summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--.gitignore6
-rw-r--r--README.md2
-rw-r--r--client/map/index.js25
-rw-r--r--client/tables.js20
-rw-r--r--megapixels/app/site/parser.py4
-rw-r--r--scraper/s2-citation-report.py20
-rw-r--r--site/assets/css/applets.css10
-rw-r--r--site/assets/css/css.css151
-rw-r--r--site/assets/css/splash.css9
-rwxr-xr-x[-rw-r--r--]site/assets/img/megapixels_logo_white.svg10
-rwxr-xr-x[-rw-r--r--]site/content/assets/megapixels_logo.svg10
-rw-r--r--site/content/assets/megapixels_logo_01.svg (renamed from site/assets/img/megapixels_logo.svg)0
-rw-r--r--site/content/pages/about/index.md11
-rw-r--r--site/content/pages/about/press.md10
-rw-r--r--site/content/pages/about/privacy.md6
-rw-r--r--site/content/pages/about/research.md7
-rw-r--r--site/content/pages/about/terms.md12
-rw-r--r--site/content/pages/datasets/brainwash/assets/00425000_960.jpgbin0 -> 47240 bytes
-rwxr-xr-x[-rw-r--r--]site/content/pages/datasets/brainwash/assets/background.jpgbin47724 -> 86425 bytes
-rw-r--r--site/content/pages/datasets/brainwash/assets/brainwash_montage.jpgbin0 -> 235410 bytes
-rwxr-xr-x[-rw-r--r--]site/content/pages/datasets/brainwash/assets/index.jpgbin6088 -> 15644 bytes
-rw-r--r--site/content/pages/datasets/brainwash/index.md61
-rw-r--r--site/content/pages/datasets/index.md1
-rw-r--r--site/content/pages/datasets/lfw/assets/background.jpgbin316873 -> 212118 bytes
-rw-r--r--site/content/pages/datasets/lfw/assets/background_lg.jpgbin0 -> 316873 bytes
-rw-r--r--site/content/pages/datasets/lfw/assets/fetch_lfw_people.py34
-rw-r--r--site/content/pages/datasets/lfw/index.md61
-rw-r--r--site/includes/map.html11
-rw-r--r--site/includes/supplementary_header.html10
-rw-r--r--site/public/about/index.html11
-rw-r--r--site/public/about/press/index.html9
-rw-r--r--site/public/about/privacy/index.html9
-rw-r--r--site/public/about/research/index.html10
-rw-r--r--site/public/about/terms/index.html11
-rw-r--r--site/public/datasets/afad/index.html62
-rw-r--r--site/public/datasets/aflw/index.html55
-rw-r--r--site/public/datasets/brainwash/index.html82
-rw-r--r--site/public/datasets/caltech_10k/index.html (renamed from site/public/about/credits/index.html)16
-rw-r--r--site/public/datasets/cofw/index.html66
-rw-r--r--site/public/datasets/facebook/index.html56
-rw-r--r--site/public/datasets/feret/index.html68
-rw-r--r--site/public/datasets/index.html1
-rw-r--r--site/public/datasets/lfpw/index.html58
-rw-r--r--site/public/datasets/lfw/index.html47
-rw-r--r--site/public/datasets/lfw/right-to-removal/index.html62
-rw-r--r--site/public/datasets/lfw/tables/index.html52
-rw-r--r--site/public/datasets/uccs/index.html90
-rw-r--r--site/public/datasets/youtube_celebrities/index.html65
-rw-r--r--site/public/index.html7
-rw-r--r--site/templates/home.html7
-rw-r--r--todo.md22
51 files changed, 1023 insertions, 334 deletions
diff --git a/.gitignore b/.gitignore
index 472246d2..cdf46edc 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,8 +1,8 @@
# Custom
3rdparty/
*_local_*
-site/public/datasets/
-site/public/*.html
+#site/public/datasets/
+#site/public/*.html
notebooks/_local_*
# Project specific
@@ -167,3 +167,5 @@ site/public/user_content
# google API key :-o
.api_key
+site/datasets/final/*.csv
+
diff --git a/README.md b/README.md
index e8c5731b..c95d56f8 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,6 @@
# MegaPixels
-FaceQuery.me, mozilla, nytimes
+Origins and ethics of publicy available facial recognition datasets
## Installation
diff --git a/client/map/index.js b/client/map/index.js
index a9afe211..ec9ebe66 100644
--- a/client/map/index.js
+++ b/client/map/index.js
@@ -37,11 +37,16 @@ const redDot = L.icon({
popupAnchor: [0, -5] // point from which the popup should open relative to the iconAnchor
})
-function addMarker(map, latlng, title, subtext, year) {
+function addMarker(map, latlng, title, subtext, year, pdf) {
const marker = L.marker(latlng, { icon: redDot }).addTo(map)
let message = [
"<b>", title, "</b>",
]
+ if (pdf && pdf.length) {
+ message.unshift("<a href='" + pdf[0] + "' target='_blank'>")
+ message.push("</a>")
+ }
+
message = message.concat([
"<br>",
subtext,
@@ -84,15 +89,19 @@ export default function append(el, payload) {
source = [address.lat, address.lng].map(n => parseFloat(n))
} else {
console.error("No address found for root paper")
- console.log(data)
+ // console.log(data)
}
citations.forEach(citation => {
- // console.log(citation)
+ console.log(citation)
+ if (!citation.addresses) {
+ console.log(citation)
+ return
+ }
const citationAddress = citation.addresses[0]
const latlng = [citationAddress.lat, citationAddress.lng].map(n => parseFloat(n))
if (Number.isNaN(latlng[0]) || Number.isNaN(latlng[1])) return
- addMarker(map, latlng, citation.title, citationAddress.name, citation.year)
+ addMarker(map, latlng, citation.title, citationAddress.name, citation.year, citation.pdf)
addArc(map, source, latlng, arcStyles[citationAddress.type])
})
@@ -107,7 +116,9 @@ export default function append(el, payload) {
mapCover.innerHTML = "<div class='cover_message'>Click here to explore the map</div>"
mapCover.querySelector('div').addEventListener('click', () => {
map.scrollWheelZoom.enable()
- el.removeChild(mapCover)
+ if (mapCover.parentNode === el) {
+ el.removeChild(mapCover)
+ }
})
function stopPropagation(e) {
e.stopPropagation()
@@ -118,7 +129,9 @@ export default function append(el, payload) {
map.scrollWheelZoom.disable()
map.on('focus', () => {
map.scrollWheelZoom.enable()
- el.removeChild(mapCover)
+ if (mapCover.parentNode === el) {
+ el.removeChild(mapCover)
+ }
})
map.on('blur', () => {
map.scrollWheelZoom.disable()
diff --git a/client/tables.js b/client/tables.js
index 3fadb797..851f76f5 100644
--- a/client/tables.js
+++ b/client/tables.js
@@ -13,7 +13,9 @@ const datasetColumns = [
const citationsColumns = [
{ title: 'Title', field: 'title', sorter: 'string' },
{ title: 'Institution', field: 'institution', sorter: 'string' },
- { title: 'Year', field: 'year', sorter: 'number' },
+ { title: 'Country', field: 'country', sorter: 'string', width: 140 },
+ { title: 'Year', field: 'year', sorter: 'number', width: 70 },
+ { title: 'PDF', field: 'pdf', formatter: 'link', sorter: 'string', width: 100 },
]
function getColumns(payload) {
@@ -33,17 +35,19 @@ function getColumns(payload) {
}
function getCitations(dataset) {
- console.log(dataset.citations)
+ // console.log(dataset.citations)
return dataset.citations.map(citation => ({
- title: citation['title'],
- institution: citation['addresses'][0]['name'],
- year: citation['year'],
+ title: citation.title,
+ institution: citation.addresses[0].name,
+ country: citation.addresses[0].country,
+ year: citation.year,
+ pdf: (citation.pdf && citation.pdf.length) ? citation.pdf[0] : "",
}))
}
export default function append(el, payload) {
const columns = getColumns(payload)
- console.log(columns)
+ // console.log(columns)
const table = new Tabulator(el, {
height: '311px',
layout: 'fitColumns',
@@ -57,7 +61,7 @@ export default function append(el, payload) {
if (payload.cmd === 'citations') {
let { data } = payload
const citations = getCitations(data)
- console.log(citations)
+ // console.log(citations)
table.setData(citations)
el.classList.add('loaded')
} else {
@@ -65,7 +69,7 @@ export default function append(el, payload) {
.then(r => r.text())
.then(text => {
try {
- console.log(text)
+ // console.log(text)
const data = csv.toJSON(text, { headers: { included: true } })
// console.log(data)
table.setData(data)
diff --git a/megapixels/app/site/parser.py b/megapixels/app/site/parser.py
index 87539ade..f6e308f3 100644
--- a/megapixels/app/site/parser.py
+++ b/megapixels/app/site/parser.py
@@ -136,11 +136,11 @@ def intro_section(metadata, s3_path):
# colorize the first instance of the database name in the header
if 'color' in metadata and metadata['title'] in desc:
desc = desc.replace(metadata['title'], "<span style='color: {}'>{}</span>".format(metadata['color'], metadata['title']), 1)
- section += "<div class='hero_desc'><span>{}</span></div>".format(desc, desc)
+ section += "<div class='hero_desc'><span class='bgpad'>{}</span></div>".format(desc, desc)
if 'subdesc' in metadata:
subdesc = markdown(metadata['subdesc']).replace('<p>', '').replace('</p>', '')
- section += "<div class='hero_subdesc'><span>{}</span></div>".format(subdesc, subdesc)
+ section += "<div class='hero_subdesc'><span class='bgpad'>{}</span></div>".format(subdesc, subdesc)
section += "</div>"
section += "</section>"
diff --git a/scraper/s2-citation-report.py b/scraper/s2-citation-report.py
index bf3bfdb9..3797a1bd 100644
--- a/scraper/s2-citation-report.py
+++ b/scraper/s2-citation-report.py
@@ -35,12 +35,6 @@ def s2_citation_report():
write_master_report('{}/{}'.format(DIR_PUBLIC_CITATIONS, "datasets.csv"), papers)
- subprocess.call([
- "s3cmd", "put", "-P", "--recursive",
- DIR_PUBLIC_CITATIONS + '/',
- "s3://megapixels/v1/citations/",
- ])
-
def write_master_report(fn, papers):
# first make a lookup of the keys that have papers
paper_key_lookup = {}
@@ -352,13 +346,13 @@ def process_paper(row, addresses, success):
f.write('<script src="../map.js"></script>')
f.write("</html>")
# template = env.get_template('paper.html')
- with open('{}/{}.json'.format(DIR_PUBLIC_CITATIONS, row['key']), 'w') as f:
- json.dump({
- 'id': paper.paper_id,
- 'paper': res,
- 'address': paper_address,
- 'citations': geocoded_citations,
- }, f)
+ # with open('{}/{}.json'.format(DIR_PUBLIC_CITATIONS, row['key']), 'w') as f:
+ # json.dump({
+ # 'id': paper.paper_id,
+ # 'paper': res,
+ # 'address': paper_address,
+ # 'citations': geocoded_citations,
+ # }, f)
return res
def load_megapixels_queries():
diff --git a/site/assets/css/applets.css b/site/assets/css/applets.css
index e84fcfc2..d3ca75c0 100644
--- a/site/assets/css/applets.css
+++ b/site/assets/css/applets.css
@@ -134,6 +134,8 @@
max-width: 40px;
}
+/* map */
+
.map, .map .applet {
height: 500px;
}
@@ -162,6 +164,14 @@
.desktop .map_cover:hover {
opacity: 1;
}
+.leaflet-popup-content a {
+ color: #0078A8;
+ border-bottom: 1px solid rgba(0, 128, 160, 0.4);
+}
+.desktop .leaflet-popup-content a:hover {
+ color: #0078A8;
+ border-bottom: 1px solid rgba(0, 128, 160, 0.9);
+}
/* tabulator */
diff --git a/site/assets/css/css.css b/site/assets/css/css.css
index b8798cd9..e0d15c80 100644
--- a/site/assets/css/css.css
+++ b/site/assets/css/css.css
@@ -11,10 +11,11 @@ html, body {
html {
background: #181818;
}
-
+a {outline : none;}
+img {border : 0;}
.content {
opacity: 0;
- transition: opacity 0.2s cubic-bezier(0,1,1,1);
+ transition: opacity 0.1s cubic-bezier(0,1,1,1);
}
html.desktop .content,
html.mobile .content {
@@ -48,16 +49,28 @@ header .logo {
background-image: url(../img/megapixels_logo_white.svg);
background-size: contain;
background-repeat: no-repeat;
- margin-top: 7px;
- margin-right: 10px;
- width: 39px;
- height: 30px;
+ margin-top: 0px;
+ margin-right: 8px;
+ width: 20px;
+ height: 20px;
}
header .site_name {
font-family: 'Roboto', sans-serif;
- font-weight: bold;
+ font-weight: 600;
+ text-transform: uppercase;;
color: #fff;
- font-size: 14px;
+ font-size: 12px;
+ line-height: 12px;
+ letter-spacing: 4px;
+}
+header .site_name.splash{
+ font-size: 20px;
+ line-height: 20px;
+ font-weight: 400;
+}
+header .links{
+ font-size: 18px;
+ line-height: 18px;
}
header .sub {
margin-left: 4px;
@@ -82,25 +95,30 @@ header .links {
header .links span,
header .links a {
display: block;
- color: #777;
+ color: #d7ba5a;
text-decoration: none;
text-transform: uppercase;
margin-right: 32px;
- transition: color 0.1s cubic-bezier(0,0,1,1), border-color 0.1s cubic-bezier(0,0,1,1);
+ transition: color 0.1s cubic-bezier(0,0,1,1), border-color 0.05s cubic-bezier(0,0,1,1);
border-bottom: 1px solid rgba(255,255,255,0);
padding: 3px;
- font-weight: 500;
+ font-weight: 400;
}
header .links a.active {
- color: #bbb;
+ color: #f3c266;
+ border-bottom: 1px solid rgba(240,200,150,255);
}
.desktop header .links a:hover {
- color: #fff;
- border-bottom: 1px solid rgba(255,255,255,255);
+ color: #e9bb5f;
+ border-bottom: 1px solid rgba(240,200,150,255);
}
.desktop header .links a.active:hover {
- color: #fff;
- border-bottom: 1px solid rgba(255,255,255,255);
+ color: #e9bb5f;
+ border-bottom: 1px solid rgba(240,200,150,255);
+}
+header .links.splash{
+ font-size:22px;
+ font-weight: 400;
}
/* footer */
@@ -129,7 +147,7 @@ footer > div:nth-child(2) {
footer a {
display: inline-block;
color: #888;
- transition: color 0.2s cubic-bezier(0,0,1,1);
+ transition: color 0.1s cubic-bezier(0,0,1,1);
margin-right: 5px;
}
footer a:hover {
@@ -144,7 +162,7 @@ h1 {
font-size: 28pt;
margin: 75px 0 10px;
padding: 0;
- transition: color 0.2s cubic-bezier(0,0,1,1);
+ transition: color 0.1s cubic-bezier(0,0,1,1);
font-family: 'Roboto';
}
h2 {
@@ -153,15 +171,15 @@ h2 {
font-size: 28pt;
margin: 20px 0 10px;
padding: 0;
- transition: color 0.2s cubic-bezier(0,0,1,1);
+ transition: color 0.1s cubic-bezier(0,0,1,1);
font-family: 'Roboto';
}
h3 {
margin: 0 0 20px 0;
padding: 20px 0 0 0;
- font-size: 16pt;
+ font-size: 18pt;
font-weight: 500;
- transition: color 0.2s cubic-bezier(0,0,1,1);
+ transition: color 0.1s cubic-bezier(0,0,1,1);
font-family: 'Roboto';
}
h4 {
@@ -169,7 +187,7 @@ h4 {
padding: 0;
font-size: 11pt;
font-weight: 500;
- transition: color 0.2s cubic-bezier(0,0,1,1);
+ transition: color 0.1s cubic-bezier(0,0,1,1);
font-family: 'Roboto';
}
.content h3 a {
@@ -206,7 +224,7 @@ th, .gray {
/* content */
.content {
- padding-top: 70px;
+ padding-top: 28px;
padding-bottom: 100px;
min-height: calc(100vh - 55px);
line-height: 1.5;
@@ -227,7 +245,7 @@ section {
line-height: 36px;
}
p {
- margin: 0 0 20px 0;
+ margin: 0 10px 20px 0;
line-height: 2;
font-size: 16px;
font-weight: 300;
@@ -236,7 +254,7 @@ p {
color: #fff;
text-decoration: none;
border-bottom: 1px dashed;
- transition: color 0.2s cubic-bezier(0,0,1,1);
+ transition: color 0.1s cubic-bezier(0,0,1,1);
}
.desktop .content a:hover {
color: #fff;
@@ -250,16 +268,19 @@ p {
flex-direction: row;
justify-content: flex-start;
align-items: flex-start;
- font-size: 11pt;
+ font-size: 14px;
margin-bottom: 20px;
font-family: 'Roboto', sans-serif;
}
.meta > div {
- margin-right: 30px;
+ margin-right: 20px;
+ line-height: 19px
+ /*font-size:11px;*/
}
.meta .gray {
font-size: 9pt;
padding-bottom: 4px;
+ line-height: 14px
}
.right-sidebar {
float: right;
@@ -278,7 +299,7 @@ p {
padding-top: 10px;
padding-right: 20px;
margin-right: 20px;
- margin-bottom: 10px;
+ margin-bottom: 30px;
/*border-right: 1px solid #444;*/
font-family: 'Roboto';
font-size: 14px;
@@ -292,7 +313,7 @@ p {
margin-bottom: 10px;
}
.left-sidebar .meta > div {
- margin-bottom: 10px;
+ margin-bottom: 15px;
}
.right-sidebar ul {
margin-bottom: 10px;
@@ -366,6 +387,9 @@ blockquote {
.footnotes hr {
display: none;
}
+ul.footnotes li, ul.footnotes p{
+ font-size:12px;
+}
.footnotes ol:before {
content: 'Footnotes';
margin: 0 0 10px -40px;
@@ -386,7 +410,7 @@ section img {
margin: 0 auto;
}
section .image {
- margin-bottom: 40px;
+ margin-bottom: 20px;
}
section.images {
display: flex;
@@ -440,12 +464,20 @@ section.fullwidth .image {
}
.caption {
text-align: left;
- font-size: 9pt;
+ font-size: 10pt;
color: #999;
max-width: 960px;
margin: 10px auto 10px auto;
font-family: 'Roboto';
}
+.caption a{
+ color:#ccc;
+ border: 0;
+}
+.caption a:hover{
+ color:#fff;
+ border: 0;
+}
.sideimage {
margin: 0px 0 40px 0;
display: flex;
@@ -595,8 +627,8 @@ section.fullwidth .image {
height: 140px;
padding: 10px;
color: white;
- font-weight: 300;
- font-family: 'Roboto Mono'
+ font-weight: 400;
+ font-family: 'Roboto'
}
.desktop .content .dataset-list a{
border:none;
@@ -632,6 +664,7 @@ section.intro_section {
justify-content: center;
align-items: center;
background-color: #111111;
+ margin-bottom: 30px;
}
.intro_section .inner {
max-width: 960px;
@@ -648,13 +681,19 @@ section.intro_section {
font-size: 17px;
line-height: 36px;
max-width: 680px;
- font-weight: 400;
+ font-weight: 300;
color: #ddd;
}
-.intro_section div > span {
- box-shadow: -10px -10px #181818, 10px -10px #181818, 10px 10px #181818, -10px 10px #181818;
+.intro_section .hero_desc .bgpad {
+ box-shadow: -7px -7px #181818, 7px -7px #181818, 7px 7px #181818, -7px 7px #181818;
background: #181818;
}
+.intro_section .hero_subdesc .bgpad {
+ box-shadow: -8px -8px #181818, 8px -8px #181818, 8px 8px #181818, -8px 8px #181818;
+ background: #181818;
+}
+
+
.firefox .intro_section div > span {
box-decoration-break: clone;
}
@@ -669,19 +708,43 @@ page-specific formatting
margin-bottom: 10px
}
+.hr-wave-holder {
+ /* Clip edges, as some of the lines don't terminate nicely. */
+ overflow: hidden;
+ position: relative;
+ width: 100%;
+ height: 50px;
+ margin-top:100px;
+}
+
+.hr-wave-line1 {
+ background: linear-gradient(45deg, transparent, transparent 49%, #fff 49%, transparent 51%);
+}
+.hr-wave-line2 {
+ background: linear-gradient(-45deg, transparent, transparent 49%, #fff 49%, transparent 51%);
+}
+.hr-wave-line {
+ background-size: 20px 20px;
+ position: absolute;
+ width: 100%;
+ height: 10px;
+}
+
+
/* map */
.map-legend-item{
display: inline-block;
- margin-right: 10px
+ margin-right: 10px;
+ padding-top:4px;
}
-.edu {
+.map-legend-item .edu {
color: #f2f293;
}
-.com {
+.map-legend-item .com {
color: #3264f6;
}
-.gov {
+.map-legend-item .gov {
color: #f30000;
}
@@ -692,14 +755,16 @@ page-specific formatting
}
.content-about .about-menu ul li{
display:inline-block;
- font-size: 12px;
+ font-size: 14px;
font-weight: 400;
- margin-right: 5px;
+ margin-right: 8px;
text-transform: uppercase;
- margin-right: 10px
+ margin-right: 15px;
+ font-family: 'Roboto';
}
.content-about .about-menu ul li a{
border-bottom: 0;
+ color: #aaa;
}
diff --git a/site/assets/css/splash.css b/site/assets/css/splash.css
index 9dd5afba..8b07918b 100644
--- a/site/assets/css/splash.css
+++ b/site/assets/css/splash.css
@@ -18,14 +18,15 @@ footer {
footer div {
z-index: 2;
}
-header, footer {
- text-shadow: 0 0 5px #191919, 0 0 5px #191919, 0 0 5px #191919;
+footer {
+ /*text-shadow: 0 0 5px #191919, 0 0 5px #191919, 0 0 5px #191919;*/
+ background: #111;
}
header > div a,
footer > div {
- background: rgba(25, 25, 25, 0.8);
+ /*background: rgba(25, 25, 25, 0.8);
padding: 3px;
- border-radius: 2px;
+ border-radius: 2px;*/
}
header .links a.activeLink {
color: white;
diff --git a/site/assets/img/megapixels_logo_white.svg b/site/assets/img/megapixels_logo_white.svg
index 061e30ab..00aa430f 100644..100755
--- a/site/assets/img/megapixels_logo_white.svg
+++ b/site/assets/img/megapixels_logo_white.svg
@@ -2,13 +2,9 @@
<!-- Generator: Adobe Illustrator 16.0.0, SVG Export Plug-In . SVG Version: 6.00 Build 0) -->
<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
<svg version="1.1" id="Layer_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px"
- width="92.718px" height="58.333px" viewBox="0 0 92.718 58.333" enable-background="new 0 0 92.718 58.333" xml:space="preserve">
+ width="30px" height="30px" viewBox="0 0 30 30" enable-background="new 0 0 30 30" xml:space="preserve">
<g>
- <polygon fill="#ffffff" points="66.937,28.509 71.575,23.871 76.214,28.509 78.942,25.78 74.304,21.142 78.942,16.503
- 76.214,13.774 71.575,18.413 66.937,13.774 64.208,16.503 68.847,21.142 64.208,25.78 "/>
- <polygon fill="#ffffff" points="34.288,0 27.144,0 17.144,0 10,0 0.144,0 0,0 0,44 10,44 10,10 17.144,10 17.144,44 27.144,44
- 27.144,10 34.288,10 34.288,44 44.288,44 44.288,0 44.144,0 "/>
- <path fill="#ffffff" d="M92.717,0h-10H60.432h-9.999h-0.001v16.049v26.235v16.049h10V42.284h22.286h10h0L92.717,0L92.717,0z
- M82.718,32.284H60.432V16.049V10h22.286V32.284z"/>
+ <rect x="9.833" y="9.833" fill="#FFFFFF" width="10.334" height="10.333"/>
+ <path fill="#FFFFFF" d="M0,0v30h30V0H0z M25,25.002H5V4.999h20V25.002z"/>
</g>
</svg>
diff --git a/site/content/assets/megapixels_logo.svg b/site/content/assets/megapixels_logo.svg
index a9b7eff2..00aa430f 100644..100755
--- a/site/content/assets/megapixels_logo.svg
+++ b/site/content/assets/megapixels_logo.svg
@@ -2,13 +2,9 @@
<!-- Generator: Adobe Illustrator 16.0.0, SVG Export Plug-In . SVG Version: 6.00 Build 0) -->
<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
<svg version="1.1" id="Layer_1" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" x="0px" y="0px"
- width="92.718px" height="58.333px" viewBox="0 0 92.718 58.333" enable-background="new 0 0 92.718 58.333" xml:space="preserve">
+ width="30px" height="30px" viewBox="0 0 30 30" enable-background="new 0 0 30 30" xml:space="preserve">
<g>
- <polygon fill="#000001" points="66.937,28.509 71.575,23.871 76.214,28.509 78.942,25.78 74.304,21.142 78.942,16.503
- 76.214,13.774 71.575,18.413 66.937,13.774 64.208,16.503 68.847,21.142 64.208,25.78 "/>
- <polygon fill="#000001" points="34.288,0 27.144,0 17.144,0 10,0 0.144,0 0,0 0,44 10,44 10,10 17.144,10 17.144,44 27.144,44
- 27.144,10 34.288,10 34.288,44 44.288,44 44.288,0 44.144,0 "/>
- <path fill="#000001" d="M92.717,0h-10H60.432h-9.999h-0.001v16.049v26.235v16.049h10V42.284h22.286h10h0L92.717,0L92.717,0z
- M82.718,32.284H60.432V16.049V10h22.286V32.284z"/>
+ <rect x="9.833" y="9.833" fill="#FFFFFF" width="10.334" height="10.333"/>
+ <path fill="#FFFFFF" d="M0,0v30h30V0H0z M25,25.002H5V4.999h20V25.002z"/>
</g>
</svg>
diff --git a/site/assets/img/megapixels_logo.svg b/site/content/assets/megapixels_logo_01.svg
index a9b7eff2..a9b7eff2 100644
--- a/site/assets/img/megapixels_logo.svg
+++ b/site/content/assets/megapixels_logo_01.svg
diff --git a/site/content/pages/about/index.md b/site/content/pages/about/index.md
index 17302118..ccb6ed0d 100644
--- a/site/content/pages/about/index.md
+++ b/site/content/pages/about/index.md
@@ -11,7 +11,7 @@ authors: Adam Harvey
------------
-# About This Project
+# About MegaPixels
{% include 'about_navigation.html' %}
@@ -21,6 +21,15 @@ MegaPixels sets out to answer to these questions and reveal the stories behind t
MegaPixels sets out to answer to these questions and reveal the stories behind the millions of images used to train, evaluate, and power the facial recognition surveillance algorithms used today. MegaPixels is authored by Adam Harvey, developed in collaboration with Jules LaPlace, and produced in partnership with Mozilla.
+Notes
+
+- critical but informative
+- not anti-dataset
+- pro-sharing, pro-public dataset
+- w/o data
+- not generally anti-researcher, their parent organization should have checks in place to prevent dubious dataset collection methods
+-
+
![sideimage:Adam Harvey](assets/adam-harvey.jpg) **Adam Harvey** is an American artist and researcher based in Berlin. His previous projects (CV Dazzle, Stealth Wear, and SkyLift) explore the potential for countersurveillance as artwork. He is the founder of VFRAME (visual forensics software for human rights groups), the recipient of 2 PrototypeFund awards, and is currently a researcher in residence at Karlsruhe HfG studying artifical intelligence and datasets.
diff --git a/site/content/pages/about/press.md b/site/content/pages/about/press.md
index 1c80d020..abd4d823 100644
--- a/site/content/pages/about/press.md
+++ b/site/content/pages/about/press.md
@@ -13,15 +13,7 @@ authors: Adam Harvey
# Press
-- [About](/about/)
-- [Press](/about/press/)
-- [Disclaimer](/about/disclaimer/)
-- [Terms and Conditions](/about/terms/)
-- [Privacy Policy](/about/privacy/)
-
-### Sidebar
-
-## End Sidebar
+{% include 'about_navigation.html' %}
(list of press articles and images will go here)
diff --git a/site/content/pages/about/privacy.md b/site/content/pages/about/privacy.md
index 43db5032..a47b74cc 100644
--- a/site/content/pages/about/privacy.md
+++ b/site/content/pages/about/privacy.md
@@ -13,11 +13,7 @@ authors: Adam Harvey
# Privacy Policy
-- [About](/about/)
-- [Press](/about/press/)
-- [Disclaimer](/about/disclaimer/)
-- [Terms and Conditions](/about/terms/)
-- [Privacy Policy](/about/privacy/)
+{% include 'about_navigation.html' %}
A summary of our privacy policy is as follows:
diff --git a/site/content/pages/about/research.md b/site/content/pages/about/research.md
index 71dedcf0..8f001cc9 100644
--- a/site/content/pages/about/research.md
+++ b/site/content/pages/about/research.md
@@ -13,9 +13,4 @@ authors: Adam Harvey
# Research Methodologies
-- [About](/about/)
-- [Press](/about/press/)
-- [Research Methodology](/about/research/)
-- [Disclaimer](/about/disclaimer/)
-- [Terms and Conditions](/about/terms/)
-- [Privacy Policy](/about/privacy/)
+{% include 'about_navigation.html' %} \ No newline at end of file
diff --git a/site/content/pages/about/terms.md b/site/content/pages/about/terms.md
index aa298421..38d43735 100644
--- a/site/content/pages/about/terms.md
+++ b/site/content/pages/about/terms.md
@@ -14,17 +14,7 @@ authors: Adam Harvey
# Terms and Conditions ("Terms")
-### Sidebar
-
-- [About](/about/)
-- [Press](/about/press/)
-- [Credits](/about/credits/)
-- [Research Methodology](/about/research/)
-- [Disclaimer](/about/disclaimer/)
-- [Terms and Conditions](/about/terms/)
-- [Privacy Policy](/about/privacy/)
-
-## End Sidebar
+{% include 'about_navigation.html' %}
(FPO: this is only example text)
diff --git a/site/content/pages/datasets/brainwash/assets/00425000_960.jpg b/site/content/pages/datasets/brainwash/assets/00425000_960.jpg
new file mode 100644
index 00000000..caa96fe2
--- /dev/null
+++ b/site/content/pages/datasets/brainwash/assets/00425000_960.jpg
Binary files differ
diff --git a/site/content/pages/datasets/brainwash/assets/background.jpg b/site/content/pages/datasets/brainwash/assets/background.jpg
index f6efb253..8f2de697 100644..100755
--- a/site/content/pages/datasets/brainwash/assets/background.jpg
+++ b/site/content/pages/datasets/brainwash/assets/background.jpg
Binary files differ
diff --git a/site/content/pages/datasets/brainwash/assets/brainwash_montage.jpg b/site/content/pages/datasets/brainwash/assets/brainwash_montage.jpg
new file mode 100644
index 00000000..193fdd03
--- /dev/null
+++ b/site/content/pages/datasets/brainwash/assets/brainwash_montage.jpg
Binary files differ
diff --git a/site/content/pages/datasets/brainwash/assets/index.jpg b/site/content/pages/datasets/brainwash/assets/index.jpg
index e85f75c2..e5004ec0 100644..100755
--- a/site/content/pages/datasets/brainwash/assets/index.jpg
+++ b/site/content/pages/datasets/brainwash/assets/index.jpg
Binary files differ
diff --git a/site/content/pages/datasets/brainwash/index.md b/site/content/pages/datasets/brainwash/index.md
index a99dce3a..6c8cad97 100644
--- a/site/content/pages/datasets/brainwash/index.md
+++ b/site/content/pages/datasets/brainwash/index.md
@@ -3,9 +3,9 @@
status: published
title: Brainwash
desc: <span style="color:#ffaa00">Brainwash</span> is a dataset of people from webcams the Brainwash Cafe in San Francisco being used to train face detection algorithms
-subdesc: Brainwash dataset includes 11,918 images of people getting coffee at the Brainwash cafe during 2014
-caption: An sample image from the Brainwash dataset used for training face detection algorithms for surveillance. License: Open Data Commons Public Domain Dedication (PDDL)
+subdesc: Brainwash dataset includes 11,918 images of "everyday life of a busy downtown cafe"
slug: brainwash
+cssclass: dataset
image: assets/background.jpg
published: 2019-2-23
updated: 2019-2-23
@@ -13,68 +13,49 @@ authors: Adam Harvey
------------
-### Statistics
+### sidebar
+ Collected: 2014
+ Published: 2015
-+ Location: 1122 Folsom Street​ San Franscisco
-+ Images: 11,917
++ Images: 11,918
+ Faces: 91,146
+ Created by: Stanford Department of Computer Science
-+ Funding: Max Planck Center for Visual Computing and Communication
++ Funded by: Max Planck Center for Visual Computing and Communication
+ Resolution: 640x480px
-+ Origin: Angelcam IP Cam
++ Size: 4.1GB
++ Origin: Brainwash Cafe, San Franscisco
+ Purpose: Training face detection
++ Website: <a href="https://exhibits.stanford.edu/data/catalog/sx925dc9385">stanford.edu</a>
++ Paper: <a href="http://arxiv.org/abs/1506.04878">End-to-End People Detection in Crowded Scenes</a>
-- more info1
-- more info2
-- more info3
## Brainwash Dataset
-*Brainwash* is a face detection dataset created from the Brainwash Cafe's livecam footage. The stream is It was published in 2015 by researchers at the Stanford University and has been used 1122 Folsom Street​ | USA
+*Brainwash* is a face detection dataset created from the Brainwash Cafe's livecam footage including 11,918 images of "everyday life of a busy downtown cafe[^readme]". The images are used to develop face detection algorithms for the "challenging task of detecting people in crowded scenes" and tracking them.
-The photos were collected on
-- Oct 27, 2014
-- Nov 11, 2014
-- Nov 245, 2017
+Before closing in 2017, Brainwash Cafe was a "cafe and laundromat" located in San Francisco's Lower Haight district. The cafe published a publicy available livestream from the cafe with a view of the cash register, performance stage, and seating area.
-Sed ut perspiciatis, unde omnis iste natus error sit voluptatem accusantium doloremque laudantium, totam rem aperiam eaque ipsa, quae ab illo inventore veritatis et quasi architecto beatae vitae dicta sunt, explicabo. Nemo enim ipsam voluptatem, quia voluptas sit, aspernatur aut odit aut fugit, sed quia consequuntur magni dolores eos, qui ratione voluptatem sequi nesciunt, neque porro quisquam est, qui dolorem ipsum, quia dolor sit amet consectetur adipisci[ng] velit, sed quia non-numquam [do] eius modi tempora inci[di]dunt, ut labore et dolore magnam aliquam quaerat voluptatem. Ut enim ad minima veniam.
+Since it's publication by Stanford in 2015, the Brainwash dataset has appeared in several notable research papers. In September 2016 four researchers from the National University of Defense Technology in Changsha, China used the Brainwash dataset for a research study on "people head detection in crowded scenes", concluding that their algorithm "achieves superior head detection performance on the crowded scenes dataset[^localized_region_context]". And again in 2017 three researchers at the National University of Defense Technology used Brainwash for a study on object detection noting "the data set used in our experiment is shown in Table 1, which includes one scene of the brainwash dataset[^replacement_algorithm]".
-![Example images from the Brainwash dataset](assets/00425000_640x480.jpg)
-![Example images from the Brainwash dataset](assets/00818000_640x480.jpg)
-
-porro quisquam est, qui dolorem ipsum, quia dolor sit amet consectetur adipisci[ng] velit, sed quia non-numquam [do] eius modi tempora inci[di]dunt, ut labore et dolore magnam aliquam quaerat voluptatem. Ut enim ad minima veniam, quis nostrum[d] exercitationem ullam corporis suscipit laboriosam, nisi ut aliquid ex ea commodi consequatur? Quis autem vel eum iure reprehenderit, qui in ea voluptate velit esse, quam nihil molestiae consequatur, vel illum, qui dolorem eum fugiat, quo voluptas nulla pariatur?
+![caption: An sample image from the Brainwash dataset used for training face and head detection algorithms for surveillance. The datset contains about 12,000 images. License: Open Data Commons Public Domain Dedication (PDDL)](assets/00425000_960.jpg)
+![caption: 49 of the 11,918 images included in the Brainwash dataset. License: Open Data Commons Public Domain Dedication (PDDL)](assets/brainwash_montage.jpg)
{% include 'map.html' %}
-<hr class="supp">
-## Supplementary Information for Brainwash Dataset
+{% include 'supplementary_header.html' %}
{% include 'citations.html' %}
---------
-
-RESEARCH below this line
-
----
-
-The file is 4.1GB
-- add sha256 hash
-- the images were taken from Dropcam which was runnign on https://www.angelcam.com/ "Angelcam’s Real-time Surveillance takes the weight of keeping your home or business secure off your shoulders."
-
+### Additional Information
-> This package contains the "Brainwash" dataset. The dataset consists of images capturing the everyday life of a busy downtown cafe and is split into the following subsets:
-> training set: 10769 with 81975 annotated people
-> validation set: 500 images with 3318 annotated people
-> test set: 500 images with 5007 annotated people
+- The dataset author spoke about his research at the CVPR conference in 2016 <https://www.youtube.com/watch?v=Nl2fBKxwusQ>
-> Bounding box annotations are provided in a simple text file format. Each line in the file contains
-image name followed by the list of annotation rectangles in the \[xmin, ymin, max, ymax\] format.
-> We refer to the following arXiv submission for details on the dataset and the evaluation procedure:
+### Footnotes
-http://arxiv.org/abs/1506.04878 \ No newline at end of file
+[^readme]: "readme.txt" https://exhibits.stanford.edu/data/catalog/sx925dc9385.
+[^localized_region_context]: 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.
+[^replacement_algorithm]: Zhao. X, Wang Y, Dou, Y. A Replacement Algorithm of Non-Maximum Suppression Base on Graph Clustering. \ No newline at end of file
diff --git a/site/content/pages/datasets/index.md b/site/content/pages/datasets/index.md
index 47d0bce2..30fca496 100644
--- a/site/content/pages/datasets/index.md
+++ b/site/content/pages/datasets/index.md
@@ -13,3 +13,4 @@ sync: false
# Facial Recognition Datasets
+[add text, make sortable] This is a list of all the facial recognition datasets \ No newline at end of file
diff --git a/site/content/pages/datasets/lfw/assets/background.jpg b/site/content/pages/datasets/lfw/assets/background.jpg
index 3ab1607d..2c517060 100644
--- a/site/content/pages/datasets/lfw/assets/background.jpg
+++ b/site/content/pages/datasets/lfw/assets/background.jpg
Binary files differ
diff --git a/site/content/pages/datasets/lfw/assets/background_lg.jpg b/site/content/pages/datasets/lfw/assets/background_lg.jpg
new file mode 100644
index 00000000..3ab1607d
--- /dev/null
+++ b/site/content/pages/datasets/lfw/assets/background_lg.jpg
Binary files differ
diff --git a/site/content/pages/datasets/lfw/assets/fetch_lfw_people.py b/site/content/pages/datasets/lfw/assets/fetch_lfw_people.py
new file mode 100644
index 00000000..639883a6
--- /dev/null
+++ b/site/content/pages/datasets/lfw/assets/fetch_lfw_people.py
@@ -0,0 +1,34 @@
+#!/usr/bin/python
+
+# ------------------------------------------------------------
+#
+# Script to generate montage of LFW faces used in scikit-learn
+#
+# ------------------------------------------------------------
+
+import numpy as np
+from sklearn.datasets import fetch_lfw_people
+import imageio
+import imutils
+
+# download LFW dataset (first run takes a while)
+lfw_people = fetch_lfw_people(min_faces_per_person=1, resize=1, color=True, funneled=False)
+
+# introspect dataset
+n_samples, h, w, c = lfw_people.images.shape
+print(f'{n_samples:,} images at {w}x{h} pixels')
+cols, rows = (176, 76)
+n_ims = cols * rows
+
+# build montages
+im_scale = 0.5
+ims = lfw_people.images[:n_ims]
+montages = imutils.build_montages(ims, (int(w * im_scale, int(h * im_scale)), (cols, rows))
+montage = montages[0]
+
+# save full montage image
+imageio.imwrite('lfw_montage_full.png', montage)
+
+# make a smaller version
+montage = imutils.resize(montage, width=960)
+imageio.imwrite('lfw_montage_960.jpg', montage) \ No newline at end of file
diff --git a/site/content/pages/datasets/lfw/index.md b/site/content/pages/datasets/lfw/index.md
index 1af263dc..80e30ab3 100644
--- a/site/content/pages/datasets/lfw/index.md
+++ b/site/content/pages/datasets/lfw/index.md
@@ -5,7 +5,6 @@ title: Labeled Faces in The Wild
desc: <span style="color:#ff0000">Labeled Faces in The Wild (LFW)</span> is a database of face photographs designed for studying the problem of unconstrained face recognition.
subdesc: It includes 13,456 images of 4,432 people's images copied from the Internet during 2002-2004.
image: assets/background.jpg
-caption: A few of the 5,749 people in the Labeled Faces in the Wild Dataset, thee most widely used face dataset for benchmarking face recognition algorithms.
slug: lfw
published: 2019-2-23
updated: 2019-2-23
@@ -15,12 +14,12 @@ authors: Adam Harvey
### sidebar
-+ Created: 2002-2004
++ Created: 2002 &ndash; 2004
+ Images: 13,233
+ Identities: 5,749
+ Origin: Yahoo! News Images
+ Used by: Facebook, Google, Microsoft, Baidu, Tencent, SenseTime, Face++, CIA, NSA, IARPA
-+ Website: <a href="http://vis-www.cs.umass.edu/lfw">vis-www.cs.umass.edu/lfw</a>
++ Website: <a href="http://vis-www.cs.umass.edu/lfw">umass.edu</a>
- There are about 3 men for every 1 woman in the LFW dataset[^lfw_www]
- The person with the most images is [George W. Bush](http://vis-www.cs.umass.edu/lfw/person/George_W_Bush_comp.html) with 530
@@ -48,23 +47,11 @@ The *Names and Faces* dataset was the first face recognition dataset created ent
{% include 'map.html' %}
- Sed ut perspiciatis, unde omnis iste natus error sit voluptatem accusantium doloremque laudantium, totam rem aperiam eaque ipsa, quae ab illo inventore veritatis et quasi architecto beatae vitae dicta sunt, explicabo. Nemo enim ipsam voluptatem, quia voluptas sit, aspernatur aut odit aut fugit, sed quia.
-
-<hr class="supp">
-
-## Supplementary Information for Labeled Faces in The Wild
+{% include 'supplementary_header.html' %}
{% include 'citations.html' %}
-{% include 'synthetic_faces_intro.html' %}
-
-![Synthetically generated face from the visual space of LFW dataset](assets/synthetic_01.jpg)
-![Synthetically generated face from the visual space of LFW dataset](assets/synthetic_02.jpg)
-![Synthetically generated face from the visual space of LFW dataset](assets/synthetic_03.jpg)
-![Synthetically generated face from the visual space of LFW dataset](assets/synthetic_01.jpg)
-
-
-### Commercial Use of Labeled Faces in The Wild
+### Commercial Use
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.
@@ -73,46 +60,6 @@ load_file assets/lfw_commercial_use.csv
name_display, company_url, example_url, country, description
```
-### Code
-
-The LFW dataset is so widely used that access to the facial data has built directly into a popular code library called Sci-Kit Learn. It includes a function called `fetch_lfw_people` to download the faces in the LFW dataset.
-
-```python
-#!/usr/bin/python
-
-# ------------------------------------------------------------
-#
-# Script to generate montage of LFW faces used in scikit-learn
-#
-# ------------------------------------------------------------
-
-import numpy as np
-from sklearn.datasets import fetch_lfw_people
-import imageio
-import imutils
-
-# download LFW dataset (first run takes a while)
-lfw_people = fetch_lfw_people(min_faces_per_person=1, resize=1, color=True, funneled=False)
-
-# introspect dataset
-n_samples, h, w, c = lfw_people.images.shape
-print(f'{n_samples:,} images at {w}x{h} pixels')
-cols, rows = (176, 76)
-n_ims = cols * rows
-
-# build montages
-im_scale = 0.5
-ims = lfw_people.images[:n_ims]
-montages = imutils.build_montages(ims, (int(w * im_scale, int(h * im_scale)), (cols, rows))
-montage = montages[0]
-
-# save full montage image
-imageio.imwrite('lfw_montage_full.png', montage)
-
-# make a smaller version
-montage = imutils.resize(montage, width=960)
-imageio.imwrite('lfw_montage_960.jpg', montage)
-```
Research, text, and graphics ©Adam Harvey / megapixels.cc
diff --git a/site/includes/map.html b/site/includes/map.html
index 730e30d0..9b99a732 100644
--- a/site/includes/map.html
+++ b/site/includes/map.html
@@ -1,6 +1,6 @@
<section>
- <h3>Biometric Trade Routes</h3>
+ <h3>Information Supply Chain</h3>
<!--
<div class="map-sidebar right-sidebar">
<h3>Legend</h3>
@@ -12,7 +12,7 @@
</div>
-->
<p>
- To understand how this dataset has been used, its citations have been geocoded to show an approximate geographic digital trade route of the biometric data. Lines indicate an organization (education, commercial, or governmental) that has cited the LFW dataset in their research. Data is compiled from <a href="https://www.semanticscholar.org">Semantic Scholar</a>.
+ To understand how and where this dataset has been used, organizations using the dataset are plotted below. The data is generated by collecting all citations for all the original research papers associated with the dataset. The PDFs are then converted to text and the organization names are extracted and geocoded. Because of the automated approach to extracting data, <span style="color:#ff8a72">not all organizations have been confirmed as using the dataset</span>. This visualization is provided to help locate and confirm usage and will be updated as data noise is reduced.
</p>
</section>
@@ -22,7 +22,8 @@
</section>
<div class="caption">
- <div class="map-legend-item"><span class="edu">&#9632;</span> Academic</div>
- <div class="map-legend-item"><span class="com">&#9632;</span> Industry</div>
- <div class="map-legend-item"><span class="gov">&#9632;</span> Government</div>
+ <div class="map-legend-item edu">Academic</div>
+ <div class="map-legend-item com">Industry</div>
+ <div class="map-legend-item gov">Government</div>
+ Data is compiled from <a href="https://www.semanticscholar.org">Semantic Scholar</a> and not yet manually verified.
</div>
diff --git a/site/includes/supplementary_header.html b/site/includes/supplementary_header.html
new file mode 100644
index 00000000..5fd4b2b4
--- /dev/null
+++ b/site/includes/supplementary_header.html
@@ -0,0 +1,10 @@
+<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>
diff --git a/site/public/about/index.html b/site/public/about/index.html
index ed80691a..a1370663 100644
--- a/site/public/about/index.html
+++ b/site/public/about/index.html
@@ -27,10 +27,19 @@
</header>
<div class="content content-about">
- <section><h1>About This Project</h1>
+ <section><h1>About MegaPixels</h1>
</section><section class="about-menu"><ul><li><a href="/about/">About</a></li><li><a href="/about/press/">Press</a></li><li><a href="/about/research/">Research Methodology</a></li><li><a href="/about/disclaimer/">Disclaimer</a></li><li><a href="/about/terms/">Terms and Conditions</a></li><li><a href="/about/privacy/">Privacy Policy</a></li></ul></section><section><p>MegaPixels is an art and research project by Adam Harvey about the origins and ethics of facial analysis datasets. Where do they come from? Who's included? Who created it and for what reason?</p>
<p>MegaPixels sets out to answer to these questions and reveal the stories behind the millions of images used to train, evaluate, and power the facial recognition surveillance algorithms used today. MegaPixels is authored by Adam Harvey, developed in collaboration with Jules LaPlace, and produced in partnership with Mozilla.</p>
<p>MegaPixels sets out to answer to these questions and reveal the stories behind the millions of images used to train, evaluate, and power the facial recognition surveillance algorithms used today. MegaPixels is authored by Adam Harvey, developed in collaboration with Jules LaPlace, and produced in partnership with Mozilla.</p>
+<p>Notes</p>
+<ul>
+<li>critical but informative</li>
+<li>not anti-dataset</li>
+<li>pro-sharing, pro-public dataset</li>
+<li>w/o data</li>
+<li>not generally anti-researcher, their parent organization should have checks in place to prevent dubious dataset collection methods</li>
+<li></li>
+</ul>
</section><section class='images'><div class='sideimage'><img src='https://nyc3.digitaloceanspaces.com/megapixels/v1/site/about/assets/adam-harvey.jpg' alt='Adam Harvey'><div><p><strong>Adam Harvey</strong> is an American artist and researcher based in Berlin. His previous projects (CV Dazzle, Stealth Wear, and SkyLift) explore the potential for countersurveillance as artwork. He is the founder of VFRAME (visual forensics software for human rights groups), the recipient of 2 PrototypeFund awards, and is currently a researcher in residence at Karlsruhe HfG studying artifical intelligence and datasets.</p>
</div></div></section><section class='images'><div class='sideimage'><img src='https://nyc3.digitaloceanspaces.com/megapixels/v1/site/about/assets/jules-laplace.jpg' alt='Jules LaPlace'><div><p><strong>Jules LaPlace</strong> is an American artist and technologist also based in Berlin. He was previously the CTO of a NYC digital agency and currently works at VFRAME, developing computer vision for human rights groups, and building creative software for artists.</p>
</div></div></section><section><h2>Partnership</h2>
diff --git a/site/public/about/press/index.html b/site/public/about/press/index.html
index 0791d2a2..1efe1999 100644
--- a/site/public/about/press/index.html
+++ b/site/public/about/press/index.html
@@ -28,14 +28,7 @@
<div class="content content-about">
<section><h1>Press</h1>
-<ul>
-<li><a href="/about/">About</a></li>
-<li><a href="/about/press/">Press</a></li>
-<li><a href="/about/disclaimer/">Disclaimer</a></li>
-<li><a href="/about/terms/">Terms and Conditions</a></li>
-<li><a href="/about/privacy/">Privacy Policy</a></li>
-</ul>
-</section><section><p>(list of press articles and images will go here)</p>
+</section><section class="about-menu"><ul><li><a href="/about/">About</a></li><li><a href="/about/press/">Press</a></li><li><a href="/about/research/">Research Methodology</a></li><li><a href="/about/disclaimer/">Disclaimer</a></li><li><a href="/about/terms/">Terms and Conditions</a></li><li><a href="/about/privacy/">Privacy Policy</a></li></ul></section><section><p>(list of press articles and images will go here)</p>
<ul>
<li>Aug 22, 2018: "Transgender YouTubers had their videos grabbed to train facial recognition software" by James Vincent <a href="https://www.theverge.com/2017/8/22/16180080/transgender-youtubers-ai-facial-recognition-dataset">https://www.theverge.com/2017/8/22/16180080/transgender-youtubers-ai-facial-recognition-dataset</a></li>
</ul>
diff --git a/site/public/about/privacy/index.html b/site/public/about/privacy/index.html
index 1d9b2252..9a0836a1 100644
--- a/site/public/about/privacy/index.html
+++ b/site/public/about/privacy/index.html
@@ -28,14 +28,7 @@
<div class="content content-about">
<section><h1>Privacy Policy</h1>
-<ul>
-<li><a href="/about/">About</a></li>
-<li><a href="/about/press/">Press</a></li>
-<li><a href="/about/disclaimer/">Disclaimer</a></li>
-<li><a href="/about/terms/">Terms and Conditions</a></li>
-<li><a href="/about/privacy/">Privacy Policy</a></li>
-</ul>
-<p>A summary of our privacy policy is as follows:</p>
+</section><section class="about-menu"><ul><li><a href="/about/">About</a></li><li><a href="/about/press/">Press</a></li><li><a href="/about/research/">Research Methodology</a></li><li><a href="/about/disclaimer/">Disclaimer</a></li><li><a href="/about/terms/">Terms and Conditions</a></li><li><a href="/about/privacy/">Privacy Policy</a></li></ul></section><section><p>A summary of our privacy policy is as follows:</p>
<p>The MegaPixels site does not use any analytics programs or collect any data besides the necessary IP address of your connection, which are deleted every 30 days and used only for security and to prevent misuse.</p>
<p>The image processing sections of the site do not collect any data whatsoever. All processing takes place in temporary memory (RAM) and then is displayed back to the user over a SSL secured HTTPS connection. It is the sole responsibility of the user whether they discard, by closing the page, or share their analyzed information and any potential consequences that may arise from doing so.</p>
<p>A more complete legal version is below:</p>
diff --git a/site/public/about/research/index.html b/site/public/about/research/index.html
index 94b4e2ee..db21fbc3 100644
--- a/site/public/about/research/index.html
+++ b/site/public/about/research/index.html
@@ -28,15 +28,7 @@
<div class="content content-about">
<section><h1>Research Methodologies</h1>
-<ul>
-<li><a href="/about/">About</a></li>
-<li><a href="/about/press/">Press</a></li>
-<li><a href="/about/research/">Research Methodology</a></li>
-<li><a href="/about/disclaimer/">Disclaimer</a></li>
-<li><a href="/about/terms/">Terms and Conditions</a></li>
-<li><a href="/about/privacy/">Privacy Policy</a></li>
-</ul>
-</section>
+</section><section class="about-menu"><ul><li><a href="/about/">About</a></li><li><a href="/about/press/">Press</a></li><li><a href="/about/research/">Research Methodology</a></li><li><a href="/about/disclaimer/">Disclaimer</a></li><li><a href="/about/terms/">Terms and Conditions</a></li><li><a href="/about/privacy/">Privacy Policy</a></li></ul></section>
</div>
<footer>
diff --git a/site/public/about/terms/index.html b/site/public/about/terms/index.html
index 650366e0..b5b9a457 100644
--- a/site/public/about/terms/index.html
+++ b/site/public/about/terms/index.html
@@ -28,16 +28,7 @@
<div class="content content-about">
<section><h1>Terms and Conditions ("Terms")</h1>
-</section><section><div class='left-sidebar'><ul>
-<li><a href="/about/">About</a></li>
-<li><a href="/about/press/">Press</a></li>
-<li><a href="/about/credits/">Credits</a></li>
-<li><a href="/about/research/">Research Methodology</a></li>
-<li><a href="/about/disclaimer/">Disclaimer</a></li>
-<li><a href="/about/terms/">Terms and Conditions</a></li>
-<li><a href="/about/privacy/">Privacy Policy</a></li>
-</ul>
-</div><p>(FPO: this is only example text)</p>
+</section><section class="about-menu"><ul><li><a href="/about/">About</a></li><li><a href="/about/press/">Press</a></li><li><a href="/about/research/">Research Methodology</a></li><li><a href="/about/disclaimer/">Disclaimer</a></li><li><a href="/about/terms/">Terms and Conditions</a></li><li><a href="/about/privacy/">Privacy Policy</a></li></ul></section><section><p>(FPO: this is only example text)</p>
<p>Last updated: December 04, 2018</p>
<p>Please read these Terms and Conditions ("Terms", "Terms and Conditions") carefully before using the MegaPixels website (the "Service") operated by megapixels.cc ("us", "we", or "our").</p>
<p>Your access to and use of the Service is conditioned on your acceptance of and compliance with these Terms.</p>
diff --git a/site/public/datasets/afad/index.html b/site/public/datasets/afad/index.html
new file mode 100644
index 00000000..cfb2dc76
--- /dev/null
+++ b/site/public/datasets/afad/index.html
@@ -0,0 +1,62 @@
+<!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/tabulator.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>
+ </a>
+ <div class='links'>
+ <a href="/datasets/">Datasets</a>
+ <a href="/research/">Research</a>
+ <a href="/about/">About</a>
+ </div>
+ </header>
+ <div class="content content-">
+
+ <section><h1>Asian Face Age Dataset</h1>
+</section><section><div class='meta'><div><div class='gray'>Years</div><div>2016?</div></div><div><div class='gray'>Images</div><div>164,432</div></div><div><div class='gray'>Identities</div><div>4,362</div></div><div><div class='gray'>Origin</div><div>RenRen</div></div></div><section><section><h2>Research</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>
+ <div>
+ <a href="/">MegaPixels.cc</a>
+ <a href="/about/disclaimer/">Disclaimer</a>
+ <a href="/about/terms/">Terms of Use</a>
+ <a href="/about/privacy/">Privacy</a>
+ <a href="/about/">About</a>
+ <a href="/about/team/">Team</a>
+ </div>
+ <div>
+ MegaPixels &copy;2017-19 Adam R. Harvey /&nbsp;
+ <a href="https://ahprojects.com">ahprojects.com</a>
+ </div>
+ </footer>
+</body>
+
+<script src="/assets/js/dist/index.js"></script>
+</html> \ No newline at end of file
diff --git a/site/public/datasets/aflw/index.html b/site/public/datasets/aflw/index.html
new file mode 100644
index 00000000..58291ba1
--- /dev/null
+++ b/site/public/datasets/aflw/index.html
@@ -0,0 +1,55 @@
+<!doctype html>
+<html>
+<head>
+ <title>MegaPixels</title>
+ <meta charset="utf-8" />
+ <meta name="author" content="Adam Harvey" />
+ <meta name="description" content="AFLW: Annotated Facial Landmarks 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/tabulator.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>
+ </a>
+ <div class='links'>
+ <a href="/datasets/">Datasets</a>
+ <a href="/research/">Research</a>
+ <a href="/about/">About</a>
+ </div>
+ </header>
+ <div class="content content-">
+
+ <section><h1>Annotated Facial Landmarks in The Wild</h1>
+</section><section><div class='meta'><div><div class='gray'>Years</div><div>1993-1996</div></div><div><div class='gray'>Images</div><div>25,993</div></div><div><div class='gray'>Identities</div><div>1,199 </div></div><div><div class='gray'>Origin</div><div>Flickr</div></div></div><section><section><!--header--></section><section class='images'><div class='image'><img src='https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/aflw/aflw_index.gif' alt=''></div></section><section><p>RESEARCH below this line</p>
+<blockquote><p>The motivation for the AFLW database is the need for a large-scale, multi-view, real-world face database with annotated facial features. We gathered the images on Flickr using a wide range of face relevant tags (e.g., face, mugshot, profile face). The downloaded set of images was manually scanned for images containing faces. The key data and most important properties of the database are:</p>
+</blockquote>
+<p><a href="https://www.tugraz.at/institute/icg/research/team-bischof/lrs/downloads/aflw/">https://www.tugraz.at/institute/icg/research/team-bischof/lrs/downloads/aflw/</a></p>
+</section>
+
+ </div>
+ <footer>
+ <div>
+ <a href="/">MegaPixels.cc</a>
+ <a href="/about/disclaimer/">Disclaimer</a>
+ <a href="/about/terms/">Terms of Use</a>
+ <a href="/about/privacy/">Privacy</a>
+ <a href="/about/">About</a>
+ <a href="/about/team/">Team</a>
+ </div>
+ <div>
+ MegaPixels &copy;2017-19 Adam R. Harvey /&nbsp;
+ <a href="https://ahprojects.com">ahprojects.com</a>
+ </div>
+ </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
new file mode 100644
index 00000000..94a5e395
--- /dev/null
+++ b/site/public/datasets/brainwash/index.html
@@ -0,0 +1,82 @@
+<!doctype html>
+<html>
+<head>
+ <title>MegaPixels</title>
+ <meta charset="utf-8" />
+ <meta name="author" content="Adam Harvey" />
+ <meta name="description" content="<span style="color:#ffaa00">Brainwash</span> is a dataset of people from webcams the Brainwash Cafe in San Francisco being used to train face detection 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/tabulator.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>
+ </a>
+ <div class='links'>
+ <a href="/datasets/">Datasets</a>
+ <a href="/research/">Research</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'><span style="color:#ffaa00">Brainwash</span> is a dataset of people from webcams the Brainwash Cafe in San Francisco being used to train face detection algorithms</span></div><div class='hero_subdesc'><span class='bgpad'>Brainwash dataset includes 11,918 images of people getting coffee at the Brainwash cafe during 2014
+</span></div></div></section><section><div class='left-sidebar'><div class='meta'><div><div class='gray'>Collected</div><div>2014</div></div><div><div class='gray'>Published</div><div>2015</div></div><div><div class='gray'>Images</div><div>11,917</div></div><div><div class='gray'>Faces</div><div>91,146</div></div><div><div class='gray'>Created by</div><div>Stanford Department of Computer Science</div></div><div><div class='gray'>Funded by</div><div>Max Planck Center for Visual Computing and Communication</div></div><div><div class='gray'>Resolution</div><div>640x480px</div></div><div><div class='gray'>Origin</div><div>Brainwash Cafe, San Franscisco</div></div><div><div class='gray'>Purpose</div><div>Training face detection</div></div><div><div class='gray'>Website</div><div><a href="https://exhibits.stanford.edu/data/catalog/sx925dc9385">stanford.edu</a></div></div></div><ul>
+<li>more info1</li>
+<li>more info2</li>
+<li>more info3</li>
+</ul>
+</div><h2>Brainwash Dataset</h2>
+<p><em>Brainwash</em> is a face detection dataset created from the Brainwash Cafe's livecam footage. The stream is It was published in 2015 by researchers at the Stanford University and has been used 1122 Folsom Street​ | USA</p>
+<p>The photos were collected on</p>
+<ul>
+<li>Oct 27, 2014</li>
+<li>Nov 11, 2014</li>
+<li>Nov 245, 2017</li>
+</ul>
+<p>Sed ut perspiciatis, unde omnis iste natus error sit voluptatem accusantium doloremque laudantium, totam rem aperiam eaque ipsa, quae ab illo inventore veritatis et quasi architecto beatae vitae dicta sunt, explicabo. Nemo enim ipsam voluptatem, quia voluptas sit, aspernatur aut odit aut fugit, sed quia consequuntur magni dolores eos, qui ratione voluptatem sequi nesciunt, neque porro quisquam est, qui dolorem ipsum, quia dolor sit amet consectetur adipisci[ng] velit, sed quia non-numquam [do] eius modi tempora inci[di]dunt, ut labore et dolore magnam aliquam quaerat voluptatem. Ut enim ad minima veniam.</p>
+</section><section class='images'><div class='image'><img src='https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/brainwash/assets/00425000_960.jpg' alt=' An sample image from the Brainwash dataset used for training face detection algorithms for surveillance. The datset contains over 12,000 images. License: Open Data Commons Public Domain Dedication (PDDL)'><div class='caption'> An sample image from the Brainwash dataset used for training face detection algorithms for surveillance. The datset contains over 12,000 images. License: Open Data Commons Public Domain Dedication (PDDL)</div></div></section><section><p>porro quisquam est, qui dolorem ipsum, quia dolor sit amet consectetur adipisci[ng] velit, sed quia non-numquam [do] eius modi tempora inci[di]dunt, ut labore et dolore magnam aliquam quaerat voluptatem. Ut enim ad minima veniam, quis nostrum[d] exercitationem ullam corporis suscipit laboriosam, nisi ut aliquid ex ea commodi consequatur? Quis autem vel eum iure reprehenderit, qui in ea voluptate velit esse, quam nihil molestiae consequatur, vel illum, qui dolorem eum fugiat, quo voluptas nulla pariatur?</p>
+</section><section> <h3>Biometric Trade Routes</h3><!-- <div class="map-sidebar right-sidebar"> <h3>Legend</h3> <ul> <li><span style="color: #f2f293">&#9632;</span> Industry</li> <li><span style="color: #f30000">&#9632;</span> Academic</li> <li><span style="color: #3264f6">&#9632;</span> Government</li> </ul> </div> --> <p> To understand how this dataset has been used, its citations have been geocoded to show an approximate geographic digital trade route of the biometric data. Lines indicate an organization (education, commercial, or governmental) that has cited the LFW dataset in their research.</a>. </p> </section><section class="applet_container"> <div class="applet" data-payload="{&quot;command&quot;: &quot;map&quot;}"></div></section><div class="caption"> <div class="map-legend-item"><span class="edu">&#9632;</span> Academic</div> <div class="map-legend-item"><span class="com">&#9632;</span> Industry</div> <div class="map-legend-item"><span class="gov">&#9632;</span> Government</div> Data is compiled from <a href="https://www.semanticscholar.org">Semantic Scholar</a></div><section><p>A short analysis of the map information</p>
+</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="applet_container"> <h3>Citations</h3> <p>Add graph showing distribution by country. Add information about how the citations were generated. Add button/link to download CSV</p> <div class="applet" data-payload="{&quot;command&quot;: &quot;citations&quot;}"></div></section><section><p>RESEARCH below this line</p>
+<p>The file is 4.1GB</p>
+<ul>
+<li>add sha256 hash</li>
+<li>the images were taken from Dropcam which was runnign on <a href="https://www.angelcam.com/">https://www.angelcam.com/</a> "Angelcam’s Real-time Surveillance takes the weight of keeping your home or business secure off your shoulders."</li>
+</ul>
+<blockquote><p>This package contains the "Brainwash" dataset. The dataset consists of images capturing the everyday life of a busy downtown cafe and is split into the following subsets:
+training set: 10769 with 81975 annotated people
+validation set: 500 images with 3318 annotated people
+test set: 500 images with 5007 annotated people</p>
+<p>Bounding box annotations are provided in a simple text file format. Each line in the file contains
+image name followed by the list of annotation rectangles in the [xmin, ymin, max, ymax] format.</p>
+<p>We refer to the following arXiv submission for details on the dataset and the evaluation procedure:</p>
+</blockquote>
+<p><a href="http://arxiv.org/abs/1506.04878">http://arxiv.org/abs/1506.04878</a></p>
+</section>
+
+ </div>
+ <footer>
+ <div>
+ <a href="/">MegaPixels.cc</a>
+ <a href="/about/disclaimer/">Disclaimer</a>
+ <a href="/about/terms/">Terms of Use</a>
+ <a href="/about/privacy/">Privacy</a>
+ <a href="/about/">About</a>
+ <a href="/about/team/">Team</a>
+ </div>
+ <div>
+ MegaPixels &copy;2017-19 Adam R. Harvey /&nbsp;
+ <a href="https://ahprojects.com">ahprojects.com</a>
+ </div>
+ </footer>
+</body>
+
+<script src="/assets/js/dist/index.js"></script>
+</html> \ No newline at end of file
diff --git a/site/public/about/credits/index.html b/site/public/datasets/caltech_10k/index.html
index 7f3da564..c9d98e99 100644
--- a/site/public/about/credits/index.html
+++ b/site/public/datasets/caltech_10k/index.html
@@ -4,7 +4,7 @@
<title>MegaPixels</title>
<meta charset="utf-8" />
<meta name="author" content="Adam Harvey" />
- <meta name="description" content="MegaPixels Project Team Credits" />
+ <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' />
@@ -25,18 +25,10 @@
<a href="/about/">About</a>
</div>
</header>
- <div class="content">
+ <div class="content content-">
- <section><h1>Credits</h1>
-</section><section><div class='right-sidebar'><ul>
-<li><a href="/about/">About</a></li>
-<li><a href="/about/press/">Press</a></li>
-<li><a href="/about/credits/">Credits</a></li>
-<li><a href="/about/disclaimer/">Disclaimer</a></li>
-<li><a href="/about/terms/">Terms and Conditions</a></li>
-<li><a href="/about/privacy/">Privacy Policy</a></li>
-</ul>
-</div></section>
+ <section><h1>Caltech 10K Faces Dataset</h1>
+</section><section><div class='meta'><div><div class='gray'>Years</div><div>TBD</div></div><div><div class='gray'>Images</div><div>TBD</div></div><div><div class='gray'>Identities</div><div>TBD</div></div><div><div class='gray'>Origin</div><div>Google Search</div></div><div><div class='gray'>Funding</div><div>TBD</div></div></div><section>
</div>
<footer>
diff --git a/site/public/datasets/cofw/index.html b/site/public/datasets/cofw/index.html
new file mode 100644
index 00000000..82842955
--- /dev/null
+++ b/site/public/datasets/cofw/index.html
@@ -0,0 +1,66 @@
+<!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/tabulator.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>
+ </a>
+ <div class='links'>
+ <a href="/datasets/">Datasets</a>
+ <a href="/research/">Research</a>
+ <a href="/about/">About</a>
+ </div>
+ </header>
+ <div class="content content-">
+
+ <section><h1>Caltech Occluded Faces in The Wild</h1>
+</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><!--header--></section><section class='images'><div class='image'><img src='https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/cofw/assets/cofw_index.gif' alt=''></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>
+<p>RESEARCH below this line</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&amp;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>
+<p>TODO</p>
+<h2>- replace graphic</h2>
+</section>
+
+ </div>
+ <footer>
+ <div>
+ <a href="/">MegaPixels.cc</a>
+ <a href="/about/disclaimer/">Disclaimer</a>
+ <a href="/about/terms/">Terms of Use</a>
+ <a href="/about/privacy/">Privacy</a>
+ <a href="/about/">About</a>
+ <a href="/about/team/">Team</a>
+ </div>
+ <div>
+ MegaPixels &copy;2017-19 Adam R. Harvey /&nbsp;
+ <a href="https://ahprojects.com">ahprojects.com</a>
+ </div>
+ </footer>
+</body>
+
+<script src="/assets/js/dist/index.js"></script>
+</html> \ No newline at end of file
diff --git a/site/public/datasets/facebook/index.html b/site/public/datasets/facebook/index.html
new file mode 100644
index 00000000..a9f1b225
--- /dev/null
+++ b/site/public/datasets/facebook/index.html
@@ -0,0 +1,56 @@
+<!doctype html>
+<html>
+<head>
+ <title>MegaPixels</title>
+ <meta charset="utf-8" />
+ <meta name="author" content="Adam Harvey" />
+ <meta name="description" content="TBD" />
+ <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/tabulator.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>
+ </a>
+ <div class='links'>
+ <a href="/datasets/">Datasets</a>
+ <a href="/research/">Research</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/facebook/assets/background.jpg)'><div class='inner'><div class='hero_desc'><span class='bgpad'>TBD</span></div><div class='hero_subdesc'><span class='bgpad'>TBD
+</span></div></div></section><section><div class='image'><div class='intro-caption caption'>TBD</div></div></section><section><h3>Statistics</h3>
+<div class='meta'><div><div class='gray'>Years</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'>Funding</div><div>(Possibly, partially CIA)</div></div></div><p>Ignore content below these lines</p>
+<ul>
+<li>Tool to create face datasets from Facebook <a href="https://github.com/ankitaggarwal011/FaceGrab">https://github.com/ankitaggarwal011/FaceGrab</a></li>
+</ul>
+</section>
+
+ </div>
+ <footer>
+ <div>
+ <a href="/">MegaPixels.cc</a>
+ <a href="/about/disclaimer/">Disclaimer</a>
+ <a href="/about/terms/">Terms of Use</a>
+ <a href="/about/privacy/">Privacy</a>
+ <a href="/about/">About</a>
+ <a href="/about/team/">Team</a>
+ </div>
+ <div>
+ MegaPixels &copy;2017-19 Adam R. Harvey /&nbsp;
+ <a href="https://ahprojects.com">ahprojects.com</a>
+ </div>
+ </footer>
+</body>
+
+<script src="/assets/js/dist/index.js"></script>
+</html> \ No newline at end of file
diff --git a/site/public/datasets/feret/index.html b/site/public/datasets/feret/index.html
new file mode 100644
index 00000000..51f9038a
--- /dev/null
+++ b/site/public/datasets/feret/index.html
@@ -0,0 +1,68 @@
+<!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/tabulator.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>
+ </a>
+ <div class='links'>
+ <a href="/datasets/">Datasets</a>
+ <a href="/research/">Research</a>
+ <a href="/about/">About</a>
+ </div>
+ </header>
+ <div class="content content-">
+
+ <section><h1>FERET</h1>
+</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>Fairfax, MD</div></div></div><section><section><!--header--></section><section class='images'><div class='image'><img src='https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/feret/assets/feret_index.gif' alt=''></div></section><section><p><em>Facial Recognition Evaluation</em> (FERET) is develop, test, and evaluate face recognition algorithms</p>
+<p>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.</p>
+<ul>
+<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>
+<p>RESEARCH below this line</p>
+<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>
+ <div>
+ <a href="/">MegaPixels.cc</a>
+ <a href="/about/disclaimer/">Disclaimer</a>
+ <a href="/about/terms/">Terms of Use</a>
+ <a href="/about/privacy/">Privacy</a>
+ <a href="/about/">About</a>
+ <a href="/about/team/">Team</a>
+ </div>
+ <div>
+ MegaPixels &copy;2017-19 Adam R. Harvey /&nbsp;
+ <a href="https://ahprojects.com">ahprojects.com</a>
+ </div>
+ </footer>
+</body>
+
+<script src="/assets/js/dist/index.js"></script>
+</html> \ No newline at end of file
diff --git a/site/public/datasets/index.html b/site/public/datasets/index.html
index 9cd50016..313ed91e 100644
--- a/site/public/datasets/index.html
+++ b/site/public/datasets/index.html
@@ -29,6 +29,7 @@
<section><h1>Facial Recognition Datasets</h1>
+<p>[add text, make sortable] This is a list of all the facial recognition datasets</p>
</section>
<section class='wide dataset-intro'>
diff --git a/site/public/datasets/lfpw/index.html b/site/public/datasets/lfpw/index.html
new file mode 100644
index 00000000..385bd189
--- /dev/null
+++ b/site/public/datasets/lfpw/index.html
@@ -0,0 +1,58 @@
+<!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/tabulator.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>
+ </a>
+ <div class='links'>
+ <a href="/datasets/">Datasets</a>
+ <a href="/research/">Research</a>
+ <a href="/about/">About</a>
+ </div>
+ </header>
+ <div class="content content-">
+
+ <section><h1>Labeled Face Parts in The Wild</h1>
+</section><section><div class='meta'><div><div class='gray'>Year</div><div>2011</div></div><div><div class='gray'>Images</div><div>1,432</div></div><div><div class='gray'>Origin</div><div>Flickr</div></div><div><div class='gray'>Funding</div><div>CIA</div></div></div><section><section class='images'><div class='image'><img src='https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/lfpw/assets/background.jpg' alt=''></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>
+ <div>
+ <a href="/">MegaPixels.cc</a>
+ <a href="/about/disclaimer/">Disclaimer</a>
+ <a href="/about/terms/">Terms of Use</a>
+ <a href="/about/privacy/">Privacy</a>
+ <a href="/about/">About</a>
+ <a href="/about/team/">Team</a>
+ </div>
+ <div>
+ MegaPixels &copy;2017-19 Adam R. Harvey /&nbsp;
+ <a href="https://ahprojects.com">ahprojects.com</a>
+ </div>
+ </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
index e90cdcc5..3c7fd45f 100644
--- a/site/public/datasets/lfw/index.html
+++ b/site/public/datasets/lfw/index.html
@@ -27,8 +27,8 @@
</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><span style="color:#ff0000">Labeled Faces in The Wild (LFW)</span> is a database of face photographs designed for studying the problem of unconstrained face recognition.</span></div><div class='hero_subdesc'><span>It includes 13,456 images of 4,432 people's images copied from the Internet during 2002-2004.
-</span></div></div></section><section><div class='image'><div class='intro-caption caption'>A few of the 5,749 people in the Labeled Faces in the Wild Dataset, thee most widely used face dataset for benchmarking face recognition algorithms.</div></div></section><section><div class='left-sidebar'><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">vis-www.cs.umass.edu/lfw</a></div></div></div><ul>
+ <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 style="color:#ff0000">Labeled Faces in The Wild (LFW)</span> is a database of face photographs designed for studying the problem of unconstrained face recognition.</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.
+</span></div></div></section><section><div class='left-sidebar'><div class='meta'><div><div class='gray'>Created</div><div>2002 &ndash; 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><ul>
<li>There are about 3 men for every 1 woman in the LFW dataset<a class="footnote_shim" name="[^lfw_www]_1"> </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>
@@ -44,47 +44,10 @@
<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>Biometric Trade Routes</h3><!-- <div class="map-sidebar right-sidebar"> <h3>Legend</h3> <ul> <li><span style="color: #f2f293">&#9632;</span> Industry</li> <li><span style="color: #f30000">&#9632;</span> Academic</li> <li><span style="color: #3264f6">&#9632;</span> Government</li> </ul> </div> --> <p> To understand how this dataset has been used, its citations have been geocoded to show an approximate geographic digital trade route of the biometric data. Lines indicate an organization (education, commercial, or governmental) that has cited the LFW dataset in their research. Data is compiled from <a href="https://www.semanticscholar.org">Semantic Scholar</a>. </p> </section><section class="applet_container"> <div class="applet" data-payload="{&quot;command&quot;: &quot;map&quot;}"></div></section><div class="caption"> <div class="map-legend-item"><span class="edu">&#9632;</span> Academic</div> <div class="map-legend-item"><span class="com">&#9632;</span> Industry</div> <div class="map-legend-item"><span class="gov">&#9632;</span> Government</div></div><section><p>Sed ut perspiciatis, unde omnis iste natus error sit voluptatem accusantium doloremque laudantium, totam rem aperiam eaque ipsa, quae ab illo inventore veritatis et quasi architecto beatae vitae dicta sunt, explicabo. Nemo enim ipsam voluptatem, quia voluptas sit, aspernatur aut odit aut fugit, sed quia.</p>
-<hr class="supp">
-
-<h2>Supplementary Information for Labeled Faces in The Wild</h2>
-</section><section class="applet_container"> <h3>Citations</h3> <p>Add graph showing distribution by country. Add information about how the citations were generated. Add button/link to download CSV</p> <div class="applet" data-payload="{&quot;command&quot;: &quot;citations&quot;}"></div></section><section> <h3>Synthetic Faces</h3> <p>To visualize the types of photos in the dataset without explicitly publishing individual's identities a generative adversarial network (GAN) was trained on the entire dataset. The images in this video show a neural network learning the visual latent space and then interpolating between archetypical identities within the LFW dataset.</p></section><section class='images'><div class='image'><img src='https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/lfw/assets/synthetic_01.jpg' alt='Synthetically generated face from the visual space of LFW dataset'><div class='caption'>Synthetically generated face from the visual space of LFW dataset</div></div>
-<div class='image'><img src='https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/lfw/assets/synthetic_02.jpg' alt='Synthetically generated face from the visual space of LFW dataset'><div class='caption'>Synthetically generated face from the visual space of LFW dataset</div></div>
-<div class='image'><img src='https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/lfw/assets/synthetic_03.jpg' alt='Synthetically generated face from the visual space of LFW dataset'><div class='caption'>Synthetically generated face from the visual space of LFW dataset</div></div>
-<div class='image'><img src='https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/lfw/assets/synthetic_01.jpg' alt='Synthetically generated face from the visual space of LFW dataset'><div class='caption'>Synthetically generated face from the visual space of LFW dataset</div></div></section><section><h3>Commercial Use of Labeled Faces in The Wild</h3>
+</section><section> <h3>Biometric Trade Routes</h3><!-- <div class="map-sidebar right-sidebar"> <h3>Legend</h3> <ul> <li><span style="color: #f2f293">&#9632;</span> Industry</li> <li><span style="color: #f30000">&#9632;</span> Academic</li> <li><span style="color: #3264f6">&#9632;</span> Government</li> </ul> </div> --> <p> To understand how this dataset has been used, its citations have been geocoded to show an approximate geographic digital trade route of the biometric data. Lines indicate an organization (education, commercial, or governmental) that has cited the LFW dataset in their research.</a>. </p> </section><section class="applet_container"> <div class="applet" data-payload="{&quot;command&quot;: &quot;map&quot;}"></div></section><div class="caption"> <div class="map-legend-item"><span class="edu">&#9632;</span> Academic</div> <div class="map-legend-item"><span class="com">&#9632;</span> Industry</div> <div class="map-legend-item"><span class="gov">&#9632;</span> Government</div> Data is compiled from <a href="https://www.semanticscholar.org">Semantic Scholar</a></div><section><p>Sed ut perspiciatis, unde omnis iste natus error sit voluptatem accusantium doloremque laudantium, totam rem aperiam eaque ipsa, quae ab illo inventore veritatis et quasi architecto beatae vitae dicta sunt, explicabo. Nemo enim ipsam voluptatem, quia voluptas sit, aspernatur aut odit aut fugit, sed quia.</p>
+</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="applet_container"> <h3>Citations</h3> <p>Add graph showing distribution by country. Add information about how the citations were generated. Add button/link to download CSV</p> <div class="applet" data-payload="{&quot;command&quot;: &quot;citations&quot;}"></div></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>Code</h3>
-<p>The LFW dataset is so widely used that access to the facial data has built directly into a popular code library called Sci-Kit Learn. It includes a function called <code>fetch_lfw_people</code> to download the faces in the LFW dataset.</p>
-</section><section><pre><code class="lang-python">#!/usr/bin/python
-
-import numpy as np
-from sklearn.datasets import fetch_lfw_people
-import imageio
-import imutils
-
-# download LFW dataset (first run takes a while)
-lfw_people = fetch_lfw_people(min_faces_per_person=1, resize=1, color=True, funneled=False)
-
-# introspect dataset
-n_samples, h, w, c = lfw_people.images.shape
-print(f&#39;{n_samples:,} images at {w}x{h} pixels&#39;)
-cols, rows = (176, 76)
-n_ims = cols * rows
-
-# build montages
-im_scale = 0.5
-ims = lfw_people.images[:n_ims]
-montages = imutils.build_montages(ims, (int(w * im_scale, int(h * im_scale)), (cols, rows))
-montage = montages[0]
-
-# save full montage image
-imageio.imwrite(&#39;lfw_montage_full.png&#39;, montage)
-
-# make a smaller version
-montage = imutils.resize(montage, width=960)
-imageio.imwrite(&#39;lfw_montage_960.jpg&#39;, montage)
-</code></pre>
-</section><section><p>Research, text, and graphics ©Adam Harvey / megapixels.cc</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><p>Research, text, and graphics ©Adam Harvey / megapixels.cc</p>
</section><section><ul class="footnotes"><li><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><p><a href="http://vis-www.cs.umass.edu/lfw/results.html">http://vis-www.cs.umass.edu/lfw/results.html</a></p>
</li><li><a name="[^lfw_baidu]" class="footnote_shim"></a><span class="backlinks"></span><p>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></p>
</li><li><a name="[^lfw_pingan]" class="footnote_shim"></a><span class="backlinks"><a href="#[^lfw_pingan]_1">a</a></span><p>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></p>
diff --git a/site/public/datasets/lfw/right-to-removal/index.html b/site/public/datasets/lfw/right-to-removal/index.html
new file mode 100644
index 00000000..5dc269b2
--- /dev/null
+++ b/site/public/datasets/lfw/right-to-removal/index.html
@@ -0,0 +1,62 @@
+<!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/tabulator.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>
+ </a>
+ <div class='links'>
+ <a href="/datasets/">Datasets</a>
+ <a href="/research/">Research</a>
+ <a href="/about/">About</a>
+ </div>
+ </header>
+ <div class="content">
+
+ <section><h1>Labeled Faces in the Wild</h1>
+<h2>Right to Removal</h2>
+<p>If you are affected by disclosure of your identity in this dataset please do contact the authors. Many have stated that they are willing to remove images upon request. The authors of the LFW dataset provide the following email for inquiries:</p>
+<p>You can use the following message to request removal from the dataset:</p>
+<p>To: Gary Huang <a href="mailto:mailto:gbhuang@cs.umass.edu">mailto:gbhuang@cs.umass.edu</a></p>
+<p>Subject: Request for Removal from LFW Face Dataset</p>
+<p>Dear [researcher name],</p>
+<p>I am writing to you about the "Labeled Faces in The Wild Dataset". Recently I discovered that your dataset includes my identity and I no longer wish to be included in your dataset.</p>
+<p>The dataset is being used thousands of companies around the world to improve facial recognition software including usage by governments for the purpose of law enforcement, national security, tracking consumers in retail environments, and tracking individuals through public spaces.</p>
+<p>My name as it appears in your dataset is [your name]. Please remove all images from your dataset and inform your newsletter subscribers to likewise update their copies.</p>
+<p>- [your name]</p>
+<hr>
+</section>
+
+ </div>
+ <footer>
+ <div>
+ <a href="/">MegaPixels.cc</a>
+ <a href="/about/disclaimer/">Disclaimer</a>
+ <a href="/about/terms/">Terms of Use</a>
+ <a href="/about/privacy/">Privacy</a>
+ <a href="/about/">About</a>
+ <a href="/about/team/">Team</a>
+ </div>
+ <div>
+ MegaPixels &copy;2017-19 Adam R. Harvey /&nbsp;
+ <a href="https://ahprojects.com">ahprojects.com</a>
+ </div>
+ </footer>
+</body>
+
+<script src="/assets/js/dist/index.js"></script>
+</html> \ No newline at end of file
diff --git a/site/public/datasets/lfw/tables/index.html b/site/public/datasets/lfw/tables/index.html
new file mode 100644
index 00000000..dd460843
--- /dev/null
+++ b/site/public/datasets/lfw/tables/index.html
@@ -0,0 +1,52 @@
+<!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/tabulator.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>
+ </a>
+ <div class='links'>
+ <a href="/datasets/">Datasets</a>
+ <a href="/research/">Research</a>
+ <a href="/about/">About</a>
+ </div>
+ </header>
+ <div class="content">
+
+ <section><h1>Labeled Faces in the Wild</h1>
+<h2>Tables</h2>
+</section><section class='applet_container'><div class='applet' data-payload='{"command": "load_file assets/lfw_names_gender_kg_min.csv", "fields": ["Name, Images, Gender, Description"]}'></div></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></section>
+
+ </div>
+ <footer>
+ <div>
+ <a href="/">MegaPixels.cc</a>
+ <a href="/about/disclaimer/">Disclaimer</a>
+ <a href="/about/terms/">Terms of Use</a>
+ <a href="/about/privacy/">Privacy</a>
+ <a href="/about/">About</a>
+ <a href="/about/team/">Team</a>
+ </div>
+ <div>
+ MegaPixels &copy;2017-19 Adam R. Harvey /&nbsp;
+ <a href="https://ahprojects.com">ahprojects.com</a>
+ </div>
+ </footer>
+</body>
+
+<script src="/assets/js/dist/index.js"></script>
+</html> \ No newline at end of file
diff --git a/site/public/datasets/uccs/index.html b/site/public/datasets/uccs/index.html
new file mode 100644
index 00000000..21d1e6bb
--- /dev/null
+++ b/site/public/datasets/uccs/index.html
@@ -0,0 +1,90 @@
+<!doctype html>
+<html>
+<head>
+ <title>MegaPixels</title>
+ <meta charset="utf-8" />
+ <meta name="author" content="Adam Harvey" />
+ <meta name="description" content="UCCS: Unconstrained College Students" />
+ <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/tabulator.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>
+ </a>
+ <div class='links'>
+ <a href="/datasets/">Datasets</a>
+ <a href="/research/">Research</a>
+ <a href="/about/">About</a>
+ </div>
+ </header>
+ <div class="content content-">
+
+ <section><h1>Unconstrained College Students</h1>
+</section><section><div class='meta'><div><div class='gray'>Years</div><div>2012-2013</div></div><div><div class='gray'>Images</div><div>16,149</div></div><div><div class='gray'>Identities</div><div>4,362</div></div><div><div class='gray'>Origin</div><div>Colorado Springs Campus</div></div></div><section><section class='fullwidth'><div class='image'><img src='https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/uccs/images/uccs_index.gif' alt='Pixellated and redacted example image from the UCCS dataset. ©Adam Harvey'><div class='caption'>Pixellated and redacted example image from the UCCS dataset. ©Adam Harvey</div></div></section><section><p><strong>Unconstrained College Students</strong> is a large-scale, unconstrained face detection and recognition dataset. It includes</p>
+<p>The UCCS includes...</p>
+<h3>Funding Sources</h3>
+<p>The original Sapkota and Boult dataset, from which UCCS is derived, received funding from[^funding_sb]:</p>
+<ul>
+<li>ONR (Office of Naval Research) MURI (The Department of Defense Multidisciplinary University Research Initiative) grant N00014-08-1-0638</li>
+<li>Army SBIR (Small Business Innovation Research) grant W15P7T-12-C-A210</li>
+<li>SOCOM (Special Operations Command) SBIR (Small Business Innovation Research) grant H92222-07-P-0020</li>
+</ul>
+<p>The more recent UCCS version of the dataset received funding from [^funding_uccs]:</p>
+<ul>
+<li>National Science Foundation Grant IIS-1320956</li>
+<li>ODNI (Office of Director of National Intelligence)</li>
+<li>IARPA (Intelligence Advance Research Projects Activity) R&amp;D contract 2014-14071600012</li>
+</ul>
+<h3>Citations</h3>
+<p>[add map here]</p>
+<p>[add citations table here]</p>
+</section><section class='fullwidth'><div class='image'><img src='https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/uccs/images/uccs_synthetic.jpg' alt='Pixellated and redacted example image from the UCCS dataset. ©Adam Harvey'><div class='caption'>Pixellated and redacted example image from the UCCS dataset. ©Adam Harvey</div></div></section><section><h3>Notes</h3>
+<ul>
+<li>Images from UCCS are not available for public display. Instead a pixellated, redacted, and colored interpretation has been displayed here. The full images are available here.</li>
+<li>Images can be downloaded from...</li>
+</ul>
+<h3>Resources</h3>
+<ul>
+<li>Download video</li>
+<li>links to UCCS</li>
+<li>download synthetic images</li>
+</ul>
+<h3>Image Terms of Use</h3>
+<ul>
+<li>All images are ©Adam Harvey / megapixels.cc</li>
+<li>You are welcomed to use these images for academic and journalistic use including for research papers, news stories, presentations. </li>
+<li>Please use the following citation:</li>
+</ul>
+</section><section class='applet_container'><div class='applet' data-payload='{"command": "MegaPixels.cc Adam Harvey 2013-2019."}'></div></section><section><div class="footnotes">
+<hr>
+<ol></ol>
+</div>
+</section>
+
+ </div>
+ <footer>
+ <div>
+ <a href="/">MegaPixels.cc</a>
+ <a href="/about/disclaimer/">Disclaimer</a>
+ <a href="/about/terms/">Terms of Use</a>
+ <a href="/about/privacy/">Privacy</a>
+ <a href="/about/">About</a>
+ <a href="/about/team/">Team</a>
+ </div>
+ <div>
+ MegaPixels &copy;2017-19 Adam R. Harvey /&nbsp;
+ <a href="https://ahprojects.com">ahprojects.com</a>
+ </div>
+ </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
new file mode 100644
index 00000000..f830eb3a
--- /dev/null
+++ b/site/public/datasets/youtube_celebrities/index.html
@@ -0,0 +1,65 @@
+<!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/tabulator.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>
+ </a>
+ <div class='links'>
+ <a href="/datasets/">Datasets</a>
+ <a href="/research/">Research</a>
+ <a href="/about/">About</a>
+ </div>
+ </header>
+ <div class="content content-">
+
+ <section><h1>YouTube Celebrities</h1>
+</section><section><div class='meta'><div><div class='gray'>Years</div><div>TBD</div></div><div><div class='gray'>Images</div><div>TBD</div></div><div><div class='gray'>Identities</div><div>TBD</div></div><div><div class='gray'>Origin</div><div>YouTube.com</div></div><div><div class='gray'>Funded by</div><div>CIA, US Army</div></div></div><section><section><p>TODO</p>
+<p>RESEARCH below these lines</p>
+<blockquote><p>Selected dataset sequences: (a) MBGC, (b) CMU MoBo, (c) First
+Honda/UCSD, and (d) YouTube Celebrities.
+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.</p>
+</blockquote>
+<ul>
+<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>
+ <div>
+ <a href="/">MegaPixels.cc</a>
+ <a href="/about/disclaimer/">Disclaimer</a>
+ <a href="/about/terms/">Terms of Use</a>
+ <a href="/about/privacy/">Privacy</a>
+ <a href="/about/">About</a>
+ <a href="/about/team/">Team</a>
+ </div>
+ <div>
+ MegaPixels &copy;2017-19 Adam R. Harvey /&nbsp;
+ <a href="https://ahprojects.com">ahprojects.com</a>
+ </div>
+ </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 d5a2e59f..cb357e3f 100644
--- a/site/public/index.html
+++ b/site/public/index.html
@@ -3,8 +3,8 @@
<head>
<title>MegaPixels</title>
<meta charset="utf-8" />
- <meta name="author" content="info@megapixels.cc" />
- <meta name="description" content="The Dark Side of Datasets" />
+ <meta name="author" content="Adam Harvey, ahprojects.com" />
+ <meta name="description" content="MegaPixels: Facial Recognition Datasets" />
<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' />
@@ -17,7 +17,7 @@
<div class='logo'></div>
<div class='site_name'>MegaPixels</div>
</a>
- <div class='links'>
+ <div class='links splash'>
<a href="/datasets/" class='aboutLink'>DATASETS</a>
<a href="/research/" class='aboutLink'>RESEARCH</a>
<a href="/about/" class='aboutLink'>ABOUT</a>
@@ -28,6 +28,7 @@
</div>
<footer>
<div>
+ MegaPixels is an art and research project by Adam Harvey about the origins and ethics of facial analysis datasets
</div>
<div>
MegaPixels &copy;2017-19 Adam R. Harvey /&nbsp;
diff --git a/site/templates/home.html b/site/templates/home.html
index d5a2e59f..cb357e3f 100644
--- a/site/templates/home.html
+++ b/site/templates/home.html
@@ -3,8 +3,8 @@
<head>
<title>MegaPixels</title>
<meta charset="utf-8" />
- <meta name="author" content="info@megapixels.cc" />
- <meta name="description" content="The Dark Side of Datasets" />
+ <meta name="author" content="Adam Harvey, ahprojects.com" />
+ <meta name="description" content="MegaPixels: Facial Recognition Datasets" />
<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' />
@@ -17,7 +17,7 @@
<div class='logo'></div>
<div class='site_name'>MegaPixels</div>
</a>
- <div class='links'>
+ <div class='links splash'>
<a href="/datasets/" class='aboutLink'>DATASETS</a>
<a href="/research/" class='aboutLink'>RESEARCH</a>
<a href="/about/" class='aboutLink'>ABOUT</a>
@@ -28,6 +28,7 @@
</div>
<footer>
<div>
+ MegaPixels is an art and research project by Adam Harvey about the origins and ethics of facial analysis datasets
</div>
<div>
MegaPixels &copy;2017-19 Adam R. Harvey /&nbsp;
diff --git a/todo.md b/todo.md
index e9eca615..300d7879 100644
--- a/todo.md
+++ b/todo.md
@@ -2,9 +2,10 @@
## Splash
- - AH: work on CTA overlay design
- - AH: render one head from each activate dataset
- - JL: add "Name / Dataset Name" below head? and make linkable to dataset?
+- AH: work on CTA overlay design
+- AH: render one head from each activate dataset
+- JL: add "Name \n Dataset Name" below head? and make linkable to dataset?
+- change animation to be only colored vertices <---> colored landmarks
## Datasets Index
@@ -14,23 +15,22 @@
## Datasets
- overall looking really good
-- AH: small CSS tweaks to font
-- JL: possible to fade in background graphic?
+- JL: possible to fade in background header graphic?
- AH: add more synthetic faces
- modify layout into section:
- Overview
- Citations
- Supplementary Information
-
-### Dataset Citations:
-
-- JL: add URL text and href to citations
-- JL: add download button and search option for CSV?
+- modify layout for synthetic images (1 large image/video left column, 4 small thumbnails right column)
+- [x] JL: add URL text and href to citations
+- JL: add download (button) and search option for CSV? or link to github
- AH: Try creating another google doc to manually review each citation and send to FT to maybe help with review
-- AH/JL: add color legend to citations (red, blue, yellow)
+- JL/AH: add graph showing distribtion by country
+- JL/AH: add graph/number display showing distribution by sector (edu, gov, com)
## About
+- layout still feels awkward
- AH: update text and images
- AH/JL: update layout, css tweaks
- awaiting Mozilla response for their text