of age estimation, which contains more than 160K facial images and the corresponding age and gender labels. This dataset is oriented to age estimation on Asian faces, so all the facial images are for Asian faces. It is noted that the AFAD is the biggest dataset for age estimation to date. It is well suited to evaluate how deep learning methods can be adopted for age estimation. -Motivation</p> -<p>For age estimation, there are several public datasets for evaluating the performance of a specific algorithm, such as FG-NET [1] (1002 face images), MORPH I (1690 face images), and MORPH II[2] (55,608 face images). Among them, the MORPH II is the biggest public dataset to date. On the other hand, as we know it is necessary to collect a large scale dataset to train a deep Convolutional Neural Network. Therefore, the MORPH II dataset is extensively used to evaluate how deep learning methods can be adopted for age estimation [3][4].</p> -<p>However, the ethnic is very unbalanced for the MORPH II dataset, i.e., it has only less than 1% Asian faces. In order to evaluate the previous methods for age estimation on Asian Faces, the Asian Face Age Dataset (AFAD) was proposed.</p> -<p>There are 164,432 well-labeled photos in the AFAD dataset. It consist of 63,680 photos for female as well as 100,752 photos for male, and the ages range from 15 to 40. The distribution of photo counts for distinct ages are illustrated in the figure above. Some samples are shown in the Figure on the top. Its download link is provided in the "Download" section.</p> -<p>In addition, we also provide a subset of the AFAD dataset, called AFAD-Lite, which only contains PLACEHOLDER well-labeled photos. It consist of PLACEHOLDER photos for female as well as PLACEHOLDER photos for male, and the ages range from 15 to 40. The distribution of photo counts for distinct ages are illustrated in Fig. PLACEHOLDER. Its download link is also provided in the "Download" section.</p> -<p>The AFAD dataset is built by collecting selfie photos on a particular social network -- RenRen Social Network (RSN) [5]. The RSN is widely used by Asian students including middle school, high school, undergraduate, and graduate students. Even after leaving from school, some people still access their RSN account to connect with their old classmates. So, the age of the RSN user crosses a wide range from 15-years to more than 40-years old.</p> -<p>Please notice that this dataset is made available for academic research purpose only.</p> -</blockquote> -<p><a href="https://afad-dataset.github.io/">https://afad-dataset.github.io/</a></p> -</section> - - </div> - <footer> - <ul class="footer-left"> - <li><a href="/">MegaPixels.cc</a></li> - <li><a href="/datasets/">Datasets</a></li> - <li><a href="/about/">About</a></li> - <li><a href="/about/press/">Press</a></li> - <li><a href="/about/legal/">Legal and Privacy</a></li> - </ul> - <ul class="footer-right"> - <li>MegaPixels ©2017-19 <a href="https://ahprojects.com">Adam R. Harvey</a></li> - <li>Made with support from <a href="https://mozilla.org">Mozilla</a></li> - </ul> - </footer> -</body> - -<script src="/assets/js/dist/index.js"></script> -</html>
\ No newline at end of file diff --git a/site/public/datasets/brainwash/ijb_c/index.html b/site/public/datasets/brainwash/ijb_c/index.html deleted file mode 100644 index f57d180b..00000000 --- a/site/public/datasets/brainwash/ijb_c/index.html +++ /dev/null @@ -1,152 +0,0 @@ -<!doctype html> -<html> -<head> - <title>MegaPixels</title> - <meta charset="utf-8" /> - <meta name="author" content="Adam Harvey" /> - <meta name="description" content="IJB-C is a datset ..." /> - <meta name="referrer" content="no-referrer" /> - <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes" /> - <link rel='stylesheet' href='/assets/css/fonts.css' /> - <link rel='stylesheet' href='/assets/css/css.css' /> - <link rel='stylesheet' href='/assets/css/leaflet.css' /> - <link rel='stylesheet' href='/assets/css/applets.css' /> -</head> -<body> - <header> - <a class='slogan' href="/"> - <div class='logo'></div> - <div class='site_name'>MegaPixels</div> - <div class='splash'>IJB-C</div> - </a> - <div class='links'> - <a href="/datasets/">Datasets</a> - <a href="/about/">About</a> - </div> - </header> - <div class="content content-dataset"> - - <section class='intro_section' style='background-image: url(https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/brainwash/assets/background.jpg)'><div class='inner'><div class='hero_desc'><span class='bgpad'>IJB-C is a datset ...</span></div><div class='hero_subdesc'><span class='bgpad'>The IJB-C dataset contains... -</span></div></div></section><section><h2>Brainwash Dataset</h2> -</section><section><div class='right-sidebar'><div class='meta'> - <div class='gray'>Published</div> - <div>2017</div> - </div><div class='meta'> - <div class='gray'>Images</div> - <div>21,294 </div> - </div><div class='meta'> - <div class='gray'>Videos</div> - <div>11,779 </div> - </div><div class='meta'> - <div class='gray'>Identities</div> - <div>3,531 </div> - </div><div class='meta'> - <div class='gray'>Purpose</div> - <div>face recognition challenge by NIST in full motion videos</div> - </div><div class='meta'> - <div class='gray'>Website</div> - <div><a href='https://www.nist.gov/programs-projects/face-challenges' target='_blank' rel='nofollow noopener'>nist.gov</a></div> - </div></div><p>Brainwash is a dataset of livecam images taken from San Francisco's Brainwash Cafe. It includes 11,918 images of "everyday life of a busy downtown cafe"<a class="footnote_shim" name="[^readme]_1"> </a><a href="#[^readme]" class="footnote" title="Footnote 1">1</a> captured at 100 second intervals throught the entire day. The Brainwash dataset includes 3 full days of webcam images taken on October 27, November 13, and November 24 in 2014. According the author's <a href="https://www.semanticscholar.org/paper/End-to-End-People-Detection-in-Crowded-Scenes-Stewart-Andriluka/1bd1645a629f1b612960ab9bba276afd4cf7c666">reserach paper</a> introducing the dataset, the images were acquired with the help of Angelcam.com<a class="footnote_shim" name="[^end_to_end]_1"> </a><a href="#[^end_to_end]" class="footnote" title="Footnote 2">2</a></p> -<p>The Brainwash dataset is unique because it uses images from a publicly available webcam that records people inside a privately owned business without any consent. No ordinary cafe custom could ever suspect there image would end up in dataset used for surveillance reserach and development, but that is exactly what happened to customers at Brainwash cafe in San Francisco.</p> -<p>Although Brainwash appears to be a less popular dataset, it was used in 2016 and 2017 by researchers from the National University of Defense Technology in China took note of the dataset and used it for two <a href="https://www.semanticscholar.org/paper/Localized-region-context-and-object-feature-fusion-Li-Dou/b02d31c640b0a31fb18c4f170d841d8e21ffb66c">research</a> <a href="https://www.semanticscholar.org/paper/A-Replacement-Algorithm-of-Non-Maximum-Suppression-Zhao-Wang/591a4bfa6380c9fcd5f3ae690e3ac5c09b7bf37b">projects</a> on advancing the capabilities of object detection to more accurately isolate the target region in an image (<a href="https://www.itm-conferences.org/articles/itmconf/pdf/2017/04/itmconf_ita2017_05006.pdf">PDF</a>). <a class="footnote_shim" name="[^localized_region_context]_1"> </a><a href="#[^localized_region_context]" class="footnote" title="Footnote 3">3</a> <a class="footnote_shim" name="[^replacement_algorithm]_1"> </a><a href="#[^replacement_algorithm]" class="footnote" title="Footnote 4">4</a>. The dataset also appears in a 2017 <a href="https://ieeexplore.ieee.org/document/7877809">research paper</a> from Peking University for the purpose of improving surveillance capabilities for "people detection in the crowded scenes".</p> -</section><section class='images'><div class='image'><img src='https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/brainwash/assets/brainwash_grid.jpg' alt=' A visualization of 81,973 head annotations from the Brainwash dataset training partition. Credit: megapixels.cc. License: Open Data Commons Public Domain Dedication (PDDL)'><div class='caption'> A visualization of 81,973 head annotations from the Brainwash dataset training partition. Credit: megapixels.cc. License: Open Data Commons Public Domain Dedication (PDDL)</div></div></section><section> - <h3>Who used IJB-C?</h3> - - <p> - This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. - </p> - - </section> - -<section class="applet_container"> -<!-- <div style="position: absolute;top: 0px;right: -55px;width: 180px;font-size: 14px;">Labeled Faces in the Wild Dataset<br><span class="numc" style="font-size: 11px;">20 citations</span> -</div> --> - <div class="applet" data-payload="{"command": "chart"}"></div> -</section> - -<section class="applet_container"> - <div class="applet" data-payload="{"command": "piechart"}"></div> -</section> - -<section> - - <h3>Biometric Trade Routes</h3> - - <p> - To help understand how IJB-C has been used around the world by commercial, military, and academic organizations; existing publicly available research citing IARPA Janus Benchmark C was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. - </p> - - </section> - -<section class="applet_container fullwidth"> - <div class="applet" data-payload="{"command": "map"}"></div> -</section> - -<div class="caption"> - <ul class="map-legend"> - <li class="edu">Academic</li> - <li class="com">Commercial</li> - <li class="gov">Military / Government</li> - </ul> - <div class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</div > -</div> - - -<section class="applet_container"> - - <h3>Dataset Citations</h3> - <p> - The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. If you use our data, please <a href="/about/attribution">cite our work</a>. - </p> - - <div class="applet" data-payload="{"command": "citations"}"></div> -</section><section> - - <div class="hr-wave-holder"> - <div class="hr-wave-line hr-wave-line1"></div> - <div class="hr-wave-line hr-wave-line2"></div> - </div> - - <h2>Supplementary Information</h2> - -</section><section class='images'><div class='image'><img src='https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/brainwash/assets/brainwash_example.jpg' alt=' An sample image from the Brainwash dataset used for training face and head detection algorithms for surveillance. The datset contains 11,916 more images like this one. Credit: megapixels.cc. License: Open Data Commons Public Domain Dedication (PDDL)'><div class='caption'> An sample image from the Brainwash dataset used for training face and head detection algorithms for surveillance. The datset contains 11,916 more images like this one. Credit: megapixels.cc. License: Open Data Commons Public Domain Dedication (PDDL)</div></div></section><section class='images'><div class='image'><img src='https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/brainwash/assets/brainwash_saliency_map.jpg' alt=' A visualization of the active regions for 81,973 head annotations from the Brainwash dataset training partition. Credit: megapixels.cc. License: Open Data Commons Public Domain Dedication (PDDL)'><div class='caption'> A visualization of the active regions for 81,973 head annotations from the Brainwash dataset training partition. Credit: megapixels.cc. License: Open Data Commons Public Domain Dedication (PDDL)</div></div></section><section> - - <h4>Cite Our Work</h4> - <p> - - If you use our data, research, or graphics please cite our work: - -<pre id="cite-bibtex"> -@online{megapixels, - author = {Harvey, Adam. LaPlace, Jules.}, - title = {MegaPixels: Origins, Ethics, and Privacy Implications of Publicly Available Face Recognition Image Datasets}, - year = 2019, - url = {https://megapixels.cc/}, - urldate = {2019-04-18} -}</pre> - - </p> -</section><section><h3>References</h3><section><ul class="footnotes"><li><a name="[^readme]" class="footnote_shim"></a><span class="backlinks"><a href="#[^readme]_1">a</a></span><p>"readme.txt" <a href="https://exhibits.stanford.edu/data/catalog/sx925dc9385">https://exhibits.stanford.edu/data/catalog/sx925dc9385</a>.</p> -</li><li><a name="[^end_to_end]" class="footnote_shim"></a><span class="backlinks"><a href="#[^end_to_end]_1">a</a></span><p>Stewart, Russel. Andriluka, Mykhaylo. "End-to-end people detection in crowded scenes". 2016.</p> -</li><li><a name="[^localized_region_context]" class="footnote_shim"></a><span class="backlinks"><a href="#[^localized_region_context]_1">a</a></span><p>Li, Y. and Dou, Y. and Liu, X. and Li, T. Localized Region Context and Object Feature Fusion for People Head Detection. ICIP16 Proceedings. 2016. Pages 594-598.</p> -</li><li><a name="[^replacement_algorithm]" class="footnote_shim"></a><span class="backlinks"><a href="#[^replacement_algorithm]_1">a</a></span><p>Zhao. X, Wang Y, Dou, Y. A Replacement Algorithm of Non-Maximum Suppression Base on Graph Clustering.</p> -</li></ul></section></section> - - </div> - <footer> - <ul class="footer-left"> - <li><a href="/">MegaPixels.cc</a></li> - <li><a href="/datasets/">Datasets</a></li> - <li><a href="/about/">About</a></li> - <li><a href="/about/press/">Press</a></li> - <li><a href="/about/legal/">Legal and Privacy</a></li> - </ul> - <ul class="footer-right"> - <li>MegaPixels ©2017-19 <a href="https://ahprojects.com">Adam R. Harvey</a></li> - <li>Made with support from <a href="https://mozilla.org">Mozilla</a></li> - </ul> - </footer> -</body> - -<script src="/assets/js/dist/index.js"></script> -</html>
\ No newline at end of file diff --git a/site/public/datasets/brainwash/index.html b/site/public/datasets/brainwash/index.html index 898a77e3..28f8ccc6 100644 --- a/site/public/datasets/brainwash/index.html +++ b/site/public/datasets/brainwash/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-dataset"> @@ -103,7 +104,7 @@ <section> - <h3>Biometric Trade Routes</h3> + <h3>Information Supply chain</h3> <p> To help understand how Brainwash Dataset has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Brainwash Dataset was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. diff --git a/site/public/datasets/caltech_10k/index.html b/site/public/datasets/caltech_10k/index.html deleted file mode 100644 index 5848b804..00000000 --- a/site/public/datasets/caltech_10k/index.html +++ /dev/null @@ -1,125 +0,0 @@ -<!doctype html> -<html> -<head> - <title>MegaPixels</title> - <meta charset="utf-8" /> - <meta name="author" content="Adam Harvey" /> - <meta name="description" content="Caltech 10K Faces Dataset" /> - <meta name="referrer" content="no-referrer" /> - <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes" /> - <link rel='stylesheet' href='/assets/css/fonts.css' /> - <link rel='stylesheet' href='/assets/css/css.css' /> - <link rel='stylesheet' href='/assets/css/leaflet.css' /> - <link rel='stylesheet' href='/assets/css/applets.css' /> - <link rel='stylesheet' href='/assets/css/mobile .css' /> -</head> -<body> - <header> - <a class='slogan' href="/"> - <div class='logo'></div> - <div class='site_name'>MegaPixels</div> - <div class='page_name'>Brainwash Dataset</div> - </a> - <div class='links'> - <a href="/datasets/">Datasets</a> - <a href="/about/">About</a> - </div> - </header> - <div class="content content-"> - - <section><h2>Caltech 10K Faces Dataset</h2> -</section><section><div class='right-sidebar'><div class='meta'> - <div class='gray'>Published</div> - <div>2015</div> - </div><div class='meta'> - <div class='gray'>Images</div> - <div>11,917 </div> - </div><div class='meta'> - <div class='gray'>Purpose</div> - <div>Head detection</div> - </div><div class='meta'> - <div class='gray'>Created by</div> - <div>Stanford University (US), Max Planck Institute for Informatics (DE)</div> - </div><div class='meta'> - <div class='gray'>Funded by</div> - <div>Max Planck Center for Visual Computing and Communication</div> - </div><div class='meta'> - <div class='gray'>Download Size</div> - <div>4.1 GB</div> - </div><div class='meta'> - <div class='gray'>Website</div> - <div><a href='https://purl.stanford.edu/sx925dc9385' target='_blank' rel='nofollow noopener'>stanford.edu</a></div> - </div></div><p>[ page under development ]</p> -</section><section> - <h3>Who used Brainwash Dataset?</h3> - - <p> - This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. - </p> - - </section> - -<section class="applet_container"> -<!-- <div style="position: absolute;top: 0px;right: -55px;width: 180px;font-size: 14px;">Labeled Faces in the Wild Dataset<br><span class="numc" style="font-size: 11px;">20 citations</span> -</div> --> - <div class="applet" data-payload="{"command": "chart"}"></div> -</section> - -<section class="applet_container"> - <div class="applet" data-payload="{"command": "piechart"}"></div> -</section> - -<section> - - <h3>Biometric Trade Routes</h3> - - <p> - To help understand how Brainwash Dataset has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Brainwash Dataset was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. - </p> - - </section> - -<section class="applet_container fullwidth"> - <div class="applet" data-payload="{"command": "map"}"></div> -</section> - -<div class="caption"> - <ul class="map-legend"> - <li class="edu">Academic</li> - <li class="com">Commercial</li> - <li class="gov">Military / Government</li> - </ul> - <div class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</div > -</div> - - -<section class="applet_container"> - - <h3>Dataset Citations</h3> - <p> - The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. If you use our data, please <a href="/about/attribution">cite our work</a>. - </p> - - <div class="applet" data-payload="{"command": "citations"}"></div> -</section><section><h3>(ignore) research notes</h3> -<p>The dataset contains images of people collected from the web by typing common given names into Google Image Search. The coordinates of the eyes, the nose and the center of the mouth for each frontal face are provided in a ground truth file. This information can be used to align and crop the human faces or as a ground truth for a face detection algorithm. The dataset has 10,524 human faces of various resolutions and in different settings, e.g. portrait images, groups of people, etc. Profile faces or very low resolution faces are not labeled.</p> -</section> - - </div> - <footer> - <ul class="footer-left"> - <li><a href="/">MegaPixels.cc</a></li> - <li><a href="/datasets/">Datasets</a></li> - <li><a href="/about/">About</a></li> - <li><a href="/about/press/">Press</a></li> - <li><a href="/about/legal/">Legal and Privacy</a></li> - </ul> - <ul class="footer-right"> - <li>MegaPixels ©2017-19 <a href="https://ahprojects.com">Adam R. Harvey</a></li> - <li>Made with support from <a href="https://mozilla.org">Mozilla</a></li> - </ul> - </footer> -</body> - -<script src="/assets/js/dist/index.js"></script> -</html>
\ No newline at end of file diff --git a/site/public/datasets/celeba/index.html b/site/public/datasets/celeba/index.html deleted file mode 100644 index 92c0e334..00000000 --- a/site/public/datasets/celeba/index.html +++ /dev/null @@ -1,127 +0,0 @@ -<!doctype html> -<html> -<head> - <title>MegaPixels</title> - <meta charset="utf-8" /> - <meta name="author" content="Adam Harvey" /> - <meta name="description" content="CelebA is a dataset of people..." /> - <meta name="referrer" content="no-referrer" /> - <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes" /> - <link rel='stylesheet' href='/assets/css/fonts.css' /> - <link rel='stylesheet' href='/assets/css/css.css' /> - <link rel='stylesheet' href='/assets/css/leaflet.css' /> - <link rel='stylesheet' href='/assets/css/applets.css' /> - <link rel='stylesheet' href='/assets/css/mobile .css' /> -</head> -<body> - <header> - <a class='slogan' href="/"> - <div class='logo'></div> - <div class='site_name'>MegaPixels</div> - <div class='page_name'>CelebA Dataset</div> - </a> - <div class='links'> - <a href="/datasets/">Datasets</a> - <a href="/about/">About</a> - </div> - </header> - <div class="content content-dataset"> - - <section class='intro_section' style='background-image: url(https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/celeba/assets/background.jpg)'><div class='inner'><div class='hero_desc'><span class='bgpad'><span style="color:#ffaa00">CelebA</span> is a dataset of people...</span></div><div class='hero_subdesc'><span class='bgpad'>CelebA includes... -</span></div></div></section><section><h2>CelebA Dataset</h2> -</section><section><div class='right-sidebar'><div class='meta'> - <div class='gray'>Published</div> - <div>2015</div> - </div><div class='meta'> - <div class='gray'>Images</div> - <div>202,599 </div> - </div><div class='meta'> - <div class='gray'>Identities</div> - <div>10,177 </div> - </div><div class='meta'> - <div class='gray'>Purpose</div> - <div>face attribute recognition, face detection, and landmark (or facial part) localization</div> - </div><div class='meta'> - <div class='gray'>Download Size</div> - <div>1.4 GB</div> - </div><div class='meta'> - <div class='gray'>Website</div> - <div><a href='http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html' target='_blank' rel='nofollow noopener'>edu.hk</a></div> - </div></div><p>[ PAGE UNDER DEVELOPMENT ]</p> -</section><section> - <h3>Who used CelebA Dataset?</h3> - - <p> - This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. - </p> - - </section> - -<section class="applet_container"> -<!-- <div style="position: absolute;top: 0px;right: -55px;width: 180px;font-size: 14px;">Labeled Faces in the Wild Dataset<br><span class="numc" style="font-size: 11px;">20 citations</span> -</div> --> - <div class="applet" data-payload="{"command": "chart"}"></div> -</section> - -<section class="applet_container"> - <div class="applet" data-payload="{"command": "piechart"}"></div> -</section> - -<section> - - <h3>Biometric Trade Routes</h3> - - <p> - To help understand how CelebA Dataset has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Large-scale CelebFaces Attributes Dataset was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. - </p> - - </section> - -<section class="applet_container fullwidth"> - <div class="applet" data-payload="{"command": "map"}"></div> -</section> - -<div class="caption"> - <ul class="map-legend"> - <li class="edu">Academic</li> - <li class="com">Commercial</li> - <li class="gov">Military / Government</li> - </ul> - <div class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</div > -</div> - - -<section class="applet_container"> - - <h3>Dataset Citations</h3> - <p> - The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. If you use our data, please <a href="/about/attribution">cite our work</a>. - </p> - - <div class="applet" data-payload="{"command": "citations"}"></div> -</section><section><h3>Research</h3> -<ul> -<li>"An Unsupervised Approach to Solving Inverse Problems using Generative Adversarial Networks" mentions use by sponsored by an agency of the United States government. Neither the United States government nor Lawrence Livermore National Security, LLC, nor any of their"</li> -<li>7dab6fbf42f82f0f5730fc902f72c3fb628ef2f0</li> -<li>principal responsibility is ensuring the safety, security and reliability of the nation's nuclear weapons NNSA ( National Nuclear Security Administration )</li> -</ul> -</section> - - </div> - <footer> - <ul class="footer-left"> - <li><a href="/">MegaPixels.cc</a></li> - <li><a href="/datasets/">Datasets</a></li> - <li><a href="/about/">About</a></li> - <li><a href="/about/press/">Press</a></li> - <li><a href="/about/legal/">Legal and Privacy</a></li> - </ul> - <ul class="footer-right"> - <li>MegaPixels ©2017-19 <a href="https://ahprojects.com">Adam R. Harvey</a></li> - <li>Made with support from <a href="https://mozilla.org">Mozilla</a></li> - </ul> - </footer> -</body> - -<script src="/assets/js/dist/index.js"></script> -</html>
\ No newline at end of file diff --git a/site/public/datasets/cofw/index.html b/site/public/datasets/cofw/index.html deleted file mode 100644 index fd6d86ae..00000000 --- a/site/public/datasets/cofw/index.html +++ /dev/null @@ -1,180 +0,0 @@ -<!doctype html> -<html> -<head> - <title>MegaPixels</title> - <meta charset="utf-8" /> - <meta name="author" content="Adam Harvey" /> - <meta name="description" content="COFW: Caltech Occluded Faces in The Wild" /> - <meta name="referrer" content="no-referrer" /> - <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes" /> - <link rel='stylesheet' href='/assets/css/fonts.css' /> - <link rel='stylesheet' href='/assets/css/css.css' /> - <link rel='stylesheet' href='/assets/css/leaflet.css' /> - <link rel='stylesheet' href='/assets/css/applets.css' /> - <link rel='stylesheet' href='/assets/css/mobile .css' /> -</head> -<body> - <header> - <a class='slogan' href="/"> - <div class='logo'></div> - <div class='site_name'>MegaPixels</div> - <div class='page_name'>COFW Dataset</div> - </a> - <div class='links'> - <a href="/datasets/">Datasets</a> - <a href="/about/">About</a> - </div> - </header> - <div class="content content-"> - - <section><h2>Caltech Occluded Faces in the Wild</h2> -</section><section><div class='right-sidebar'><div class='meta'> - <div class='gray'>Published</div> - <div>2013</div> - </div><div class='meta'> - <div class='gray'>Images</div> - <div>1,007 </div> - </div><div class='meta'> - <div class='gray'>Purpose</div> - <div>challenging dataset (sunglasses, hats, interaction with objects)</div> - </div><div class='meta'> - <div class='gray'>Website</div> - <div><a href='http://www.vision.caltech.edu/xpburgos/ICCV13/' target='_blank' rel='nofollow noopener'>caltech.edu</a></div> - </div></div><p>[ PAGE UNDER DEVELOPMENT ]</p> -</section><section> - <h3>Who used COFW Dataset?</h3> - - <p> - This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. - </p> - - </section> - -<section class="applet_container"> -<!-- <div style="position: absolute;top: 0px;right: -55px;width: 180px;font-size: 14px;">Labeled Faces in the Wild Dataset<br><span class="numc" style="font-size: 11px;">20 citations</span> -</div> --> - <div class="applet" data-payload="{"command": "chart"}"></div> -</section> - -<section class="applet_container"> - <div class="applet" data-payload="{"command": "piechart"}"></div> -</section> - -<section> - - <h3>Biometric Trade Routes</h3> - - <p> - To help understand how COFW Dataset has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Caltech Occluded Faces in the Wild was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. - </p> - - </section> - -<section class="applet_container fullwidth"> - <div class="applet" data-payload="{"command": "map"}"></div> -</section> - -<div class="caption"> - <ul class="map-legend"> - <li class="edu">Academic</li> - <li class="com">Commercial</li> - <li class="gov">Military / Government</li> - </ul> - <div class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</div > -</div> - - -<section class="applet_container"> - - <h3>Dataset Citations</h3> - <p> - The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. If you use our data, please <a href="/about/attribution">cite our work</a>. - </p> - - <div class="applet" data-payload="{"command": "citations"}"></div> -</section><section><h3>(ignore) research notes</h3> -</section><section><div class='meta'><div><div class='gray'>Years</div><div>1993-1996</div></div><div><div class='gray'>Images</div><div>14,126</div></div><div><div class='gray'>Identities</div><div>1,199 </div></div><div><div class='gray'>Origin</div><div>Web Searches</div></div><div><div class='gray'>Funded by</div><div>ODNI, IARPA, Microsoft</div></div></div><section><section><p>COFW is "is designed to benchmark face landmark algorithms in realistic conditions, which include heavy occlusions and large shape variations" [Robust face landmark estimation under occlusion].</p> -<blockquote><p>We asked four people with different levels of computer vision knowledge to each collect 250 faces representative of typical real-world images, with the clear goal of challenging computer vision methods. -The result is 1,007 images of faces obtained from a variety of sources.</p> -</blockquote> -<p>Robust face landmark estimation under occlusion</p> -<blockquote><p>Our face dataset is designed to present faces in real-world conditions. Faces show large variations in shape and occlusions due to differences in pose, expression, use of accessories such as sunglasses and hats and interactions with objects (e.g. food, hands, microphones, etc.). All images were hand annotated in our lab using the same 29 landmarks as in LFPW. We annotated both the landmark positions as well as their occluded/unoccluded state. The faces are occluded to different degrees, with large variations in the type of occlusions encountered. COFW has an average occlusion of over 23%. -To increase the number of training images, and since COFW has the exact same landmarks as LFPW, for training we use the original non-augmented 845 LFPW faces + 500 COFW faces (1345 total), and for testing the remaining 507 COFW faces. To make sure all images had occlusion labels, we annotated occlusion on the available 845 LFPW training images, finding an average of only 2% occlusion.</p> -</blockquote> -<p><a href="http://www.vision.caltech.edu/xpburgos/ICCV13/">http://www.vision.caltech.edu/xpburgos/ICCV13/</a></p> -<blockquote><p>This research is supported by NSF Grant 0954083 and by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via IARPA R&D Contract No. 2014-14071600012.</p> -</blockquote> -<p><a href="https://www.cs.cmu.edu/~peiyunh/topdown/">https://www.cs.cmu.edu/~peiyunh/topdown/</a></p> -</section><section> - - <h3>Biometric Trade Routes</h3> - - <p> - To help understand how COFW Dataset has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Caltech Occluded Faces in the Wild was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the location markers to reveal research projects at that location. - </p> - - </section> - -<section class="applet_container fullwidth"> - <div class="applet" data-payload="{"command": "map"}"></div> -</section> - -<div class="caption"> - <ul class="map-legend"> - <li class="edu">Academic</li> - <li class="com">Commercial</li> - <li class="gov">Military / Government</li> - </ul> - <div class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> and then dataset usage verified and geolocated.</div > -</div><section> - - <div class="hr-wave-holder"> - <div class="hr-wave-line hr-wave-line1"></div> - <div class="hr-wave-line hr-wave-line2"></div> - </div> - - <h2>Supplementary Information</h2> - -</section><section class="applet_container"> - - <h3>Dataset Citations</h3> - <p> - The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. If you use our data, please <a href="/about/attribution">cite our work</a>. - </p> - - <div class="applet" data-payload="{"command": "citations"}"></div> -</section><section> - <h3>Who used COFW Dataset?</h3> - - <p> - This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. - </p> - - </section> - -<section class="applet_container"> -<!-- <div style="position: absolute;top: 0px;right: -55px;width: 180px;font-size: 14px;">Labeled Faces in the Wild Dataset<br><span class="numc" style="font-size: 11px;">20 citations</span> -</div> --> - <div class="applet" data-payload="{"command": "chart"}"></div> -</section><section><p>TODO</p> -<h2>- replace graphic</h2> -</section> - - </div> - <footer> - <ul class="footer-left"> - <li><a href="/">MegaPixels.cc</a></li> - <li><a href="/datasets/">Datasets</a></li> - <li><a href="/about/">About</a></li> - <li><a href="/about/press/">Press</a></li> - <li><a href="/about/legal/">Legal and Privacy</a></li> - </ul> - <ul class="footer-right"> - <li>MegaPixels ©2017-19 <a href="https://ahprojects.com">Adam R. Harvey</a></li> - <li>Made with support from <a href="https://mozilla.org">Mozilla</a></li> - </ul> - </footer> -</body> - -<script src="/assets/js/dist/index.js"></script> -</html>
\ No newline at end of file diff --git a/site/public/datasets/duke_mtmc/index.html b/site/public/datasets/duke_mtmc/index.html index 3655e1c9..adb81953 100644 --- a/site/public/datasets/duke_mtmc/index.html +++ b/site/public/datasets/duke_mtmc/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-dataset"> @@ -266,7 +267,7 @@ <section> - <h3>Biometric Trade Routes</h3> + <h3>Information Supply chain</h3> <p> To help understand how Duke MTMC Dataset has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Duke Multi-Target, Multi-Camera Tracking Project was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. diff --git a/site/public/datasets/feret/index.html b/site/public/datasets/feret/index.html deleted file mode 100644 index 88b025ae..00000000 --- a/site/public/datasets/feret/index.html +++ /dev/null @@ -1,138 +0,0 @@ -<!doctype html> -<html> -<head> - <title>MegaPixels</title> - <meta charset="utf-8" /> - <meta name="author" content="Adam Harvey" /> - <meta name="description" content="LFW: Labeled Faces in The Wild" /> - <meta name="referrer" content="no-referrer" /> - <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes" /> - <link rel='stylesheet' href='/assets/css/fonts.css' /> - <link rel='stylesheet' href='/assets/css/css.css' /> - <link rel='stylesheet' href='/assets/css/leaflet.css' /> - <link rel='stylesheet' href='/assets/css/applets.css' /> - <link rel='stylesheet' href='/assets/css/mobile .css' /> -</head> -<body> - <header> - <a class='slogan' href="/"> - <div class='logo'></div> - <div class='site_name'>MegaPixels</div> - <div class='page_name'>LFW</div> - </a> - <div class='links'> - <a href="/datasets/">Datasets</a> - <a href="/about/">About</a> - </div> - </header> - <div class="content content-"> - - <section><h1>FacE REcognition Dataset (FERET)</h1> -</section><section><div class='right-sidebar'><div class='meta'> - <div class='gray'>Published</div> - <div>2007</div> - </div><div class='meta'> - <div class='gray'>Images</div> - <div>13,233 </div> - </div><div class='meta'> - <div class='gray'>Identities</div> - <div>5,749 </div> - </div><div class='meta'> - <div class='gray'>Purpose</div> - <div>face recognition</div> - </div><div class='meta'> - <div class='gray'>Website</div> - <div><a href='http://vis-www.cs.umass.edu/lfw/' target='_blank' rel='nofollow noopener'>umass.edu</a></div> - </div></div><p>[ page under development ]</p> -</section><section> - <h3>Who used LFW?</h3> - - <p> - This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. - </p> - - </section> - -<section class="applet_container"> -<!-- <div style="position: absolute;top: 0px;right: -55px;width: 180px;font-size: 14px;">Labeled Faces in the Wild Dataset<br><span class="numc" style="font-size: 11px;">20 citations</span> -</div> --> - <div class="applet" data-payload="{"command": "chart"}"></div> -</section> - -<section class="applet_container"> - <div class="applet" data-payload="{"command": "piechart"}"></div> -</section> - -<section> - - <h3>Biometric Trade Routes</h3> - - <p> - To help understand how LFW has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Labeled Faces in the Wild was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. - </p> - - </section> - -<section class="applet_container fullwidth"> - <div class="applet" data-payload="{"command": "map"}"></div> -</section> - -<div class="caption"> - <ul class="map-legend"> - <li class="edu">Academic</li> - <li class="com">Commercial</li> - <li class="gov">Military / Government</li> - </ul> - <div class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</div > -</div> - - -<section class="applet_container"> - - <h3>Dataset Citations</h3> - <p> - The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. If you use our data, please <a href="/about/attribution">cite our work</a>. - </p> - - <div class="applet" data-payload="{"command": "citations"}"></div> -</section><section><h3>(ignore) RESEARCH below this line</h3> -<ul> -<li>Years: 1993-1996</li> -<li>Images: 14,126</li> -<li>Identities: 1,199 </li> -<li>Origin: Fairfax, MD</li> -<li><em>Facial Recognition Evaluation</em> (FERET) is develop, test, and evaluate face recognition algorithms</li> -<li>The goal of the FERET program was to develop automatic face recognition capabilities that could be employed to assist security, intelligence, and law enforcement personnel in the performance of their duties.</li> -<li><a href="https://www.nist.gov/programs-projects/face-recognition-technology-feret">https://www.nist.gov/programs-projects/face-recognition-technology-feret</a></li> -</ul> -<h3>"The FERET database and evaluation procedure for face-recognition algorithms"</h3> -<ul> -<li>Images were captured using Kodak Ultra film</li> -<li>The facial images were collected in 11 sessions from August 1993 to December 1994. Conducted at George Mason University and at US Army Research Laboratory facilities, </li> -</ul> -<h3>FERET (Face Recognition Technology) Recognition Algorithm Development and Test Results</h3> -<ul> -<li>"A release form is necessary because of the privacy laws in the United States."</li> -</ul> -<h2>Funding</h2> -<p>The FERET program is sponsored by the U.S. Depart- ment of Defense’s Counterdrug Technology Development Program Office. The U.S. Army Research Laboratory (ARL) is the technical agent for the FERET program. ARL designed, administered, and scored the FERET tests. George Mason University collected, processed, and main- tained the FERET database. Inquiries regarding the FERET database or test should be directed to P. Jonathon Phillips.</p> -</section> - - </div> - <footer> - <ul class="footer-left"> - <li><a href="/">MegaPixels.cc</a></li> - <li><a href="/datasets/">Datasets</a></li> - <li><a href="/about/">About</a></li> - <li><a href="/about/press/">Press</a></li> - <li><a href="/about/legal/">Legal and Privacy</a></li> - </ul> - <ul class="footer-right"> - <li>MegaPixels ©2017-19 <a href="https://ahprojects.com">Adam R. Harvey</a></li> - <li>Made with support from <a href="https://mozilla.org">Mozilla</a></li> - </ul> - </footer> -</body> - -<script src="/assets/js/dist/index.js"></script> -</html>
\ No newline at end of file diff --git a/site/public/datasets/hrt_transgender/index.html b/site/public/datasets/hrt_transgender/index.html index 3cc64826..4f046aa7 100644 --- a/site/public/datasets/hrt_transgender/index.html +++ b/site/public/datasets/hrt_transgender/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-dataset"> diff --git a/site/public/datasets/ijb_c/index.html b/site/public/datasets/ijb_c/index.html index f1457bbd..2b00e5d5 100644 --- a/site/public/datasets/ijb_c/index.html +++ b/site/public/datasets/ijb_c/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-dataset"> @@ -63,7 +64,7 @@ <div>21,294 </div> </div><div class='meta'> <div class='gray'>Videos</div> - <div>11,779 </div> + <div>11,799 </div> </div><div class='meta'> <div class='gray'>Identities</div> <div>3,531 </div> @@ -155,7 +156,7 @@ <section> - <h3>Biometric Trade Routes</h3> + <h3>Information Supply chain</h3> <p> To help understand how IJB-C has been used around the world by commercial, military, and academic organizations; existing publicly available research citing IARPA Janus Benchmark C was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. diff --git a/site/public/datasets/index.html b/site/public/datasets/index.html index 8a92beca..0a702c10 100644 --- a/site/public/datasets/index.html +++ b/site/public/datasets/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-"> @@ -56,7 +57,8 @@ <div class='dataset-heading'> <section><h1>Dataset Analyses</h1> -<p>Explore face and person recognition datasets contributing to the growing crisis of authoritarian biometric surveillance. This first group of 5 datasets focuses on image usage connected to foreign surveillance and defense organizations. Since publishing this project in April 2019, the <a href="https://purl.stanford.edu/sx925dc9385">Brainwash</a>, <a href="http://vision.cs.duke.edu/DukeMTMC/">Duke MTMC</a>, and <a href="http://msceleb.org/">MS Celeb</a> datasets have been taken down by their authors. The <a href="https://vast.uccs.edu/Opensetface/">UCCS</a> dataset was temporarily deactivated due to metadata exposure and the <a href="http://www.robots.ox.ac.uk/ActiveVision/Research/Projects/2009bbenfold_headpose/project.html">Town Centre data</a> remains active.</p> +<p>Explore face and person recognition datasets contributing to the growing crisis of authoritarian biometric surveillance. This first group of 5 datasets focuses on image usage connected to foreign surveillance and defense organizations.</p> +<p>Since publishing this project in April 2019, the <a href="https://purl.stanford.edu/sx925dc9385">Brainwash</a>, <a href="http://vision.cs.duke.edu/DukeMTMC/">Duke MTMC</a>, and <a href="http://msceleb.org/">MS Celeb</a> datasets have been taken down by their authors. The <a href="https://vast.uccs.edu/Opensetface/">UCCS</a> dataset was temporarily deactivated due to metadata exposure and the <a href="http://www.robots.ox.ac.uk/ActiveVision/Research/Projects/2009bbenfold_headpose/project.html">Town Centre data</a> remains active.</p> </section> </div> @@ -102,7 +104,7 @@ <div class='year visible'><span>2016</span></div> <div class='purpose'><span>Face recognition</span></div> - <div class='images'><span>10,000,000 images</span></div> + <div class='images'><span>8,200,000 images</span></div> </div> </div> diff --git a/site/public/datasets/lfpw/index.html b/site/public/datasets/lfpw/index.html deleted file mode 100644 index 68c3e033..00000000 --- a/site/public/datasets/lfpw/index.html +++ /dev/null @@ -1,117 +0,0 @@ -<!doctype html> -<html> -<head> - <title>MegaPixels</title> - <meta charset="utf-8" /> - <meta name="author" content="Adam Harvey" /> - <meta name="description" content="LFPW: Labeled Face Parts in The Wild" /> - <meta name="referrer" content="no-referrer" /> - <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes" /> - <link rel='stylesheet' href='/assets/css/fonts.css' /> - <link rel='stylesheet' href='/assets/css/css.css' /> - <link rel='stylesheet' href='/assets/css/leaflet.css' /> - <link rel='stylesheet' href='/assets/css/applets.css' /> - <link rel='stylesheet' href='/assets/css/mobile .css' /> -</head> -<body> - <header> - <a class='slogan' href="/"> - <div class='logo'></div> - <div class='site_name'>MegaPixels</div> - <div class='page_name'>LFWP</div> - </a> - <div class='links'> - <a href="/datasets/">Datasets</a> - <a href="/about/">About</a> - </div> - </header> - <div class="content content-"> - - <section><h2>Labeled Face Parts in The Wild</h2> -</section><section><div class='right-sidebar'><div class='meta'> - <div class='gray'>Published</div> - <div>2011</div> - </div><div class='meta'> - <div class='gray'>Funded by</div> - <div>CIA</div> - </div><div class='meta'> - <div class='gray'>Website</div> - <div><a href='http://neerajkumar.org/databases/lfpw/' target='_blank' rel='nofollow noopener'>neerajkumar.org</a></div> - </div></div></section><section> - <h3>Who used LFWP?</h3> - - <p> - This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. - </p> - - </section> - -<section class="applet_container"> -<!-- <div style="position: absolute;top: 0px;right: -55px;width: 180px;font-size: 14px;">Labeled Faces in the Wild Dataset<br><span class="numc" style="font-size: 11px;">20 citations</span> -</div> --> - <div class="applet" data-payload="{"command": "chart"}"></div> -</section> - -<section class="applet_container"> - <div class="applet" data-payload="{"command": "piechart"}"></div> -</section> - -<section> - - <h3>Biometric Trade Routes</h3> - - <p> - To help understand how LFWP has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Labeled Face Parts in the Wild was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. - </p> - - </section> - -<section class="applet_container fullwidth"> - <div class="applet" data-payload="{"command": "map"}"></div> -</section> - -<div class="caption"> - <ul class="map-legend"> - <li class="edu">Academic</li> - <li class="com">Commercial</li> - <li class="gov">Military / Government</li> - </ul> - <div class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</div > -</div> - - -<section class="applet_container"> - - <h3>Dataset Citations</h3> - <p> - The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. If you use our data, please <a href="/about/attribution">cite our work</a>. - </p> - - <div class="applet" data-payload="{"command": "citations"}"></div> -</section><section><p>RESEARCH below this line</p> -<blockquote><p>Release 1 of LFPW consists of 1,432 faces from images downloaded from the web using simple text queries on sites such as google.com, flickr.com, and yahoo.com. Each image was labeled by three MTurk workers, and 29 fiducial points, shown below, are included in dataset. LFPW was originally described in the following publication:</p> -<p>Due to copyright issues, we cannot distribute image files in any format to anyone. Instead, we have made available a list of image URLs where you can download the images yourself. We realize that this makes it impossible to exactly compare numbers, as image links will slowly disappear over time, but we have no other option. This seems to be the way other large web-based databases seem to be evolving.</p> -</blockquote> -<p><a href="https://neerajkumar.org/databases/lfpw/">https://neerajkumar.org/databases/lfpw/</a></p> -<blockquote><p>This research was performed at Kriegman-Belhumeur Vision Technologies and was funded by the CIA through the Office of the Chief Scientist. <a href="https://www.cs.cmu.edu/~peiyunh/topdown/">https://www.cs.cmu.edu/~peiyunh/topdown/</a> (nk_cvpr2011_faceparts.pdf)</p> -</blockquote> -</section> - - </div> - <footer> - <ul class="footer-left"> - <li><a href="/">MegaPixels.cc</a></li> - <li><a href="/datasets/">Datasets</a></li> - <li><a href="/about/">About</a></li> - <li><a href="/about/press/">Press</a></li> - <li><a href="/about/legal/">Legal and Privacy</a></li> - </ul> - <ul class="footer-right"> - <li>MegaPixels ©2017-19 <a href="https://ahprojects.com">Adam R. Harvey</a></li> - <li>Made with support from <a href="https://mozilla.org">Mozilla</a></li> - </ul> - </footer> -</body> - -<script src="/assets/js/dist/index.js"></script> -</html>
\ No newline at end of file diff --git a/site/public/datasets/lfw/index.html b/site/public/datasets/lfw/index.html deleted file mode 100644 index 7ae440a8..00000000 --- a/site/public/datasets/lfw/index.html +++ /dev/null @@ -1,167 +0,0 @@ -<!doctype html> -<html> -<head> - <title>MegaPixels</title> - <meta charset="utf-8" /> - <meta name="author" content="Adam Harvey" /> - <meta name="description" content="Labeled Faces in The Wild (LFW) is the first facial recognition dataset created entirely from online photos" /> - <meta name="referrer" content="no-referrer" /> - <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes" /> - <link rel='stylesheet' href='/assets/css/fonts.css' /> - <link rel='stylesheet' href='/assets/css/css.css' /> - <link rel='stylesheet' href='/assets/css/leaflet.css' /> - <link rel='stylesheet' href='/assets/css/applets.css' /> - <link rel='stylesheet' href='/assets/css/mobile .css' /> -</head> -<body> - <header> - <a class='slogan' href="/"> - <div class='logo'></div> - <div class='site_name'>MegaPixels</div> - <div class='page_name'>LFW</div> - </a> - <div class='links'> - <a href="/datasets/">Datasets</a> - <a href="/about/">About</a> - </div> - </header> - <div class="content content-"> - - <section class='intro_section' style='background-image: url(https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/lfw/assets/background.jpg)'><div class='inner'><div class='hero_desc'><span class='bgpad'><span class="dataset-name">Labeled Faces in The Wild (LFW)</span> is the first facial recognition dataset created entirely from online photos</span></div><div class='hero_subdesc'><span class='bgpad'>It includes 13,456 images of 4,432 people's images copied from the Internet during 2002-2004 and is the most frequently used dataset in the world for benchmarking face recognition algorithms. -</span></div></div></section><section><h2>Labeled Faces in the Wild</h2> -</section><section><div class='right-sidebar'><div class='meta'> - <div class='gray'>Published</div> - <div>2007</div> - </div><div class='meta'> - <div class='gray'>Images</div> - <div>13,233 </div> - </div><div class='meta'> - <div class='gray'>Identities</div> - <div>5,749 </div> - </div><div class='meta'> - <div class='gray'>Purpose</div> - <div>face recognition</div> - </div><div class='meta'> - <div class='gray'>Website</div> - <div><a href='http://vis-www.cs.umass.edu/lfw/' target='_blank' rel='nofollow noopener'>umass.edu</a></div> - </div></div><p>[ PAGE UNDER DEVELOPMENT ]</p> -<p><em>Labeled Faces in The Wild</em> (LFW) is "a database of face photographs designed for studying the problem of unconstrained face recognition<a class="footnote_shim" name="[^lfw_www]_1"> </a><a href="#[^lfw_www]" class="footnote" title="Footnote 1">1</a>. It is used to evaluate and improve the performance of facial recognition algorithms in academic, commercial, and government research. According to BiometricUpdate.com<a class="footnote_shim" name="[^lfw_pingan]_1"> </a><a href="#[^lfw_pingan]" class="footnote" title="Footnote 3">3</a>, LFW is "the most widely used evaluation set in the field of facial recognition, LFW attracts a few dozen teams from around the globe including Google, Facebook, Microsoft Research Asia, Baidu, Tencent, SenseTime, Face++ and Chinese University of Hong Kong."</p> -<p>The LFW dataset includes 13,233 images of 5,749 people that were collected between 2002-2004. LFW is a subset of <em>Names of Faces</em> and is part of the first facial recognition training dataset created entirely from images appearing on the Internet. The people appearing in LFW are...</p> -<p>The <em>Names and Faces</em> dataset was the first face recognition dataset created entire from online photos. However, <em>Names and Faces</em> and <em>LFW</em> are not the first face recognition dataset created entirely "in the wild". That title belongs to the <a href="/datasets/ucd_faces/">UCD dataset</a>. Images obtained "in the wild" means using an image without explicit consent or awareness from the subject or photographer.</p> -<p>The <em>Names and Faces</em> dataset was the first face recognition dataset created entire from online photos. However, <em>Names and Faces</em> and <em>LFW</em> are not the first face recognition dataset created entirely "in the wild". That title belongs to the <a href="/datasets/ucd_faces/">UCD dataset</a>. Images obtained "in the wild" means using an image without explicit consent or awareness from the subject or photographer.</p> -</section><section class='images'><div class='image'><img src='https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/lfw/assets/lfw_montage_all_crop.jpg' alt='All 5,379 people in the Labeled Faces in The Wild Dataset. Showing one face per person'><div class='caption'>All 5,379 people in the Labeled Faces in The Wild Dataset. Showing one face per person</div></div></section><section><p>The <em>Names and Faces</em> dataset was the first face recognition dataset created entire from online photos. However, <em>Names and Faces</em> and <em>LFW</em> are not the first face recognition dataset created entirely "in the wild". That title belongs to the <a href="/datasets/ucd_faces/">UCD dataset</a>. Images obtained "in the wild" means using an image without explicit consent or awareness from the subject or photographer.</p> -<p>The <em>Names and Faces</em> dataset was the first face recognition dataset created entire from online photos. However, <em>Names and Faces</em> and <em>LFW</em> are not the first face recognition dataset created entirely "in the wild". That title belongs to the <a href="/datasets/ucd_faces/">UCD dataset</a>. Images obtained "in the wild" means using an image without explicit consent or awareness from the subject or photographer.</p> -</section><section> - <h3>Who used LFW?</h3> - - <p> - This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. - </p> - - </section> - -<section class="applet_container"> -<!-- <div style="position: absolute;top: 0px;right: -55px;width: 180px;font-size: 14px;">Labeled Faces in the Wild Dataset<br><span class="numc" style="font-size: 11px;">20 citations</span> -</div> --> - <div class="applet" data-payload="{"command": "chart"}"></div> -</section> - -<section class="applet_container"> - <div class="applet" data-payload="{"command": "piechart"}"></div> -</section> - -<section> - - <h3>Biometric Trade Routes</h3> - - <p> - To help understand how LFW has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Labeled Faces in the Wild was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. - </p> - - </section> - -<section class="applet_container fullwidth"> - <div class="applet" data-payload="{"command": "map"}"></div> -</section> - -<div class="caption"> - <ul class="map-legend"> - <li class="edu">Academic</li> - <li class="com">Commercial</li> - <li class="gov">Military / Government</li> - </ul> - <div class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</div > -</div> - - -<section class="applet_container"> - - <h3>Dataset Citations</h3> - <p> - The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. If you use our data, please <a href="/about/attribution">cite our work</a>. - </p> - - <div class="applet" data-payload="{"command": "citations"}"></div> -</section><section> - - <div class="hr-wave-holder"> - <div class="hr-wave-line hr-wave-line1"></div> - <div class="hr-wave-line hr-wave-line2"></div> - </div> - - <h2>Supplementary Information</h2> - -</section><section><h3>Commercial Use</h3> -<p>Add a paragraph about how usage extends far beyond academia into research centers for largest companies in the world. And even funnels into CIA funded research in the US and defense industry usage in China.</p> -</section><section class='applet_container'><div class='applet' data-payload='{"command": "load_file assets/lfw_commercial_use.csv", "fields": ["name_display, company_url, example_url, country, description"]}'></div></section><section><h3>Research</h3> -<ul> -<li>"In our experiments, we used 10000 images and associated captions from the Faces in the wilddata set [3]."</li> -<li>"This work was supported in part by the Center for Intelligent Information Retrieval, the Central Intelligence Agency, the National Security Agency and National Science Foundation under CAREER award IIS-0546666 and grant IIS-0326249."</li> -<li>From: "People-LDA: Anchoring Topics to People using Face Recognition" <a href="https://www.semanticscholar.org/paper/People-LDA%3A-Anchoring-Topics-to-People-using-Face-Jain-Learned-Miller/10f17534dba06af1ddab96c4188a9c98a020a459">https://www.semanticscholar.org/paper/People-LDA%3A-Anchoring-Topics-to-People-using-Face-Jain-Learned-Miller/10f17534dba06af1ddab96c4188a9c98a020a459</a> and <a href="https://ieeexplore.ieee.org/document/4409055">https://ieeexplore.ieee.org/document/4409055</a></li> -<li>This paper was presented at IEEE 11th ICCV conference Oct 14-21 and the main LFW paper "Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments" was also published that same year</li> -<li>10f17534dba06af1ddab96c4188a9c98a020a459</li> -<li>This research is based upon work supported in part by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via contract number 2014-14071600010.</li> -<li>From "Labeled Faces in the Wild: Updates and New Reporting Procedures"</li> -<li>70% of people in the dataset have only 1 image and 29% have 2 or more images</li> -<li>The LFW dataset is considered the "most popular benchmark for face recognition" <a class="footnote_shim" name="[^lfw_baidu]_1"> </a><a href="#[^lfw_baidu]" class="footnote" title="Footnote 2">2</a></li> -<li>The LFW dataset is "the most widely used evaluation set in the field of facial recognition" <a class="footnote_shim" name="[^lfw_pingan]_2"> </a><a href="#[^lfw_pingan]" class="footnote" title="Footnote 3">3</a></li> -<li>All images in LFW dataset were obtained "in the wild" meaning without any consent from the subject or from the photographer</li> -<li>The faces in the LFW dataset were detected using the Viola-Jones haarcascade face detector [^lfw_website] [^lfw-survey]</li> -<li>The LFW dataset is used by several of the largest tech companies in the world including "Google, Facebook, Microsoft Research Asia, Baidu, Tencent, SenseTime, Face++ and Chinese University of Hong Kong." <a class="footnote_shim" name="[^lfw_pingan]_3"> </a><a href="#[^lfw_pingan]" class="footnote" title="Footnote 3">3</a></li> -<li>All images in the LFW dataset were copied from Yahoo News between 2002 - 2004</li> -<li>In 2014, two of the four original authors of the LFW dataset received funding from IARPA and ODNI for their followup paper <a href="https://www.semanticscholar.org/paper/Labeled-Faces-in-the-Wild-%3A-Updates-and-New-Huang-Learned-Miller/2d3482dcff69c7417c7b933f22de606a0e8e42d4">Labeled Faces in the Wild: Updates and New Reporting Procedures</a> via IARPA contract number 2014-14071600010</li> -<li>The dataset includes 2 images of <a href="http://vis-www.cs.umass.edu/lfw/person/George_Tenet.html">George Tenet</a>, the former Director of Central Intelligence (DCI) for the Central Intelligence Agency whose facial biometrics were eventually used to help train facial recognition software in China and Russia</li> -<li>./15/155205b8e288fd49bf203135871d66de879c8c04/paper.txt shows usage by DSTO Australia, supported parimal@iisc.ac.in</li> -</ul> -</section><section><div class='meta'><div><div class='gray'>Created</div><div>2002 – 2004</div></div><div><div class='gray'>Images</div><div>13,233</div></div><div><div class='gray'>Identities</div><div>5,749</div></div><div><div class='gray'>Origin</div><div>Yahoo! News Images</div></div><div><div class='gray'>Used by</div><div>Facebook, Google, Microsoft, Baidu, Tencent, SenseTime, Face++, CIA, NSA, IARPA</div></div><div><div class='gray'>Website</div><div><a href="http://vis-www.cs.umass.edu/lfw">umass.edu</a></div></div></div><section><section><ul> -<li>There are about 3 men for every 1 woman in the LFW dataset<a class="footnote_shim" name="[^lfw_www]_2"> </a><a href="#[^lfw_www]" class="footnote" title="Footnote 1">1</a></li> -<li>The person with the most images is <a href="http://vis-www.cs.umass.edu/lfw/person/George_W_Bush_comp.html">George W. Bush</a> with 530</li> -<li>There are about 3 George W. Bush's for every 1 <a href="http://vis-www.cs.umass.edu/lfw/person/Tony_Blair.html">Tony Blair</a></li> -<li>The LFW dataset includes over 500 actors, 30 models, 10 presidents, 124 basketball players, 24 football players, 11 kings, 7 queens, and 1 <a href="http://vis-www.cs.umass.edu/lfw/person/Moby.html">Moby</a></li> -<li>In all 3 of the LFW publications [^lfw_original_paper], [^lfw_survey], [^lfw_tech_report] the words "ethics", "consent", and "privacy" appear 0 times</li> -<li>The word "future" appears 71 times</li> -<li>* denotes partial funding for related research</li> -</ul> -</section><section><h3>References</h3><section><ul class="footnotes"><li>1 <a name="[^lfw_www]" class="footnote_shim"></a><span class="backlinks"><a href="#[^lfw_www]_1">a</a><a href="#[^lfw_www]_2">b</a></span><a href="http://vis-www.cs.umass.edu/lfw/results.html">http://vis-www.cs.umass.edu/lfw/results.html</a> -</li><li>2 <a name="[^lfw_baidu]" class="footnote_shim"></a><span class="backlinks"><a href="#[^lfw_baidu]_1">a</a></span>Jingtuo Liu, Yafeng Deng, Tao Bai, Zhengping Wei, Chang Huang. Targeting Ultimate Accuracy: Face Recognition via Deep Embedding. <a href="https://arxiv.org/abs/1506.07310">https://arxiv.org/abs/1506.07310</a> -</li><li>3 <a name="[^lfw_pingan]" class="footnote_shim"></a><span class="backlinks"><a href="#[^lfw_pingan]_1">a</a><a href="#[^lfw_pingan]_2">b</a><a href="#[^lfw_pingan]_3">c</a></span>Lee, Justin. "PING AN Tech facial recognition receives high score in latest LFW test results". BiometricUpdate.com. Feb 13, 2017. <a href="https://www.biometricupdate.com/201702/ping-an-tech-facial-recognition-receives-high-score-in-latest-lfw-test-results">https://www.biometricupdate.com/201702/ping-an-tech-facial-recognition-receives-high-score-in-latest-lfw-test-results</a> -</li></ul></section></section> - - </div> - <footer> - <ul class="footer-left"> - <li><a href="/">MegaPixels.cc</a></li> - <li><a href="/datasets/">Datasets</a></li> - <li><a href="/about/">About</a></li> - <li><a href="/about/press/">Press</a></li> - <li><a href="/about/legal/">Legal and Privacy</a></li> - </ul> - <ul class="footer-right"> - <li>MegaPixels ©2017-19 <a href="https://ahprojects.com">Adam R. Harvey</a></li> - <li>Made with support from <a href="https://mozilla.org">Mozilla</a></li> - </ul> - </footer> -</body> - -<script src="/assets/js/dist/index.js"></script> -</html>
\ No newline at end of file diff --git a/site/public/datasets/market_1501/index.html b/site/public/datasets/market_1501/index.html deleted file mode 100644 index 0415f969..00000000 --- a/site/public/datasets/market_1501/index.html +++ /dev/null @@ -1,133 +0,0 @@ -<!doctype html> -<html> -<head> - <title>MegaPixels</title> - <meta charset="utf-8" /> - <meta name="author" content="Adam Harvey" /> - <meta name="description" content="Market-1501 is a dataset is collection of CCTV footage from Tsinghua University" /> - <meta name="referrer" content="no-referrer" /> - <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes" /> - <link rel='stylesheet' href='/assets/css/fonts.css' /> - <link rel='stylesheet' href='/assets/css/css.css' /> - <link rel='stylesheet' href='/assets/css/leaflet.css' /> - <link rel='stylesheet' href='/assets/css/applets.css' /> - <link rel='stylesheet' href='/assets/css/mobile .css' /> -</head> -<body> - <header> - <a class='slogan' href="/"> - <div class='logo'></div> - <div class='site_name'>MegaPixels</div> - <div class='page_name'>Market 1501</div> - </a> - <div class='links'> - <a href="/datasets/">Datasets</a> - <a href="/about/">About</a> - </div> - </header> - <div class="content content-dataset"> - - <section class='intro_section' style='background-image: url(https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/market_1501/assets/background.jpg)'><div class='inner'><div class='hero_desc'><span class='bgpad'><span class="dataset-name">Market-1501</span> is a dataset is collection of CCTV footage from Tsinghua University</span></div><div class='hero_subdesc'><span class='bgpad'>The Market-1501 dataset includes 1,261 people from 5 HD surveillance cameras located on campus -</span></div></div></section><section><h2>Market-1501 Dataset</h2> -</section><section><div class='right-sidebar'><div class='meta'> - <div class='gray'>Published</div> - <div>2015</div> - </div><div class='meta'> - <div class='gray'>Images</div> - <div>32,668 </div> - </div><div class='meta'> - <div class='gray'>Identities</div> - <div>1,501 </div> - </div><div class='meta'> - <div class='gray'>Purpose</div> - <div>Person re-identification</div> - </div><div class='meta'> - <div class='gray'>Website</div> - <div><a href='http://www.liangzheng.org/Project/project_reid.html' target='_blank' rel='nofollow noopener'>liangzheng.org</a></div> - </div></div><p>[ PAGE UNDER DEVELOPMENT]</p> -</section><section> - <h3>Who used Market 1501?</h3> - - <p> - This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. - </p> - - </section> - -<section class="applet_container"> -<!-- <div style="position: absolute;top: 0px;right: -55px;width: 180px;font-size: 14px;">Labeled Faces in the Wild Dataset<br><span class="numc" style="font-size: 11px;">20 citations</span> -</div> --> - <div class="applet" data-payload="{"command": "chart"}"></div> -</section> - -<section class="applet_container"> - <div class="applet" data-payload="{"command": "piechart"}"></div> -</section> - -<section> - - <h3>Biometric Trade Routes</h3> - - <p> - To help understand how Market 1501 has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Market 1501 Dataset was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. - </p> - - </section> - -<section class="applet_container fullwidth"> - <div class="applet" data-payload="{"command": "map"}"></div> -</section> - -<div class="caption"> - <ul class="map-legend"> - <li class="edu">Academic</li> - <li class="com">Commercial</li> - <li class="gov">Military / Government</li> - </ul> - <div class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</div > -</div> - - -<section class="applet_container"> - - <h3>Dataset Citations</h3> - <p> - The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. If you use our data, please <a href="/about/attribution">cite our work</a>. - </p> - - <div class="applet" data-payload="{"command": "citations"}"></div> -</section><section><h2>(ignore) research Notes</h2> -<ul> -<li>"MARS is an extension of the Market-1501 dataset. During collection, we placed six near synchronized cameras in the campus of Tsinghua university. There were Five 1,080<em>1920 HD cameras and one 640</em>480 SD camera. MARS consists of 1,261 different pedestrians whom are captured by at least 2 cameras. Given a query tracklet, MARS aims to retrieve tracklets that contain the same ID." - main paper</li> -<li>bbox "0065C1T0002F0016.jpg", "0065" is the ID of the pedestrian. "C1" denotes the first -camera (there are totally 6 cameras). "T0002" means the 2th tracklet. "F016" is the 16th frame -within this tracklet. For the tracklets, their names are accumulated for each ID; but for frames, -they start from "F001" in each tracklet.</li> -</ul> -<p>@proceedings{zheng2016mars, -title={MARS: A Video Benchmark for Large-Scale Person Re-identification}, -author={Zheng, Liang and Bie, Zhi and Sun, Yifan and Wang, Jingdong and Su, Chi and Wang, Shengjin and Tian, Qi}, -booktitle={European Conference on Computer Vision}, -year={2016}, -organization={Springer} -}</p> -</section> - - </div> - <footer> - <ul class="footer-left"> - <li><a href="/">MegaPixels.cc</a></li> - <li><a href="/datasets/">Datasets</a></li> - <li><a href="/about/">About</a></li> - <li><a href="/about/press/">Press</a></li> - <li><a href="/about/legal/">Legal and Privacy</a></li> - </ul> - <ul class="footer-right"> - <li>MegaPixels ©2017-19 <a href="https://ahprojects.com">Adam R. Harvey</a></li> - <li>Made with support from <a href="https://mozilla.org">Mozilla</a></li> - </ul> - </footer> -</body> - -<script src="/assets/js/dist/index.js"></script> -</html>
\ No newline at end of file diff --git a/site/public/datasets/msceleb/assets/notes/index.html b/site/public/datasets/msceleb/assets/notes/index.html index 670b2df1..e9751129 100644 --- a/site/public/datasets/msceleb/assets/notes/index.html +++ b/site/public/datasets/msceleb/assets/notes/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-"> diff --git a/site/public/datasets/msceleb/index.html b/site/public/datasets/msceleb/index.html index 5cc9d4ba..8816e7ea 100644 --- a/site/public/datasets/msceleb/index.html +++ b/site/public/datasets/msceleb/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-dataset"> @@ -60,7 +61,7 @@ <div>2016</div> </div><div class='meta'> <div class='gray'>Images</div> - <div>10,000,000 </div> + <div>8,200,000 </div> </div><div class='meta'> <div class='gray'>Identities</div> <div>100,000 </div> @@ -76,12 +77,12 @@ </div><div class='meta'> <div class='gray'>Website</div> <div><a href='http://www.msceleb.org/' target='_blank' rel='nofollow noopener'>msceleb.org</a></div> - </div></div><p>Microsoft Celeb (MS Celeb or MS-Celeb-1M) is a dataset of 10 million face images harvested from the Internet for the purpose of developing face recognition technologies. According to Microsoft Research, who created and published the <a href="https://www.microsoft.com/en-us/research/publication/ms-celeb-1m-dataset-benchmark-large-scale-face-recognition-2/">dataset</a> in 2016, MS Celeb is the largest publicly available face recognition dataset in the world, containing over 10 million images of nearly 100,000 individuals. Microsoft's goal in building this dataset was to distribute an initial training dataset of 100,000 individuals' biometric data to accelerate research into recognizing a larger target list of one million people "using all the possibly collected face images of this individual on the web as training data".<a class="footnote_shim" name="[^msceleb_orig]_1"> </a><a href="#[^msceleb_orig]" class="footnote" title="Footnote 1">1</a></p> + </div></div><p>Microsoft Celeb (MS-Celeb-1M) is a dataset of 10 million face images harvested from the Internet for the purpose of developing face recognition technologies. According to Microsoft Research, who created and published the <a href="https://www.microsoft.com/en-us/research/publication/ms-celeb-1m-dataset-benchmark-large-scale-face-recognition-2/">dataset</a> in 2016, MS Celeb is the largest publicly available face recognition dataset in the world, containing over 10 million images of nearly 100,000 individuals. Microsoft's goal in building this dataset was to distribute an initial training dataset of 100,000 individuals' biometric data to accelerate research into recognizing a larger target list of one million people "using all the possibly collected face images of this individual on the web as training data".<a class="footnote_shim" name="[^msceleb_orig]_1"> </a><a href="#[^msceleb_orig]" class="footnote" title="Footnote 1">1</a></p> <p>While the majority of people in this dataset are American and British actors, the exploitative use of the term "celebrity" extends far beyond Hollywood. Many of the names in the MS Celeb face recognition dataset are merely people who must maintain an online presence for their professional lives: journalists, artists, musicians, activists, policy makers, writers, and academics. Many people in the target list are even vocal critics of the very technology Microsoft is using their name and biometric information to build. It includes digital rights activists like Jillian York; artists critical of surveillance including Trevor Paglen, Jill Magid, and Aram Bartholl; Intercept founders Laura Poitras, Jeremy Scahill, and Glenn Greenwald; Data and Society founder danah boyd; Shoshana Zuboff, author of <em>Surveillance Capitalism</em>; and even Julie Brill, the former FTC commissioner responsible for protecting consumer privacy.</p> <h3>Microsoft's 1 Million Target List</h3> -<p>Microsoft Research distributed two main digital assets: a dataset of approximately 10,000,000 images of 100,000 individuals and a target list of exactly 1 million names. The 900,000 names without images are the target list, which is used to gather more images for these individuals.</p> -<p>For example in a research project authored by researchers from SenseTime's Joint Lab at the Chinese University of Hong Kong called "<a href="https://arxiv.org/pdf/1809.01407.pdf">Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition</a>", approximately 7 million images from an additional 285,000 subjects were added to their dataset. The images were obtained by crawling the internet using the MS Celeb target list as the search query.</p> -<p>Below is a selection of 24 names from both the target list and image list curated to illustrate Microsoft's expansive and exploitative practice of scraping the Internet for biometric training data. Names with a number indicate how many images were distributed by Microsoft. Since publishing the analysis, Microsoft has quietly taken down their <a href="https://msceleb.org">msceleb.org</a> website but a partial list of the identifiers is still available on <a href="https://github.com/JinRC/C-MS-Celeb/">github.com/JinRC/C-MS-Celeb/</a>. The IDs are in the format "m.abc123" and can be accessed through <a href="https://developers.google.com/knowledge-graph/reference/rest/v1/">Google's Knowledge Graph</a> as "/m/abc123" to obtain the subject names.</p> +<p>Microsoft Research distributed two main digital assets: a dataset of approximately 10,000,000 images of 100,000 individuals and a target list of exactly 1 million names. The 900,000 names without images are the target list, which is used to gather more images for each subject.</p> +<p>For example in a research project authored by researchers from SenseTime's Joint Lab at the Chinese University of Hong Kong called "<a href="https://arxiv.org/pdf/1809.01407.pdf">Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition</a>", approximately 7 million images from an additional 285,000 subjects were added to their dataset. The images were obtained by crawling the internet using the MS Celeb target list as search queries.</p> +<p>Below is a selection of 24 names from both the target list and image list curated to illustrate Microsoft's expansive and exploitative practice of scraping the Internet for biometric training data for "celebrities". Names with a number indicate how many images were distributed by Microsoft. Since publishing the analysis, Microsoft has quietly taken down their <a href="https://msceleb.org">msceleb.org</a> website but a partial list of the identifiers is still available on <a href="https://github.com/JinRC/C-MS-Celeb/">github.com/JinRC/C-MS-Celeb/</a>. The IDs are in the format "m.abc123" and can be accessed through <a href="https://developers.google.com/knowledge-graph/reference/rest/v1/">Google's Knowledge Graph</a> as "/m/abc123" to obtain the subject names.</p> </section><section><div class='columns columns-2'><div class='column'><table> <thead><tr> <th>Name (images)</th> @@ -201,22 +202,21 @@ <p>Four more papers published by SenseTime that also use the MS Celeb dataset raise similar flags. SenseTime is a computer vision surveillance company that until <a href="https://uhrp.org/news-commentary/china%E2%80%99s-sensetime-sells-out-xinjiang-security-joint-venture">April 2019</a> provided surveillance to Chinese authorities to monitor and track Uighur Muslims in Xinjiang province, and had been <a href="https://www.nytimes.com/2019/04/14/technology/china-surveillance-artificial-intelligence-racial-profiling.html">flagged</a> numerous times as having potential links to human rights violations.</p> <p>One of the 4 SenseTime papers, "<a href="https://www.semanticscholar.org/paper/Exploring-Disentangled-Feature-Representation-Face-Liu-Wei/1fd5d08394a3278ef0a89639e9bfec7cb482e0bf">Exploring Disentangled Feature Representation Beyond Face Identification</a>", shows how SenseTime was developing automated face analysis technology to infer race, narrow eyes, nose size, and chin size, all of which could be used to target vulnerable ethnic groups based on their facial appearances, and using the MS Celeb dataset to build their technology.</p> <p>Earlier in 2019, Microsoft President and Chief Legal Officer <a href="https://blogs.microsoft.com/on-the-issues/2018/12/06/facial-recognition-its-time-for-action/">Brad Smith</a> called for the governmental regulation of face recognition, citing the potential for misuse, a rare admission that Microsoft's surveillance-driven business model had lost its bearing. More recently Smith also <a href="https://www.reuters.com/article/us-microsoft-ai/microsoft-turned-down-facial-recognition-sales-on-human-rights-concerns-idUSKCN1RS2FV">announced</a> that Microsoft would seemingly take a stand against such potential misuse, and had decided to not sell face recognition to an unnamed United States agency, citing a lack of accuracy. In effect, Microsoft's face recognition software was not suitable to be used on minorities because it was trained mostly on white male faces.</p> -<p>What the decision to block the sale announces is not so much that Microsoft had upgraded their ethics policy, but that Microsoft publicly acknowledged it can't sell a data-driven product without data. In other words, Microsoft can't sell face recognition if they don't have enough data to build it.</p> -<p>Until now, that data has been freely harvested from the Internet and packaged in training sets like MS Celeb, which are overwhelmingly <a href="https://www.nytimes.com/2018/02/09/technology/facial-recognition-race-artificial-intelligence.html">white</a> and <a href="https://gendershades.org">male</a>. Without balanced data, facial recognition contains blind spots. But without the large-scale datasets like MS Celeb, the powerful yet inaccurate facial recognition services like Microsoft's Azure Cognitive would be even less usable.</p> +<p>What the decision to block the sale announces is not so much that Microsoft had upgraded their ethics policy, but that Microsoft publicly acknowledged it can't sell a data-driven product without data. In other words, Microsoft can't sell face recognition if they don't have enough face training data to build it.</p> +<p>Until now, that data has been freely harvested from the Internet and packaged in training sets like MS Celeb, which are overwhelmingly <a href="https://www.nytimes.com/2018/02/09/technology/facial-recognition-race-artificial-intelligence.html">white</a> and <a href="https://gendershades.org">male</a>. Without balanced data, facial recognition contains blind spots. But without the large-scale datasets like MS Celeb, the powerful yet inaccurate facial recognition services like Microsoft Azure Cognitive would be even less usable.</p> </section><section class='images'><div class='image'><img src='https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/msceleb/assets/msceleb_montage.jpg' alt=' A visualization of 2,000 of the 100,000 identities included in the MS-Celeb-1M dataset distributed by Microsoft Research. License: Open Data Commons Public Domain Dedication (PDDL)'><div class='caption'> A visualization of 2,000 of the 100,000 identities included in the MS-Celeb-1M dataset distributed by Microsoft Research. License: Open Data Commons Public Domain Dedication (PDDL)</div></div></section><section><p>Microsoft didn't only create MS Celeb for other researchers to use, they also used it internally. In a publicly available 2017 Microsoft Research project called "<a href="https://www.microsoft.com/en-us/research/publication/one-shot-face-recognition-promoting-underrepresented-classes/">One-shot Face Recognition by Promoting Underrepresented Classes</a>," Microsoft used the MS Celeb face dataset to build their algorithms and advertise the results. Interestingly, Microsoft's <a href="https://www.microsoft.com/en-us/research/publication/one-shot-face-recognition-promoting-underrepresented-classes/">corporate version</a> of the paper does not mention they used the MS Celeb datset, but the <a href="https://www.semanticscholar.org/paper/One-shot-Face-Recognition-by-Promoting-Classes-Guo/6cacda04a541d251e8221d70ac61fda88fb61a70">open-access version</a> published on arxiv.org does. It states that Microsoft Research analyzed their algorithms using "the MS-Celeb-1M low-shot learning benchmark task."<a class="footnote_shim" name="[^one_shot]_1"> </a><a href="#[^one_shot]" class="footnote" title="Footnote 5">5</a></p> -<p>Typically researchers will phrase this differently and say they use data to validate their algorithm. But in reality neural network algorithms without data are only blueprints for how to use the data. Neural network algorithms are used to extract knowledge and distill it into an active format where it can be used for inference. Passing a face image through a face recognition neural network is to pass that image through the entire dataset.</p> +<p>Typically researchers will phrase this differently and say that they only use a dataset to validate their algorithm. But validation data can't be easily separated from the training process. To develop a neural network model, image training datasets are split into three parts: train, test, and validation. Training data is used to fit a model, and the validation and test data are used to provide feedback about the hyperparameters, biases, and outputs. In reality, test and validation data steers and influences the final results of neural networks.</p> <h2>Runaway Data</h2> -<p>Despite Microsoft's recent action to quietly shut down their large scale distribution of non-cooperative biometrics on the <a href="https://msceleb.org">MS Celeb</a> website, the dataset still exists in several repositories on GitHub, the hard drives of countless researchers, and will likely continue to be used in research projects around the world.</p> -<p>The most recent of which is a paper uploaded to arxiv.org on April 2, 2019 jointly authored by researchers from IIIT-Delhi and IBM TJ Watson Research Center. In their paper titled <a href="https://arxiv.org/abs/1904.01219">Deep Learning for Face Recognition: Pride or Prejudiced?</a>, the researchers use a new dataset, called <em>Racial Faces in the Wild</em> (RFW), made entirely from the original images of the MS Celeb dataset. To create it, the RFW authors uploaded everyone's image from the MS Celeb dataset to Face++ and used the inferred racial scores to segregate people into four subsets: Caucasian, Asian, Indian, and African each with 3,000 subjects.</p> -<p>Face++ is a face recognition product from Megvii Inc. who has been repeatedly linked to the oppressive surveillance of Uighur Muslims in Xinjiang, China. According to posts from the <a href="https://chinai.substack.com/p/chinai-newsletter-11-companies-involved-in-expanding-chinas-public-security-apparatus-in-xinjiang">ChinAI Newsletter</a> and <a href="https://www.buzzfeednews.com/article/ryanmac/us-money-funding-facial-recognition-sensetime-megvii">BuzzFeedNews</a>, Megvii announced in 2017 at the China-Eurasia Security Expo in Ürümqi, Xinjiang, that it would be the official technical support unit of the "Public Security Video Laboratory" in Xinjiang, China.</p> +<p>Despite the recent termination of the <a href="https://msceleb.org">msceleb.org</a> website, the dataset still exists in several repositories on GitHub, the hard drives of countless researchers, and will likely continue to be used in research projects around the world.</p> +<p>For example, on October 28, 2019, the MS Celeb dataset will be used for a new competition called "<a href="https://ibug.doc.ic.ac.uk/resources/lightweight-face-recognition-challenge-workshop/">Lightweight Face Recognition Challenge & Workshop</a>" where the best face recognition entries will be awarded $5,000 from Huawei and $3,000 from DeepGlint. The competition is part of the <a href="http://iccv2019.thecvf.com/program/workshops">ICCV 2019 conference</a>. This time the challenge is no longer being organized by Microsoft, who created the dataset, but instead by Imperial College London (UK) and <a href="https://github.com/deepinsight/insightface">InsightFace</a> (CN).</p> +<p>And earlier in 2019 images from the MS Celeb were repackaged into another face dataset called <em>Racial Faces in the Wild (RFW)</em>. To create it, the RFW authors uploaded face images from the MS Celeb dataset to the Face++ API and used the inferred racial scores to segregate people into four subsets: Caucasian, Asian, Indian, and African each with 3,000 subjects. That dataset then appeared in a subsequent research project from researchers affiliated with IIIT-Delhi and IBM TJ Watson called <a href="https://arxiv.org/abs/1904.01219">Deep Learning for Face Recognition: Pride or Prejudiced?</a>, which aims to reduce bias but also inadvertently furthers racist language and ideologies in the paper.</p> +<p>The technology that was used to compute the estimated racial scores for the MS Celeb face images used in the RFW dataset, Face++, is owned by Megvii Inc, who has been repeatedly linked to the oppressive surveillance of Uighur Muslims in Xinjiang, China. According to posts from the <a href="https://chinai.substack.com/p/chinai-newsletter-11-companies-involved-in-expanding-chinas-public-security-apparatus-in-xinjiang">ChinAI Newsletter</a> and <a href="https://www.buzzfeednews.com/article/ryanmac/us-money-funding-facial-recognition-sensetime-megvii">BuzzFeedNews</a>, Megvii announced in 2017 at the China-Eurasia Security Expo in Ürümqi, Xinjiang, that it would be the official technical support unit of the "Public Security Video Laboratory" in Xinjiang, China. If they didn't already, it's highly likely that Megvii has a copy of everyone's biometric faceprint from the MS Celeb dataset.</p> +<p>Megvii also publicly acknowledges using the MS Celeb face dataset in their 2018 research project called <a href="https://arxiv.org/pdf/1808.06210.pdf">GridFace: Face Rectification via Learning Local Homography Transformations</a>. The paper has three authors, all of whom were associated with Megvii.</p> <h2>Commercial Usage</h2> -<p>Megvii publicly acknowledges using the MS Celeb face dataset in their 2018 research project called <a href="https://arxiv.org/pdf/1808.06210.pdf">GridFace: Face Rectification via Learning Local Homography Transformations</a>. The paper has three authors, all of whom were associated with Megvii, indicating that the dataset has been used for research associated with commercial activity. However, on Microsoft's <a href="http://web.archive.org/web/20180218212120/http://www.msceleb.org/download/sampleset">website</a> they state that the dataset was released "for non-commercial research purpose only."</p> -<p>A more clear example of commercial use happened in 2017 when Microsoft Research organized a face recognition competition at the International Conference on Computer Vision (ICCV), one of the top 2 computer vision conferences worldwide, where industry and academia compete to achieve the highest performance using their recognition technology. In 2017, the winner of the MS-Celeb-1M challenge was Beijing-based OrionStar Technology Co., Ltd.. In their <a href="https://www.prnewswire.com/news-releases/orionstar-wins-challenge-to-recognize-one-million-celebrity-faces-with-artificial-intelligence-300494265.html">press release</a>, OrionStar boast 13% increase on the difficult set over last year's winner.</p> -<p>Microsoft Research also ran a similar competition in 2016 that with other commercial participants including Beijing Faceall Technology Co., Ltd., a company providing face recognition for "smart city" applications.</p> -<p>On October 28, 2019, the MS Celeb dataset will be used for yet competition called "<a href="https://ibug.doc.ic.ac.uk/resources/lightweight-face-recognition-challenge-workshop/">Lightweight Face Recognition Challenge & Workshop</a>" where the best face recognition entry will be awarded $5,000 from Huawei and $3,000 from DeepGlint. The competition is part of the <a href="http://iccv2019.thecvf.com/program/workshops">ICCV 2019 conference</a>. This time the challenge is no longer being organized by Microsoft, who created the dataset, but instead by Imperial College London (UK) and <a href="https://github.com/deepinsight/insightface">InsightFace</a> (CN).</p> -<p>Even though Microsoft has shuttered access to the official distribution website <a href="https://msceleb.org">msceleb.org</a> the dataset can still be easily downloaded from <a href="https://ibug.doc.ic.ac.uk/resources/lightweight-face-recognition-challenge-workshop/">https://ibug.doc.ic.ac.uk/resources/lightweight-face-recognition-challenge-workshop/</a> without agreeing to any terms for usage or further distribution.</p> -<p>Considering the multiple citations from commercial organizations (Canon, Hitachi, IBM, Megvii, Microsoft, Microsoft Asia, SenseTime), military use (National University of Defense Technology in China), and the proliferation of subsets being used for new face recognition competitions it's fairly clear that Microsoft is no longer in control of their MS Celeb dataset nor the biometric data of nearly 10 million images of 100,000 individuals whose images were distributed in the dataset.</p> -<p>To provide insight into where these 10 million faces images have traveled, we mapped all the publicly available research citations to show who used the dataset and where it was used.</p> +<p>The Microsoft Celeb dataset <a href="http://web.archive.org/web/20180218212120/http://www.msceleb.org/download/sampleset">website</a> says it was created for "non-commercial research purpose only." Publicly available research citations and competitions show otherwise.</p> +<p>In 2017 Microsoft Research organized a face recognition competition at the International Conference on Computer Vision (ICCV), one of the top 2 computer vision conferences worldwide, where industry and academia used the MS Celeb dataset to compete for the highest performance scores. The 2017 winner was Beijing-based OrionStar Technology Co., Ltd.. In their <a href="https://www.prnewswire.com/news-releases/orionstar-wins-challenge-to-recognize-one-million-celebrity-faces-with-artificial-intelligence-300494265.html">press release</a>, OrionStar boasted a 13% increase on the difficult set over last year's winner. The prior year's competitors included Beijing-based Faceall Technology Co., Ltd., a company providing face recognition for "smart city" applications.</p> +<p>Considering the multiple citations from commercial organizations (Canon, Hitachi, IBM, Megvii/Face++, Microsoft, Microsoft Asia, SenseTime), military use (National University of Defense Technology in China), and the proliferation of subset data (Racial Faces in the Wild) being used to develop face recognition technology for commercial or defense purposes it's fairly clear that Microsoft has lost control of their MS Celeb dataset and biometric data of nearly 100,000 individuals.</p> +<p>To provide insight into where these 10 million faces images have traveled, over 100 research papers have been verified and geolocated to show who used the dataset and where they used it.</p> </section><section> <h3>Who used Microsoft Celeb?</h3> @@ -238,7 +238,7 @@ <section> - <h3>Biometric Trade Routes</h3> + <h3>Information Supply chain</h3> <p> To help understand how Microsoft Celeb has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Microsoft Celebrity Dataset was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. diff --git a/site/public/datasets/oxford_town_centre/index.html b/site/public/datasets/oxford_town_centre/index.html index fd554809..f77b6b08 100644 --- a/site/public/datasets/oxford_town_centre/index.html +++ b/site/public/datasets/oxford_town_centre/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-dataset"> @@ -99,7 +100,7 @@ <section> - <h3>Biometric Trade Routes</h3> + <h3>Information Supply chain</h3> <p> To help understand how TownCentre has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Oxford Town Centre was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. diff --git a/site/public/datasets/pipa/index.html b/site/public/datasets/pipa/index.html deleted file mode 100644 index 065f3e47..00000000 --- a/site/public/datasets/pipa/index.html +++ /dev/null @@ -1,121 +0,0 @@ -<!doctype html> -<html> -<head> - <title>MegaPixels</title> - <meta charset="utf-8" /> - <meta name="author" content="Adam Harvey" /> - <meta name="description" content=" People in Photo Albums (PIPA) is a dataset..." /> - <meta name="referrer" content="no-referrer" /> - <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes" /> - <link rel='stylesheet' href='/assets/css/fonts.css' /> - <link rel='stylesheet' href='/assets/css/css.css' /> - <link rel='stylesheet' href='/assets/css/leaflet.css' /> - <link rel='stylesheet' href='/assets/css/applets.css' /> - <link rel='stylesheet' href='/assets/css/mobile .css' /> -</head> -<body> - <header> - <a class='slogan' href="/"> - <div class='logo'></div> - <div class='site_name'>MegaPixels</div> - <div class='page_name'>PIPA Dataset</div> - </a> - <div class='links'> - <a href="/datasets/">Datasets</a> - <a href="/about/">About</a> - </div> - </header> - <div class="content content-dataset"> - - <section class='intro_section' style='background-image: url(https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/pipa/assets/background.jpg)'><div class='inner'><div class='hero_desc'><span class='bgpad'><span class="dataset-name"> People in Photo Albums (PIPA)</span> is a dataset...</span></div><div class='hero_subdesc'><span class='bgpad'>[ add subdescrition ] -</span></div></div></section><section><h2>People in Photo Albums</h2> -</section><section><div class='right-sidebar'><div class='meta'> - <div class='gray'>Published</div> - <div>2015</div> - </div><div class='meta'> - <div class='gray'>Images</div> - <div>37,107 </div> - </div><div class='meta'> - <div class='gray'>Identities</div> - <div>2,356 </div> - </div><div class='meta'> - <div class='gray'>Purpose</div> - <div>Face recognition</div> - </div><div class='meta'> - <div class='gray'>Download Size</div> - <div>12 GB</div> - </div><div class='meta'> - <div class='gray'>Website</div> - <div><a href='https://people.eecs.berkeley.edu/~nzhang/piper.html' target='_blank' rel='nofollow noopener'>berkeley.edu</a></div> - </div></div><p>[ PAGE UNDER DEVELOPMENT ]</p> -</section><section> - <h3>Who used PIPA Dataset?</h3> - - <p> - This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. - </p> - - </section> - -<section class="applet_container"> -<!-- <div style="position: absolute;top: 0px;right: -55px;width: 180px;font-size: 14px;">Labeled Faces in the Wild Dataset<br><span class="numc" style="font-size: 11px;">20 citations</span> -</div> --> - <div class="applet" data-payload="{"command": "chart"}"></div> -</section> - -<section class="applet_container"> - <div class="applet" data-payload="{"command": "piechart"}"></div> -</section> - -<section> - - <h3>Biometric Trade Routes</h3> - - <p> - To help understand how PIPA Dataset has been used around the world by commercial, military, and academic organizations; existing publicly available research citing People in Photo Albums Dataset was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. - </p> - - </section> - -<section class="applet_container fullwidth"> - <div class="applet" data-payload="{"command": "map"}"></div> -</section> - -<div class="caption"> - <ul class="map-legend"> - <li class="edu">Academic</li> - <li class="com">Commercial</li> - <li class="gov">Military / Government</li> - </ul> - <div class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</div > -</div> - - -<section class="applet_container"> - - <h3>Dataset Citations</h3> - <p> - The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. If you use our data, please <a href="/about/attribution">cite our work</a>. - </p> - - <div class="applet" data-payload="{"command": "citations"}"></div> -</section> - - </div> - <footer> - <ul class="footer-left"> - <li><a href="/">MegaPixels.cc</a></li> - <li><a href="/datasets/">Datasets</a></li> - <li><a href="/about/">About</a></li> - <li><a href="/about/press/">Press</a></li> - <li><a href="/about/legal/">Legal and Privacy</a></li> - </ul> - <ul class="footer-right"> - <li>MegaPixels ©2017-19 <a href="https://ahprojects.com">Adam R. Harvey</a></li> - <li>Made with support from <a href="https://mozilla.org">Mozilla</a></li> - </ul> - </footer> -</body> - -<script src="/assets/js/dist/index.js"></script> -</html>
\ No newline at end of file diff --git a/site/public/datasets/pubfig/index.html b/site/public/datasets/pubfig/index.html deleted file mode 100644 index 79644e40..00000000 --- a/site/public/datasets/pubfig/index.html +++ /dev/null @@ -1,118 +0,0 @@ -<!doctype html> -<html> -<head> - <title>MegaPixels</title> - <meta charset="utf-8" /> - <meta name="author" content="Adam Harvey" /> - <meta name="description" content="PubFig is a dataset..." /> - <meta name="referrer" content="no-referrer" /> - <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes" /> - <link rel='stylesheet' href='/assets/css/fonts.css' /> - <link rel='stylesheet' href='/assets/css/css.css' /> - <link rel='stylesheet' href='/assets/css/leaflet.css' /> - <link rel='stylesheet' href='/assets/css/applets.css' /> - <link rel='stylesheet' href='/assets/css/mobile .css' /> -</head> -<body> - <header> - <a class='slogan' href="/"> - <div class='logo'></div> - <div class='site_name'>MegaPixels</div> - <div class='page_name'>PubFig</div> - </a> - <div class='links'> - <a href="/datasets/">Datasets</a> - <a href="/about/">About</a> - </div> - </header> - <div class="content content-dataset"> - - <section class='intro_section' style='background-image: url(https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/pubfig/assets/background.jpg)'><div class='inner'><div class='hero_desc'><span class='bgpad'><span class="dataset-name">PubFig</span> is a dataset...</span></div><div class='hero_subdesc'><span class='bgpad'>[ add subdescrition ] -</span></div></div></section><section><h2>PubFig</h2> -</section><section><div class='right-sidebar'><div class='meta'> - <div class='gray'>Published</div> - <div>2009</div> - </div><div class='meta'> - <div class='gray'>Images</div> - <div>58,797 </div> - </div><div class='meta'> - <div class='gray'>Identities</div> - <div>200 </div> - </div><div class='meta'> - <div class='gray'>Purpose</div> - <div>mostly names from LFW but includes new names. large variation in pose, lighting, expression, scene, camera, imaging conditions and parameters</div> - </div><div class='meta'> - <div class='gray'>Website</div> - <div><a href='http://www.cs.columbia.edu/CAVE/databases/pubfig/' target='_blank' rel='nofollow noopener'>columbia.edu</a></div> - </div></div><p>[ PAGE UNDER DEVELOPMENT ]</p> -</section><section> - <h3>Who used PubFig?</h3> - - <p> - This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. - </p> - - </section> - -<section class="applet_container"> -<!-- <div style="position: absolute;top: 0px;right: -55px;width: 180px;font-size: 14px;">Labeled Faces in the Wild Dataset<br><span class="numc" style="font-size: 11px;">20 citations</span> -</div> --> - <div class="applet" data-payload="{"command": "chart"}"></div> -</section> - -<section class="applet_container"> - <div class="applet" data-payload="{"command": "piechart"}"></div> -</section> - -<section> - - <h3>Biometric Trade Routes</h3> - - <p> - To help understand how PubFig has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Public Figures Face Dataset was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. - </p> - - </section> - -<section class="applet_container fullwidth"> - <div class="applet" data-payload="{"command": "map"}"></div> -</section> - -<div class="caption"> - <ul class="map-legend"> - <li class="edu">Academic</li> - <li class="com">Commercial</li> - <li class="gov">Military / Government</li> - </ul> - <div class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</div > -</div> - - -<section class="applet_container"> - - <h3>Dataset Citations</h3> - <p> - The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. If you use our data, please <a href="/about/attribution">cite our work</a>. - </p> - - <div class="applet" data-payload="{"command": "citations"}"></div> -</section> - - </div> - <footer> - <ul class="footer-left"> - <li><a href="/">MegaPixels.cc</a></li> - <li><a href="/datasets/">Datasets</a></li> - <li><a href="/about/">About</a></li> - <li><a href="/about/press/">Press</a></li> - <li><a href="/about/legal/">Legal and Privacy</a></li> - </ul> - <ul class="footer-right"> - <li>MegaPixels ©2017-19 <a href="https://ahprojects.com">Adam R. Harvey</a></li> - <li>Made with support from <a href="https://mozilla.org">Mozilla</a></li> - </ul> - </footer> -</body> - -<script src="/assets/js/dist/index.js"></script> -</html>
\ No newline at end of file diff --git a/site/public/datasets/uccs/assets/notes/index.html b/site/public/datasets/uccs/assets/notes/index.html index 3f7843cf..8746ed70 100644 --- a/site/public/datasets/uccs/assets/notes/index.html +++ b/site/public/datasets/uccs/assets/notes/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-"> diff --git a/site/public/datasets/uccs/index.html b/site/public/datasets/uccs/index.html index 1674ae64..0ece4c6e 100644 --- a/site/public/datasets/uccs/index.html +++ b/site/public/datasets/uccs/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-dataset"> @@ -105,7 +106,7 @@ Their setup made it impossible for students to know they were being photographed <section> - <h3>Biometric Trade Routes</h3> + <h3>Information Supply chain</h3> <p> To help understand how UCCS has been used around the world by commercial, military, and academic organizations; existing publicly available research citing UnConstrained College Students Dataset was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. diff --git a/site/public/datasets/vgg_face2/index.html b/site/public/datasets/vgg_face2/index.html deleted file mode 100644 index 7844f5f4..00000000 --- a/site/public/datasets/vgg_face2/index.html +++ /dev/null @@ -1,143 +0,0 @@ -<!doctype html> -<html> -<head> - <title>MegaPixels</title> - <meta charset="utf-8" /> - <meta name="author" content="Adam Harvey" /> - <meta name="description" content="VGG Face 2 Dataset" /> - <meta name="referrer" content="no-referrer" /> - <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes" /> - <link rel='stylesheet' href='/assets/css/fonts.css' /> - <link rel='stylesheet' href='/assets/css/css.css' /> - <link rel='stylesheet' href='/assets/css/leaflet.css' /> - <link rel='stylesheet' href='/assets/css/applets.css' /> - <link rel='stylesheet' href='/assets/css/mobile .css' /> -</head> -<body> - <header> - <a class='slogan' href="/"> - <div class='logo'></div> - <div class='site_name'>MegaPixels</div> - <div class='page_name'>Brainwash Dataset</div> - </a> - <div class='links'> - <a href="/datasets/">Datasets</a> - <a href="/about/">About</a> - </div> - </header> - <div class="content content-"> - - <section><h2>VGG Face 2</h2> -</section><section><div class='right-sidebar'><div class='meta'> - <div class='gray'>Published</div> - <div>2015</div> - </div><div class='meta'> - <div class='gray'>Images</div> - <div>11,917 </div> - </div><div class='meta'> - <div class='gray'>Purpose</div> - <div>Head detection</div> - </div><div class='meta'> - <div class='gray'>Created by</div> - <div>Stanford University (US), Max Planck Institute for Informatics (DE)</div> - </div><div class='meta'> - <div class='gray'>Funded by</div> - <div>Max Planck Center for Visual Computing and Communication</div> - </div><div class='meta'> - <div class='gray'>Download Size</div> - <div>4.1 GB</div> - </div><div class='meta'> - <div class='gray'>Website</div> - <div><a href='https://purl.stanford.edu/sx925dc9385' target='_blank' rel='nofollow noopener'>stanford.edu</a></div> - </div></div><p>[ page under development ]</p> -</section><section> - <h3>Who used Brainwash Dataset?</h3> - - <p> - This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. - </p> - - </section> - -<section class="applet_container"> -<!-- <div style="position: absolute;top: 0px;right: -55px;width: 180px;font-size: 14px;">Labeled Faces in the Wild Dataset<br><span class="numc" style="font-size: 11px;">20 citations</span> -</div> --> - <div class="applet" data-payload="{"command": "chart"}"></div> -</section> - -<section class="applet_container"> - <div class="applet" data-payload="{"command": "piechart"}"></div> -</section> - -<section> - - <h3>Biometric Trade Routes</h3> - - <p> - To help understand how Brainwash Dataset has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Brainwash Dataset was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. - </p> - - </section> - -<section class="applet_container fullwidth"> - <div class="applet" data-payload="{"command": "map"}"></div> -</section> - -<div class="caption"> - <ul class="map-legend"> - <li class="edu">Academic</li> - <li class="com">Commercial</li> - <li class="gov">Military / Government</li> - </ul> - <div class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</div > -</div> - - -<section class="applet_container"> - - <h3>Dataset Citations</h3> - <p> - The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. If you use our data, please <a href="/about/attribution">cite our work</a>. - </p> - - <div class="applet" data-payload="{"command": "citations"}"></div> -</section><section><h3>(ignore) research notes</h3> -<ul> -<li>The VGG Face 2 dataset includes approximately 1,331 actresses, 139 presidents, 16 wives, 3 husbands, 2 snooker player, and 1 guru</li> -<li>The original VGGF2 name list has been updated with the results returned from Google Knowledge</li> -<li>Names with a similarity score greater than 0.75 where automatically updated. Scores computed using <code>import difflib; seq = difflib.SequenceMatcher(a=a.lower(), b=b.lower()); score = seq.ratio()</code></li> -<li>The 97 names with a score of 0.75 or lower were manually reviewed and includes name changes validating using Wikipedia.org results for names such as "Bruce Jenner" to "Caitlyn Jenner", spousal last-name changes, and discretionary changes to improve search results such as combining nicknames with full name when appropriate, for example changing "Aleksandar Petrović" to "Aleksandar 'Aco' Petrović" and minor changes such as "Mohammad Ali" to "Muhammad Ali"</li> -<li>The 'Description' text was automatically added when the Knowledge Graph score was greater than 250</li> -</ul> -<h2>TODO</h2> -<ul> -<li>create name list, and populate with Knowledge graph information like LFW</li> -<li>make list of interesting number stats, by the numbers</li> -<li>make list of interesting important facts</li> -<li>write intro abstract</li> -<li>write analysis of usage</li> -<li>find examples, citations, and screenshots of useage</li> -<li>find list of companies using it for table</li> -<li>create montages of the dataset, like LFW</li> -<li>create right to removal information</li> -</ul> -</section> - - </div> - <footer> - <ul class="footer-left"> - <li><a href="/">MegaPixels.cc</a></li> - <li><a href="/datasets/">Datasets</a></li> - <li><a href="/about/">About</a></li> - <li><a href="/about/press/">Press</a></li> - <li><a href="/about/legal/">Legal and Privacy</a></li> - </ul> - <ul class="footer-right"> - <li>MegaPixels ©2017-19 <a href="https://ahprojects.com">Adam R. Harvey</a></li> - <li>Made with support from <a href="https://mozilla.org">Mozilla</a></li> - </ul> - </footer> -</body> - -<script src="/assets/js/dist/index.js"></script> -</html>
\ No newline at end of file diff --git a/site/public/datasets/viper/index.html b/site/public/datasets/viper/index.html deleted file mode 100644 index 320899ea..00000000 --- a/site/public/datasets/viper/index.html +++ /dev/null @@ -1,123 +0,0 @@ -<!doctype html> -<html> -<head> - <title>MegaPixels</title> - <meta charset="utf-8" /> - <meta name="author" content="Adam Harvey" /> - <meta name="description" content="VIPeR is a person re-identification dataset of images captured at UC Santa Cruz in 2007" /> - <meta name="referrer" content="no-referrer" /> - <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes" /> - <link rel='stylesheet' href='/assets/css/fonts.css' /> - <link rel='stylesheet' href='/assets/css/css.css' /> - <link rel='stylesheet' href='/assets/css/leaflet.css' /> - <link rel='stylesheet' href='/assets/css/applets.css' /> - <link rel='stylesheet' href='/assets/css/mobile .css' /> -</head> -<body> - <header> - <a class='slogan' href="/"> - <div class='logo'></div> - <div class='site_name'>MegaPixels</div> - <div class='page_name'>VIPeR</div> - </a> - <div class='links'> - <a href="/datasets/">Datasets</a> - <a href="/about/">About</a> - </div> - </header> - <div class="content content-dataset"> - - <section class='intro_section' style='background-image: url(https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/viper/assets/background.jpg)'><div class='inner'><div class='hero_desc'><span class='bgpad'><span class="dataset-name">VIPeR</span> is a person re-identification dataset of images captured at UC Santa Cruz in 2007</span></div><div class='hero_subdesc'><span class='bgpad'>VIPeR contains 1,264 images and 632 persons on the UC Santa Cruz campus and is used to train person re-identification algorithms for surveillance -</span></div></div></section><section><h2>VIPeR Dataset</h2> -</section><section><div class='right-sidebar'><div class='meta'> - <div class='gray'>Published</div> - <div>2007</div> - </div><div class='meta'> - <div class='gray'>Images</div> - <div>1,264 </div> - </div><div class='meta'> - <div class='gray'>Identities</div> - <div>632 </div> - </div><div class='meta'> - <div class='gray'>Purpose</div> - <div>Person re-identification</div> - </div><div class='meta'> - <div class='gray'>Created by</div> - <div>University of California Santa Cruz</div> - </div><div class='meta'> - <div class='gray'>Website</div> - <div><a href='https://vision.soe.ucsc.edu/node/178' target='_blank' rel='nofollow noopener'>ucsc.edu</a></div> - </div></div><p>[ page under development ]</p> -<p><em>VIPeR (Viewpoint Invariant Pedestrian Recognition)</em> is a dataset of pedestrian images captured at University of California Santa Cruz in 2007. Accoriding to the reserachers 2 "cameras were placed in different locations in an academic setting and subjects were notified of the presence of cameras, but were not coached or instructed in any way."</p> -<p>VIPeR is amongst the most widely used publicly available person re-identification datasets. In 2017 the VIPeR dataset was combined into a larger person re-identification created by the Chinese University of Hong Kong called PETA (PEdesTrian Attribute).</p> -</section><section> - <h3>Who used VIPeR?</h3> - - <p> - This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. - </p> - - </section> - -<section class="applet_container"> -<!-- <div style="position: absolute;top: 0px;right: -55px;width: 180px;font-size: 14px;">Labeled Faces in the Wild Dataset<br><span class="numc" style="font-size: 11px;">20 citations</span> -</div> --> - <div class="applet" data-payload="{"command": "chart"}"></div> -</section> - -<section class="applet_container"> - <div class="applet" data-payload="{"command": "piechart"}"></div> -</section> - -<section> - - <h3>Biometric Trade Routes</h3> - - <p> - To help understand how VIPeR has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Viewpoint Invariant Pedestrian Recognition was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. - </p> - - </section> - -<section class="applet_container fullwidth"> - <div class="applet" data-payload="{"command": "map"}"></div> -</section> - -<div class="caption"> - <ul class="map-legend"> - <li class="edu">Academic</li> - <li class="com">Commercial</li> - <li class="gov">Military / Government</li> - </ul> - <div class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</div > -</div> - - -<section class="applet_container"> - - <h3>Dataset Citations</h3> - <p> - The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. If you use our data, please <a href="/about/attribution">cite our work</a>. - </p> - - <div class="applet" data-payload="{"command": "citations"}"></div> -</section> - - </div> - <footer> - <ul class="footer-left"> - <li><a href="/">MegaPixels.cc</a></li> - <li><a href="/datasets/">Datasets</a></li> - <li><a href="/about/">About</a></li> - <li><a href="/about/press/">Press</a></li> - <li><a href="/about/legal/">Legal and Privacy</a></li> - </ul> - <ul class="footer-right"> - <li>MegaPixels ©2017-19 <a href="https://ahprojects.com">Adam R. Harvey</a></li> - <li>Made with support from <a href="https://mozilla.org">Mozilla</a></li> - </ul> - </footer> -</body> - -<script src="/assets/js/dist/index.js"></script> -</html>
\ No newline at end of file diff --git a/site/public/datasets/youtube_celebrities/index.html b/site/public/datasets/youtube_celebrities/index.html deleted file mode 100644 index b871ab18..00000000 --- a/site/public/datasets/youtube_celebrities/index.html +++ /dev/null @@ -1,114 +0,0 @@ -<!doctype html> -<html> -<head> - <title>MegaPixels</title> - <meta charset="utf-8" /> - <meta name="author" content="Adam Harvey" /> - <meta name="description" content="YouTube Celebrities" /> - <meta name="referrer" content="no-referrer" /> - <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes" /> - <link rel='stylesheet' href='/assets/css/fonts.css' /> - <link rel='stylesheet' href='/assets/css/css.css' /> - <link rel='stylesheet' href='/assets/css/leaflet.css' /> - <link rel='stylesheet' href='/assets/css/applets.css' /> - <link rel='stylesheet' href='/assets/css/mobile .css' /> -</head> -<body> - <header> - <a class='slogan' href="/"> - <div class='logo'></div> - <div class='site_name'>MegaPixels</div> - <div class='page_name'>YouTube Celebrities</div> - </a> - <div class='links'> - <a href="/datasets/">Datasets</a> - <a href="/about/">About</a> - </div> - </header> - <div class="content content-"> - - <section><h2>YouTube Celebrities</h2> -</section><section><div class='right-sidebar'></div><p>[ page under development ]</p> -</section><section> - <h3>Who used YouTube Celebrities?</h3> - - <p> - This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. - </p> - - </section> - -<section class="applet_container"> -<!-- <div style="position: absolute;top: 0px;right: -55px;width: 180px;font-size: 14px;">Labeled Faces in the Wild Dataset<br><span class="numc" style="font-size: 11px;">20 citations</span> -</div> --> - <div class="applet" data-payload="{"command": "chart"}"></div> -</section> - -<section class="applet_container"> - <div class="applet" data-payload="{"command": "piechart"}"></div> -</section> - -<section> - - <h3>Biometric Trade Routes</h3> - - <p> - To help understand how YouTube Celebrities has been used around the world by commercial, military, and academic organizations; existing publicly available research citing YouTube Celebrities was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. - </p> - - </section> - -<section class="applet_container fullwidth"> - <div class="applet" data-payload="{"command": "map"}"></div> -</section> - -<div class="caption"> - <ul class="map-legend"> - <li class="edu">Academic</li> - <li class="com">Commercial</li> - <li class="gov">Military / Government</li> - </ul> - <div class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</div > -</div> - - -<section class="applet_container"> - - <h3>Dataset Citations</h3> - <p> - The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. If you use our data, please <a href="/about/attribution">cite our work</a>. - </p> - - <div class="applet" data-payload="{"command": "citations"}"></div> -</section><section><h4>Notes...</h4> -<ul> -<li>Selected dataset sequences: (a) MBGC, (b) CMU MoBo, (c) First -Honda/UCSD, and (d) YouTube Celebrities.</li> -<li>This research is supported by the Central Intelligence Agency, the Biometrics -Task Force and the Technical Support Working Group through US Army contract -W91CRB-08-C-0093. The opinions, (cid:12)ndings, and conclusions or recommendations -expressed in this publication are those of the authors and do not necessarily re(cid:13)ect -the views of our sponsors.</li> -<li>in "Face Recognition From Video Draft 17"</li> -<li>International Journal of Pattern Recognition and Artifcial Intelligence WorldScientific Publishing Company</li> -</ul> -</section> - - </div> - <footer> - <ul class="footer-left"> - <li><a href="/">MegaPixels.cc</a></li> - <li><a href="/datasets/">Datasets</a></li> - <li><a href="/about/">About</a></li> - <li><a href="/about/press/">Press</a></li> - <li><a href="/about/legal/">Legal and Privacy</a></li> - </ul> - <ul class="footer-right"> - <li>MegaPixels ©2017-19 <a href="https://ahprojects.com">Adam R. Harvey</a></li> - <li>Made with support from <a href="https://mozilla.org">Mozilla</a></li> - </ul> - </footer> -</body> - -<script src="/assets/js/dist/index.js"></script> -</html>
\ No newline at end of file diff --git a/site/public/index.html b/site/public/index.html index feb50455..e5a6cd62 100644 --- a/site/public/index.html +++ b/site/public/index.html @@ -4,7 +4,7 @@ <title>MegaPixels: Face Recognition Datasets</title> <meta charset="utf-8" /> <meta name="author" content="Adam Harvey, ahprojects.com" /> - <meta name="description" content="MegaPixels: Investigating Face Recognition Datasets" /> + <meta name="description" content='MegaPixels is an art and research project investigating the ethics, origins, and individual privacy implications of face recognition datasets created "in the wild" by Adam Harvey and Jules LaPlace' /> <meta name="referrer" content="no-referrer" /> <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes" /> <meta property="og:title" content="MegaPixels"/> @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/" class='aboutLink'>DATASETS</a> <a href="/about/" class='aboutLink'>ABOUT</a> + <a href="/about/news" class='updateLink'>News</a> </div> </header> <div class="splash"> @@ -65,11 +66,11 @@ </div> <footer> <div> - <span><a href="/about/">MegaPixels</a> is a research project by Adam Harvey about <a href="/datasets/">facial recognition datasets</a>, made possible with support from Mozilla.</span> + <span class="intro-mobile"> is an art and research research project about <a href="/datasets/">face recognition datasets</a></span> </div> <div> - MegaPixels ©2017-19 Adam R. Harvey / - <a href="https://ahprojects.com/megapixels/">ahprojects.com</a> + <span class="intro-mobile-cr">MegaPixels ©2017-19 Adam R. Harvey / + <a href="https://ahprojects.com/megapixels/">ahprojects.com</a></span> </div> </footer> </body> diff --git a/site/public/info/index.html b/site/public/info/index.html index 2084cfdb..d1c2fb02 100644 --- a/site/public/info/index.html +++ b/site/public/info/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-"> diff --git a/site/public/research/00_introduction/index.html b/site/public/research/00_introduction/index.html index 92e51673..e056bc62 100644 --- a/site/public/research/00_introduction/index.html +++ b/site/public/research/00_introduction/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-"> diff --git a/site/public/research/01_from_1_to_100_pixels/index.html b/site/public/research/01_from_1_to_100_pixels/index.html index 717f29fd..90efd707 100644 --- a/site/public/research/01_from_1_to_100_pixels/index.html +++ b/site/public/research/01_from_1_to_100_pixels/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-"> diff --git a/site/public/research/02_what_computers_can_see/index.html b/site/public/research/02_what_computers_can_see/index.html index 9d4f124c..f8a36624 100644 --- a/site/public/research/02_what_computers_can_see/index.html +++ b/site/public/research/02_what_computers_can_see/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-"> diff --git a/site/public/research/index.html b/site/public/research/index.html index c69a74fe..569857c5 100644 --- a/site/public/research/index.html +++ b/site/public/research/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-"> diff --git a/site/public/test/chart/index.html b/site/public/test/chart/index.html index 1908aa7e..87067a28 100644 --- a/site/public/test/chart/index.html +++ b/site/public/test/chart/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-"> diff --git a/site/public/test/citations/index.html b/site/public/test/citations/index.html index 534e209a..685395f0 100644 --- a/site/public/test/citations/index.html +++ b/site/public/test/citations/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-"> diff --git a/site/public/test/csv/index.html b/site/public/test/csv/index.html index 90c5956b..9fbda1c6 100644 --- a/site/public/test/csv/index.html +++ b/site/public/test/csv/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-"> diff --git a/site/public/test/datasets/index.html b/site/public/test/datasets/index.html index 5d578082..2270349f 100644 --- a/site/public/test/datasets/index.html +++ b/site/public/test/datasets/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-"> diff --git a/site/public/test/face_search/index.html b/site/public/test/face_search/index.html index eed46867..15a6899d 100644 --- a/site/public/test/face_search/index.html +++ b/site/public/test/face_search/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-"> diff --git a/site/public/test/gallery/index.html b/site/public/test/gallery/index.html index 45c5892e..6746fe6a 100644 --- a/site/public/test/gallery/index.html +++ b/site/public/test/gallery/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-"> diff --git a/site/public/test/index.html b/site/public/test/index.html index d3d8b1d2..a0989be1 100644 --- a/site/public/test/index.html +++ b/site/public/test/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-"> diff --git a/site/public/test/map/index.html b/site/public/test/map/index.html index 623d0ce5..9229abc5 100644 --- a/site/public/test/map/index.html +++ b/site/public/test/map/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-"> diff --git a/site/public/test/name_search/index.html b/site/public/test/name_search/index.html index f4372d61..d900e565 100644 --- a/site/public/test/name_search/index.html +++ b/site/public/test/name_search/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-"> diff --git a/site/public/test/pie_chart/index.html b/site/public/test/pie_chart/index.html index bf4c5ada..72dc0290 100644 --- a/site/public/test/pie_chart/index.html +++ b/site/public/test/pie_chart/index.html @@ -49,6 +49,7 @@ <div class='links'> <a href="/datasets/">Datasets</a> <a href="/about/">About</a> + <a href="/about/news">News</a> </div> </header> <div class="content content-"> |