diff options
71 files changed, 1391 insertions, 717 deletions
diff --git a/client/applet.js b/client/applet.js index 21e1e4fa..db95168a 100644 --- a/client/applet.js +++ b/client/applet.js @@ -4,11 +4,12 @@ import { Container as FaceSearchContainer } from './faceSearch' import { Container as FaceAnalysisContainer } from './faceAnalysis' import { Container as NameSearchContainer } from './nameSearch' import { Container as DatasetListContainer } from './datasetList' +import { CitationsTable, FileTable } from './table' import { CountriesByYear, PieCharts } from './chart' export default class Applet extends Component { render() { - // console.log(this.props) + // console.log(this.props.payload.cmd) switch (this.props.payload.cmd) { case 'face_analysis': return <FaceAnalysisContainer {...this.props} /> @@ -22,6 +23,10 @@ export default class Applet extends Component { return <CountriesByYear {...this.props} /> case 'piechart': return <PieCharts {...this.props} /> + case 'citations': + return <CitationsTable {...this.props} /> + case 'load_file': + return <FileTable {...this.props} /> default: return <pre style={{ color: '#0f0' }}>{'Megapixels'}</pre> } diff --git a/client/chart/constants.js b/client/chart/constants.js index 70375ba3..b916cbd2 100644 --- a/client/chart/constants.js +++ b/client/chart/constants.js @@ -59,6 +59,6 @@ export const institutionOrder = { export const institutionLabels = { 'edu': 'Academic', 'company': 'Commercial', - 'gov': 'Government / Military', - 'mil': 'Government / Military', + 'gov': 'Military / Government', + 'mil': 'Military / Government', }
\ No newline at end of file diff --git a/client/chart/countriesByYear.chart.js b/client/chart/countriesByYear.chart.js index 4257748c..2284f774 100644 --- a/client/chart/countriesByYear.chart.js +++ b/client/chart/countriesByYear.chart.js @@ -158,6 +158,7 @@ class CountriesByYearChart extends Component { } }} /> + <div className='caption'>{paper.name}{' dataset citations by country per year'}</div> </div> ) } diff --git a/client/chart/pie.charts.js b/client/chart/pie.charts.js index 6e579537..84e85c3a 100644 --- a/client/chart/pie.charts.js +++ b/client/chart/pie.charts.js @@ -17,6 +17,7 @@ class PieCharts extends Component { render() { const { payload } = this.props const { paper, citations } = payload.data + console.log(this.props) if (!citations.length) return null const countries = {} @@ -83,9 +84,10 @@ class PieCharts extends Component { } }} size={{ - height: 336, + height: countryRows.length < 4 ? 316 : 336, }} /> + <span className='chartCaption'>{paper.name}{' dataset citations by country'}</span> </div> <div> <C3Chart @@ -105,6 +107,7 @@ class PieCharts extends Component { height: 316, }} /> + <span className='chartCaption'>{paper.name}{' dataset citations by organization type'}</span> </div> </div> ) diff --git a/client/index.js b/client/index.js index 5c8bc880..668aebfb 100644 --- a/client/index.js +++ b/client/index.js @@ -6,7 +6,6 @@ import { Provider } from 'react-redux' import { toArray } from './util' import Applet from './applet' import { store } from './store' -import appendTable from './tables' import appendMap from './map' function appendReactApplet(el, payload) { @@ -33,7 +32,8 @@ function appendApplets(applets) { case 'citations': case 'load_file': el.parentNode.classList.add('wide') - appendTable(el, payload) + appendReactApplet(el, payload) + el.classList.add('loaded') break case 'map': el.parentNode.classList.add('wide') @@ -87,9 +87,9 @@ function runApplets() { if (dataset === 'index.html') { dataset = path.pop() } - console.log('dataset from path:', dataset) + // console.log('dataset from path:', dataset) } else { - console.log('not on a dataset page') + // console.log('not on a dataset page') return [el, payload] } } diff --git a/client/map/index.js b/client/map/index.js index b35ffddb..475ba3c6 100644 --- a/client/map/index.js +++ b/client/map/index.js @@ -37,25 +37,31 @@ const redDot = L.icon({ popupAnchor: [0, -5] // point from which the popup should open relative to the iconAnchor }) -function addMarker(map, latlng, title, addresses, year, pdf) { +function addMarker(map, latlng, citations) { 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>") - } + let message = citations.map(citation => { + const { title, addresses, year, pdf, doi } = citation + let rec = [ + "<b>", title, "</b>", + ] + if (pdf && pdf.length) { + rec.unshift("<a href='" + pdf[0] + "' target='_blank'>") + rec.push("</a>") + } + else if (doi && doi.length) { + rec.unshift("<a href='" + doi[0] + "' target='_blank'>") + rec.push("</a>") + } + if (year) { + rec.push(" (" + year + ")") + } + const addressString = addresses.map(addr => addr.name).join('<br/>') + rec.push("<br>") + rec.push(addressString) + return rec.join("") + }) - const addressString = addresses.map(addr => addr.name).join('<br/>') - message = message.concat([ - "<br>", - addressString, - ]) - if (year) { - message.push(" (" + year + ")") - } - marker.bindPopup(message.join('')) + marker.bindPopup(message.join('<br><br>')) return marker } @@ -73,7 +79,7 @@ function addArc(map, src, dest, arcStyle) { export default function append(el, payload) { const { data } = payload if (!data) return - let { paper, addresses, citations } = data + let { paper, citations } = data let source = [0, 0] let map = L.map(el).setView([25, 0], 2) @@ -87,30 +93,51 @@ export default function append(el, payload) { accessToken: 'pk.eyJ1IjoiZmFuc2FsY3kiLCJhIjoiY2pvN3I1czJwMHF5NDNrbWRoMWpteHlrdCJ9.kMpM5syQUhVjKkn1iVx9fg' }).addTo(map) - if (addresses && addresses.length) { - source = [address[0].lat, address[0].lng].map(n => (parseFloat(n) || 0)) + if (paper.addresses && paper.addresses.length) { + source = [paper.addresses[0].lat, paper.addresses[0].lng].map(n => (parseFloat(n) || 0)) } else { console.error("No address found for root paper") // console.log(data) } // group papers by address + let citationsByAddress = {} citations.forEach(citation => { - console.log(citation) if (!citation.addresses) { - console.log(citation) + // console.log(citation) return } - const citationAddress = citation.addresses[0] + // console.log(citation) + citation.addresses.forEach(address => { + if (!(address.name in citationsByAddress)) { + citationsByAddress[address.name] = { address, citations: []} + } + citationsByAddress[address.name].citations.push(citation) + }) + }) + + Object.keys(citationsByAddress).map(name => { + const { citations: citationList, address: citationAddress } = citationsByAddress[name] + // console.log(name, citationsByAddress[name]) + // console.log(citation) 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, citation.addresses, citation.year, citation.pdf) - addArc(map, source, latlng, arcStyles[citationAddress.type]) + addMarker(map, latlng, citationList) + const style = { ...arcStyles[citationAddress.type] } + let weight = Math.min(citationList.length, 5) + let opacity = 0.5 + Math.min(citationList.length / 5, 0.5) + if (citationAddress.type !== 'edu') { + weight += 1 + opacity = 1 + } + style.weight = String(weight) + style.opacity = opacity + addArc(map, source, latlng, style) }) - console.log(paper) + // console.log(paper) - const rootMarker = addMarker(map, source, paper.title, addresses, paper.year) + const rootMarker = addMarker(map, source, [paper]) rootMarker.openPopup() // a transparent div to cover the map, so normal scroll events will not be eaten by leaflet diff --git a/client/table/citations.table.js b/client/table/citations.table.js new file mode 100644 index 00000000..f65998aa --- /dev/null +++ b/client/table/citations.table.js @@ -0,0 +1,63 @@ +import React, { Component } from 'react' +import { bindActionCreators } from 'redux' +import { connect } from 'react-redux' +import { ReactTabulator } from 'react-tabulator' +import { Loader } from '../common' +import { toArray, toTuples } from '../util' + +export const citationsColumns = [ + { title: 'Title', field: 'title', sorter: 'string' }, + { title: 'Institution', field: 'institution', sorter: 'string' }, + { title: 'Country', field: 'country', sorter: 'string', width: 140 }, + { title: 'Year', field: 'year', sorter: 'number', width: 70 }, + { title: 'PDF', field: 'pdf_text', formatter: 'link', + formatterParams: { target: "_blank", urlField: 'pdf_link', }, + sorter: 'string', width: 100 }, +] + +class CitationsTable extends Component { + render() { + const { payload } = this.props + const { paper, citations } = payload.data + + if (!citations.length) return <Loader /> + + const formattedCitations = citations.map(citation => { + const pdf_link = (citation.pdf && citation.pdf.length) + ? citation.pdf[0] + : (citation.doi && citation.doi.length) + ? citation.doi[0] + : 'https://www.semanticscholar.org/paper/' + citation.id + let pdf_text + const pdf_partz = pdf_link.split('/')[2].split('.') + if (pdf_partz.length > 2 && pdf_partz[pdf_partz.length - 2].length == 2) { + pdf_text = pdf_partz.slice(-3).join('.') + } else { + pdf_text = pdf_partz.slice(-2).join('.') + } + return { + title: citation.title, + institution: citation.addresses[0].name, + country: citation.addresses[0].country, + year: citation.year, + pdf_link, pdf_text, + } + }) + + // console.log(formattedCitations) + + return ( + <ReactTabulator + columns={citationsColumns} + data={formattedCitations} + options={{ + height: 311, + layout: 'fitColumns', + placeholder: 'No Data Set', + }} + /> + ) + } +} + +export default CitationsTable diff --git a/client/table/file.table.js b/client/table/file.table.js new file mode 100644 index 00000000..92f5cf72 --- /dev/null +++ b/client/table/file.table.js @@ -0,0 +1,60 @@ +import React, { Component } from 'react' +import { bindActionCreators } from 'redux' +import { connect } from 'react-redux' +import { toArray, toTuples } from '../util' + +import { Loader } from '../common' + +import csv from 'parse-csv' + +class FileTable extends Component { + state = { + data: [] + } + + componentDidMount() { + console.log(payload.url) + fetch(payload.url, { mode: 'cors' }) + .then(r => r.text()) + .then(text => { + try { + const data = csv.toJSON(text, { headers: { included: true } }) + this.setState({ data }) + } catch (e) { + console.error("error making json:", payload.url) + console.error(e) + } + }) + } + + getColumns(payload) { + let { cmd, url, fields } = payload + return ((fields && fields.length) ? fields[0] : '').split(', ').map(field => { + switch (field) { + default: + return { title: field, field: field.toLowerCase(), sorter: 'string' } + } + }) + } + + render() { + const { payload } = this.props + const { paper, citations } = payload.data + const columns = getColumns(payload) + if (!this.state.data.length) { + return <Loader /> + } + return ( + <ReactTabulator + columns={citationsColumns} + data={this.state.data} + options={{ + height: 311, + layout: 'fitColumns', + placeholder: 'No Data Set', + }} + /> + ) + } +} +export default FileTable diff --git a/client/table/index.js b/client/table/index.js new file mode 100644 index 00000000..c741f33e --- /dev/null +++ b/client/table/index.js @@ -0,0 +1,11 @@ +import 'react-tabulator/lib/styles.css' +import 'react-tabulator/lib/css/tabulator_midnight.css' +import './tabulator.css' + +import CitationsTable from './citations.table' +import FileTable from './file.table' + +export { + CitationsTable, + FileTable, +}
\ No newline at end of file diff --git a/client/table/tabulator.css b/client/table/tabulator.css new file mode 100644 index 00000000..24005368 --- /dev/null +++ b/client/table/tabulator.css @@ -0,0 +1,26 @@ +.tabulator { + border-left: 1px solid #333; + border-bottom: 1px solid #333; +} +.tabulator-row.tabulator-row-odd { + background-color: #222; +} +.tabulator-row.tabulator-row-even { + background-color: #333; +} +.desktop .tabulator-row.tabulator-selectable:hover { + background-color: #555; +} +.tabulator-row .tabulator-cell { + border-right: 1px solid #444; + padding: 8px; +} +.tabulator .tabulator-header { + border-bottom: 0; +} +.tabulator .tabulator-header .tabulator-col { + border-right: 1px solid #444; +} +.tabulator .tabulator-tableHolder .tabulator-table { + background-color: #333; +}
\ No newline at end of file diff --git a/client/tables.js b/client/tables.js deleted file mode 100644 index 3b53b5db..00000000 --- a/client/tables.js +++ /dev/null @@ -1,96 +0,0 @@ -import Tabulator from 'tabulator-tables' -import csv from 'parse-csv' - -const datasetColumns = [ - { title: 'Title', field: 'title', sorter: 'string' }, - { title: 'Images', field: 'images', sorter: 'number' }, - { title: 'People', field: 'people', sorter: 'number' }, - { title: 'Year', field: 'year', sorter: 'number' }, - { title: 'Citations', field: 'citations', sorter: 'number' }, - { title: 'Influenced', field: 'influenced', sorter: 'number' }, - // { title: 'Origin', field: 'origin', sorter: 'string' }, -] -const citationsColumns = [ - { title: 'Title', field: 'title', sorter: 'string' }, - { title: 'Institution', field: 'institution', sorter: 'string' }, - { title: 'Country', field: 'country', sorter: 'string', width: 140 }, - { title: 'Year', field: 'year', sorter: 'number', width: 70 }, - { title: 'PDF', field: 'pdf', formatter: 'link', - formatterParams: { target: "_blank", urlField: 'pdf', }, - sorter: 'string', width: 100 }, -] - -function getColumns(payload) { - let { cmd, url, fields } = payload - if (cmd === 'citations') { - return citationsColumns - } - if (url && url.match('datasets.csv')) { - return datasetColumns - } - return ((fields && fields.length) ? fields[0] : '').split(', ').map(field => { - switch (field) { - default: - return { title: field, field: field.toLowerCase(), sorter: 'string' } - } - }) -} - -function getCitations(dataset) { - // console.log(dataset.citations) - // console.log(dataset.citations.map(d => [d.pdf, d.doi])) - return dataset.citations.map(citation => ({ - 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] - : (citation.doi && citation.doi.length) - ? citation.doi[0] - : "", - })) -} - -export default function append(el, payload) { - const columns = getColumns(payload) - // console.log(columns) - const table = new Tabulator(el, { - height: '311px', - layout: 'fitColumns', - placeholder: 'No Data Set', - columns, - }) - // let path = payload.opt - // console.log(path, columns) - - if (payload.cmd === 'citations') { - let { data } = payload - if (!data) return null - const citations = getCitations(data) - // console.log(citations) - table.setData(citations) - el.classList.add('loaded') - } else { - fetch(payload.url, { mode: 'cors' }) - .then(r => r.text()) - .then(text => { - try { - // console.log(text) - const data = csv.toJSON(text, { headers: { included: true } }) - // console.log(data) - table.setData(data) - el.classList.add('loaded') - } catch (e) { - - console.error("error making json:", payload.url) - console.error(e) - // console.log(text) - } - }) - } - - // if (fields && fields.length > 1 && fields[1].indexOf('filter')) { - // const filter = fields[1].split(' ') - // } -} diff --git a/megapixels/app/site/builder.py b/megapixels/app/site/builder.py index 603d4788..55a85b0f 100644 --- a/megapixels/app/site/builder.py +++ b/megapixels/app/site/builder.py @@ -57,7 +57,7 @@ def build_page(fn, research_posts, datasets): s3.sync_directory(dirname, s3_dir, metadata) content = parser.parse_markdown(metadata, sections, s3_path, skip_h1=skip_h1) - + html = template.render( metadata=metadata, content=content, diff --git a/megapixels/app/site/loader.py b/megapixels/app/site/loader.py index a544333b..779f68ba 100644 --- a/megapixels/app/site/loader.py +++ b/megapixels/app/site/loader.py @@ -85,6 +85,8 @@ def parse_metadata(fn, sections): metadata['meta'] = load_json(dataset_path) if not metadata['meta']: print("Bad metadata? {}".format(dataset_path)) + elif 'datasets' in fn: + print("/!\\ {} does not exist!".format(dataset_path)) if 'meta' not in metadata or not metadata['meta']: # dude metadata['meta'] = {} diff --git a/megapixels/app/site/parser.py b/megapixels/app/site/parser.py index 00470e4b..06c45f41 100644 --- a/megapixels/app/site/parser.py +++ b/megapixels/app/site/parser.py @@ -27,6 +27,7 @@ def parse_markdown(metadata, sections, s3_path, skip_h1=False): current_group = [] footnotes = [] in_stats = False + in_columns = False in_footnotes = False ignoring = False @@ -50,6 +51,7 @@ def parse_markdown(metadata, sections, s3_path, skip_h1=False): footnotes.append(section) elif ignoring: continue + elif '### statistics' in section.lower() or '### sidebar' in section.lower(): if len(current_group): groups.append(format_section(current_group, s3_path)) @@ -64,6 +66,26 @@ def parse_markdown(metadata, sections, s3_path, skip_h1=False): if 'end sidebar' not in section.lower(): current_group.append(section) in_stats = False + + elif '=== columns' in section.lower(): + if len(current_group): + groups.append(format_section(current_group, s3_path)) + current_group = [] + in_columns = True + column_partz = section.split(' ') + if len(column_partz) == 3: + column_count = column_partz[2] + else: + column_count = "N" + groups.append("<section><div class='columns columns-{}'>".format(column_count)) + elif in_columns is True and '===' in section: + groups.append(format_section(current_group, s3_path, type='column', tag='div')) + current_group = [] + if 'end columns' in section: + groups.append("</div></section>") + in_columns = False + current_group = [] + elif section.strip().startswith('{% include'): groups.append(format_section(current_group, s3_path)) current_group = [] diff --git a/package-lock.json b/package-lock.json index 6d36e3ff..4e9d6fac 100644 --- a/package-lock.json +++ b/package-lock.json @@ -216,6 +216,28 @@ "resolved": "https://registry.npmjs.org/@types/node/-/node-8.10.38.tgz", "integrity": "sha512-EibsnbJerd0hBFaDjJStFrVbVBAtOy4dgL8zZFw0uOvPqzBAX59Ci8cgjg3+RgJIWhsB5A4c+pi+D4P9tQQh/A==" }, + "@types/prop-types": { + "version": "15.7.0", + "resolved": "https://registry.npmjs.org/@types/prop-types/-/prop-types-15.7.0.tgz", + "integrity": "sha512-eItQyV43bj4rR3JPV0Skpl1SncRCdziTEK9/v8VwXmV6d/qOUO8/EuWeHBbCZcsfSHfzI5UyMJLCSXtxxznyZg==" + }, + "@types/react": { + "version": "16.8.10", + "resolved": "https://registry.npmjs.org/@types/react/-/react-16.8.10.tgz", + "integrity": "sha512-7bUQeZKP4XZH/aB4i7k1i5yuwymDu/hnLMhD9NjVZvQQH7ZUgRN3d6iu8YXzx4sN/tNr0bj8jgguk8hhObzGvA==", + "requires": { + "@types/prop-types": "*", + "csstype": "^2.2.0" + } + }, + "@types/react-tag-autocomplete": { + "version": "5.6.0", + "resolved": "https://registry.npmjs.org/@types/react-tag-autocomplete/-/react-tag-autocomplete-5.6.0.tgz", + "integrity": "sha512-EsUrbpKW5agXs/NbMUQRgwtZInQbUIIPBXiUz+XcJeUP7U6BRCWjw96sQmsEPRUwO0CdPfQEd82zwpCIGEr4Ew==", + "requires": { + "@types/react": "*" + } + }, "accepts": { "version": "1.3.5", "resolved": "https://registry.npmjs.org/accepts/-/accepts-1.3.5.tgz", @@ -2249,6 +2271,11 @@ "integrity": "sha1-yBSQPkViM3GgR3tAEJqq++6t27Q=", "dev": true }, + "csstype": { + "version": "2.6.3", + "resolved": "https://registry.npmjs.org/csstype/-/csstype-2.6.3.tgz", + "integrity": "sha512-rINUZXOkcBmoHWEyu7JdHu5JMzkGRoMX4ov9830WNgxf5UYxcBUO0QTKAqeJ5EZfSdlrcJYkC8WwfVW7JYi4yg==" + }, "csv-parse": { "version": "4.2.0", "resolved": "https://registry.npmjs.org/csv-parse/-/csv-parse-4.2.0.tgz", @@ -4647,6 +4674,11 @@ "wbuf": "^1.1.0" } }, + "html-attributes": { + "version": "1.1.0", + "resolved": "https://registry.npmjs.org/html-attributes/-/html-attributes-1.1.0.tgz", + "integrity": "sha1-ggJ6T6x6YHDqbBjMOIauoY1t6gk=" + }, "html-entities": { "version": "1.2.1", "resolved": "https://registry.npmjs.org/html-entities/-/html-entities-1.2.1.tgz", @@ -5594,9 +5626,9 @@ "integrity": "sha512-RdJUflcE3cUzKiMqQgsCu06FPu9UdIJO0beYbPhHN4k6apgJtifcoCtT9bcxOpYBtpD2kCM6Sbzg4CausW/PKQ==" }, "js-yaml": { - "version": "3.12.0", - "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-3.12.0.tgz", - "integrity": "sha512-PIt2cnwmPfL4hKNwqeiuz4bKfnzHTBv6HyVgjahA6mPLwPDzjDWrplJBMjHUFxku/N3FlmrbyPclad+I+4mJ3A==", + "version": "3.13.0", + "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-3.13.0.tgz", + "integrity": "sha512-pZZoSxcCYco+DIKBTimr67J6Hy+EYGZDY/HCWC+iAEA9h1ByhMXAIVUXMcMFpOCxQ/xjXmPI2MkDL5HRm5eFrQ==", "dev": true, "requires": { "argparse": "^1.0.7", @@ -5781,6 +5813,11 @@ "resolved": "https://registry.npmjs.org/lodash.get/-/lodash.get-4.4.2.tgz", "integrity": "sha1-LRd/ZS+jHpObRDjVNBSZ36OCXpk=" }, + "lodash.isplainobject": { + "version": "4.0.6", + "resolved": "https://registry.npmjs.org/lodash.isplainobject/-/lodash.isplainobject-4.0.6.tgz", + "integrity": "sha1-fFJqUtibRcRcxpC4gWO+BJf1UMs=" + }, "lodash.merge": { "version": "4.6.1", "resolved": "https://registry.npmjs.org/lodash.merge/-/lodash.merge-4.6.1.tgz", @@ -6710,6 +6747,16 @@ "sha.js": "^2.4.8" } }, + "pick-react-known-prop": { + "version": "0.1.5", + "resolved": "https://registry.npmjs.org/pick-react-known-prop/-/pick-react-known-prop-0.1.5.tgz", + "integrity": "sha512-SnDf64AVdvqoAFpHeZUKT9kdn40Ellj84CPALRxYWqNJ6r6f44eAAT+Jtkb0Suhiw7yg5BdOFAQ25OJnjG+afw==", + "requires": { + "html-attributes": "^1.1.0", + "lodash.isplainobject": "^4.0.6", + "svg-attributes": "^1.0.0" + } + }, "pify": { "version": "3.0.0", "resolved": "https://registry.npmjs.org/pify/-/pify-3.0.0.tgz", @@ -7274,6 +7321,36 @@ "spin.js": "^2.0.1" } }, + "react-tabulator": { + "version": "0.9.1", + "resolved": "https://registry.npmjs.org/react-tabulator/-/react-tabulator-0.9.1.tgz", + "integrity": "sha512-KLkO17TZbGKzwaCPD8c84cG94OkSpU0zyvlhOleKJELQWcHEL99+63DEamEaXOsguDfxM474lxu3K+jqG2bW/Q==", + "requires": { + "@types/react-tag-autocomplete": "^5.6.0", + "date-fns": "v2.0.0-alpha.25", + "dotenv": "^6.1.0", + "pick-react-known-prop": "^0.1.5", + "react-tag-autocomplete": "^5.7.1", + "tabulator-tables": "^4.2.3" + }, + "dependencies": { + "date-fns": { + "version": "2.0.0-alpha.25", + "resolved": "https://registry.npmjs.org/date-fns/-/date-fns-2.0.0-alpha.25.tgz", + "integrity": "sha512-iQzJkHF0L4wah9Ae9PkvwemwFz6qmRLuNZcghmvf2t+ptLs1qXzONLiGtjmPQzL6+JpC01JjlTopY2AEy4NFAg==" + }, + "tabulator-tables": { + "version": "4.2.3", + "resolved": "https://registry.npmjs.org/tabulator-tables/-/tabulator-tables-4.2.3.tgz", + "integrity": "sha512-vMQ/8/HSKzOdn1zd9uv7EmnBnMTlX8JMhfxAxEUkM12qYiqhapWp/iN2ErtDX2cVi+4CUaEn61qydSFJyKjdYA==" + } + } + }, + "react-tag-autocomplete": { + "version": "5.8.2", + "resolved": "https://registry.npmjs.org/react-tag-autocomplete/-/react-tag-autocomplete-5.8.2.tgz", + "integrity": "sha512-GkOQrSLjvWo98IeqRuGgc77zaxSMyMjy+b2Rc+m9jMKTWopF9h5Lf2F/X1oK9hcnUCeUmJ5QVpc/dx9MgOA2Iw==" + }, "read-pkg": { "version": "2.0.0", "resolved": "https://registry.npmjs.org/read-pkg/-/read-pkg-2.0.0.tgz", @@ -8546,7 +8623,7 @@ }, "sprintf-js": { "version": "1.0.3", - "resolved": "http://registry.npmjs.org/sprintf-js/-/sprintf-js-1.0.3.tgz", + "resolved": "https://registry.npmjs.org/sprintf-js/-/sprintf-js-1.0.3.tgz", "integrity": "sha1-BOaSb2YolTVPPdAVIDYzuFcpfiw=", "dev": true }, @@ -8722,6 +8799,11 @@ "integrity": "sha1-U10EXOa2Nj+kARcIRimZXp3zJMc=", "dev": true }, + "svg-attributes": { + "version": "1.0.0", + "resolved": "https://registry.npmjs.org/svg-attributes/-/svg-attributes-1.0.0.tgz", + "integrity": "sha1-tcWWjzYke32+OFMgfyqcaK2Aa/w=" + }, "svgtodatauri": { "version": "0.0.0", "resolved": "https://registry.npmjs.org/svgtodatauri/-/svgtodatauri-0.0.0.tgz", diff --git a/package.json b/package.json index 4cd2f10d..6238e7e3 100644 --- a/package.json +++ b/package.json @@ -55,6 +55,7 @@ "react-router": "^4.3.1", "react-router-dom": "^4.3.1", "react-spin": "^0.6.2", + "react-tabulator": "^0.9.1", "redux": "^4.0.0", "redux-thunk": "^2.3.0", "snapsvg": "^0.5.1", diff --git a/scraper/client/paper/paper.verify.js b/scraper/client/paper/paper.verify.js index 83eb5b44..25117ff1 100644 --- a/scraper/client/paper/paper.verify.js +++ b/scraper/client/paper/paper.verify.js @@ -52,7 +52,7 @@ class PaperVerify extends Component { let newState = {} if (oldSha256 && sha256 !== oldSha256) { - console.log('update verification') + // console.log('update verification') this.props.actions.getAddress(sha256) this.props.actions.getVerification(sha256) const citationState = this.getCitationState(sha256) @@ -60,6 +60,7 @@ class PaperVerify extends Component { ...initialState, ...citationState, ...address.paper, + pdfIndex: citationState.citation.pdf.findIndex(el => el.match(/^https:/)), } this.setState(newState) } else if (verify && !verify.loading && verify.paper && (!oldPaper || oldPaper !== verify.paper)) { @@ -70,6 +71,7 @@ class PaperVerify extends Component { ...initialState, ...citationState, ...address.paper, + pdfIndex: citationState.citation.pdf.findIndex(el => el.match(/^https:/)), } this.setState(newState) } else { @@ -79,6 +81,7 @@ class PaperVerify extends Component { newState = { ...citationState, ...address.paper, + pdfIndex: citationState.citation.pdf.findIndex(el => el.match(/^https:/)), uses_dataset: paper.uses_dataset, images_in_paper: paper.images_in_paper, verified_by: paper.verified_by, @@ -156,7 +159,7 @@ class PaperVerify extends Component { if (citationIndex < 0) { history.push('/paper/' + key + '/info/') } else { - let nextId = citations[citationIndex].id + let nextId = sortedCitations[citationIndex].id history.push('/paper/' + key + '/verify/' + nextId) } } @@ -167,15 +170,16 @@ class PaperVerify extends Component { const { paperInfo, sortedCitations } = this.props.api const citations = sortedCitations || paperInfo.citations || [] let citationIndex = citations.findIndex(f => f.id === this.state.citation.id) - + console.log(sortedCitations) + console.log('going to next', key, citationIndex) if (citationIndex === -1) { history.push('/paper/' + key + '/info/') } else { citationIndex += 1 - if (citationIndex >= citations.length) { + if (citationIndex >= sortedCitations.length) { history.push('/paper/' + key + '/info/') } else { - let nextId = citations[citationIndex].id + let nextId = sortedCitations[citationIndex].id history.push('/paper/' + key + '/verify/' + nextId) } } @@ -414,7 +418,10 @@ class PaperVerify extends Component { >{'Next >'}</button> </div> - <iframe className='pdfViewer' referrerPolicy='no-referrer' src={citation.pdf[this.state.pdf_index]} /> + {citation.pdf.length + ? <iframe className='pdfViewer' referrerPolicy='no-referrer' src={citation.pdf[this.state.pdf_index] || "about:blank"} /> + : '' + } </div> ) } diff --git a/site/assets/css/applets.css b/site/assets/css/applets.css index e5c427b2..7fac3e27 100644 --- a/site/assets/css/applets.css +++ b/site/assets/css/applets.css @@ -3,6 +3,7 @@ .applet_container { min-height: 340px; clear: left; + margin: 20px auto 40px auto; } .applet_container.autosize { min-height: 0; @@ -168,6 +169,10 @@ .desktop .map_cover:hover { opacity: 1; } +.leaflet-popup-content-wrapper { + max-height: 230px; + overflow-y: auto; +} .leaflet-popup-content a { color: #0078A8; border-bottom: 1px solid rgba(0, 128, 160, 0.4); @@ -218,6 +223,10 @@ } .piechart .chart > div { width: 50%; + display: flex; + flex-direction: column; + justify-content: space-between; + align-items: center; } .piechart .chart .c3-chart-arc text { fill: #fff; @@ -227,4 +236,10 @@ } .piechart .c3 path, .piechart .c3 line { stroke: rgba(64,64,64,0.3); -}
\ No newline at end of file +} +.piechart .chartCaption { + color: #888; + font-size: 12px; + font-family: 'Roboto', sans-serif; + font-weight: 400; +} diff --git a/site/assets/css/css.css b/site/assets/css/css.css index 47fc0652..0ee8a4f3 100644 --- a/site/assets/css/css.css +++ b/site/assets/css/css.css @@ -4,7 +4,8 @@ html, body { padding: 0; width: 100%; min-height: 100%; - font-family: 'Roboto Mono', sans-serif; + /*font-family: 'Roboto Mono', sans-serif;*/ + font-family: 'Roboto', sans-serif; color: #eee; overflow-x: hidden; } @@ -163,33 +164,33 @@ h1 { margin: 75px 0 10px; padding: 0; transition: color 0.1s cubic-bezier(0,0,1,1); - font-family: 'Roboto'; + font-family: 'Roboto Mono', monospace; } h2 { color: #eee; font-weight: 400; - font-size: 32pt; - line-height: 43pt; - margin: 20px 0 10px; + font-size: 32px; + line-height: 43px; + margin: 20px 0 20px; padding: 0; transition: color 0.1s cubic-bezier(0,0,1,1); - font-family: 'Roboto'; + font-family: 'Roboto Mono', monospace; } h3 { margin: 0 0 20px 0; padding: 20px 0 0 0; font-size: 22pt; - font-weight: 500; + font-weight: 400; transition: color 0.1s cubic-bezier(0,0,1,1); - font-family: 'Roboto'; + font-family: 'Roboto Mono', monospace; } h4 { margin: 0 0 10px 0; padding: 0; font-size: 11pt; - font-weight: 500; + font-weight: 400; transition: color 0.1s cubic-bezier(0,0,1,1); - font-family: 'Roboto'; + font-family: 'Roboto Mono', monospace; } .content h3 a { color: #888; @@ -212,11 +213,11 @@ h4 { border-bottom: 0; } th, .gray { - font-family: 'Roboto Mono', monospace; + font-family: 'Roboto', monospace; font-weight: 500; text-transform: uppercase; letter-spacing: .15rem; - color: #999; + color: #777; } th, .gray { font-size: 9pt; @@ -248,8 +249,9 @@ section { p { margin: 0 10px 20px 0; line-height: 2; - font-size: 16px; + font-size: 18px; font-weight: 300; + color: #dedede; } p.subp{ font-size: 14px; @@ -272,18 +274,19 @@ p.subp{ flex-direction: row; justify-content: flex-start; align-items: flex-start; - font-size: 14px; + font-size: 12px; + color: #ccc; margin-bottom: 20px; font-family: 'Roboto', sans-serif; } .meta > div { margin-right: 20px; - line-height: 19px + line-height: 17px /*font-size:11px;*/ } .meta .gray { font-size: 9pt; - padding-bottom: 4px; + padding-bottom: 5px; line-height: 14px } .right-sidebar { @@ -303,7 +306,7 @@ p.subp{ padding-top: 10px; padding-right: 20px; /*margin-right: 20px;*/ - margin-bottom: 30px; + margin-bottom: 10px; /*border-right: 1px solid #444;*/ font-family: 'Roboto'; font-size: 14px; @@ -464,10 +467,10 @@ section.fullwidth .image { text-align: center; } .image .caption.intro-caption{ - text-align: left; + text-align: center; } .caption { - text-align: left; + text-align: center; font-size: 10pt; color: #999; max-width: 960px; @@ -484,50 +487,6 @@ section.fullwidth .image { } -/* about page */ - - -.flex-container { - padding: 0; - margin: 0; - list-style: none; - - display: -webkit-box; - display: -moz-box; - display: -ms-flexbox; - display: -webkit-flex; - display: flex; - - -webkit-flex-flow: row wrap; - justify-content: space-around; -} - -.team-photos-container{ - margin-top:40px; -} -.team-member { - height: auto; - margin-top: 10px; - color: white; - width: 400px; - font-weight: bold; - flex-grow: 1; - margin:0 40px 0 0; - padding:20px; - border-radius:6px; - background: #202020; -} -.team-member&:last-child{ - margin:0 0 0 40px; -} -.team-member p{ - font-size:14px; -} -.team-member img{ - margin:0; - display: block; -} - .sideimage { margin: 0px 0 40px 0; @@ -771,7 +730,7 @@ section.intro_section { background-size: cover; background-position: center left; padding: 50px 0; - /*min-height: 40vh;*/ + min-height: 40vh; display: flex; justify-content: center; align-items: center; @@ -829,7 +788,7 @@ page-specific formatting position: relative; width: 100%; height: 50px; - margin-top:100px; + margin-top:50px; } .hr-wave-line1 { @@ -848,39 +807,58 @@ page-specific formatting /* map */ -.map-legend-item{ +ul.map-legend{ display: inline-block; + margin:0; +} +ul.map-legend li{ margin-right: 10px; padding-top:4px; + display: inline-block; } -.map-legend-item:before { +ul.map-legend li:before { content: ''; display: inline-block; width: 10px; height: 10px; - /*margin-bottom: 2px;*/ margin-right: 6px; } -.map-legend-item.edu:before { +ul.map-legend li.edu:before { background-color: #f2f293; } -.map-legend-item.com:before { +ul.map-legend li.com:before { background-color: #3264f6; } -.map-legend-item.gov:before { +ul.map-legend li.gov:before { background-color: #f30000; } +ul.map-legend li.source:before { + content: none; + display: inline-block; + width: 0px; + margin-right: 10px; +} /* about */ .content-about { color: #fff; } +.content-about p { + font-size: 16px; +} +.content-about ul{ + font-size: 14px; + font-weight: 300; +} +.content-about section:first-of-type > p:first-of-type { + font-size: 23px; + line-height: 39px; +} .content-about .about-menu ul li { display: inline-block; font-size: 14px; font-weight: 400; - margin-right: 8px; text-transform: uppercase; margin-right: 15px; font-family: 'Roboto'; @@ -895,6 +873,81 @@ page-specific formatting color: #ddd; } +/* columns */ + +.columns { + display: flex; + flex-direction: row; + justify-content: flex-start; +} +.columns .column { + font-family: Roboto, sans-serif; + font-weight: 400; + background: #202020; + padding: 20px; + margin: 10px; +} +.columns .column:first-of-type { + margin-left: 0; +} +.columns-2 .column { + width: 50%; +} +.columns-3 .column { + width: 33%; +} +.columns-4 .column { + width: 25%; +} + +/* about page */ + + +.flex-container { + padding: 0; + margin: 0; + list-style: none; + + display: -webkit-box; + display: -moz-box; + display: -ms-flexbox; + display: -webkit-flex; + display: flex; + + -webkit-flex-flow: row wrap; + justify-content: space-around; +} + +.content-about .team-photos-container{ + margin:40px 0; +} +.content-about .team-member { + height: auto; + margin-top: 10px; + color: white; + width: 400px; + font-weight: bold; + flex-grow: 1; + margin:0 40px 0 0; + padding:20px; + border-radius:6px; + background: #202020; +} +.content-about .team-member&:last-child{ + margin:0 0 0 40px; +} +.content-about .team-member p{ + font-size:16px; +} +.content-about .team-member img{ + margin:0; + display: block; +} +.content-about .team-member h3{ + font-size:18px; +} + + /* footnotes */ diff --git a/site/assets/css/tabulator.css b/site/assets/css/tabulator.css index 41c7ffa4..d26b5cfc 100755 --- a/site/assets/css/tabulator.css +++ b/site/assets/css/tabulator.css @@ -1,7 +1,7 @@ /* Tabulator v4.1.3 (c) Oliver Folkerd */ .tabulator { position: relative; - font-size: 14px; + font-size: 13px; text-align: left; overflow: hidden; -ms-transform: translatez(0); @@ -23,7 +23,7 @@ position: relative; box-sizing: border-box; width: 100%; - border-bottom: 1px solid #999; + border-bottom: 1px solid #333; color: #ddd; white-space: nowrap; overflow: hidden; @@ -41,6 +41,7 @@ text-align: left; vertical-align: bottom; overflow: hidden; + padding: 5px 0; } .tabulator .tabulator-header .tabulator-col.tabulator-moving { @@ -63,6 +64,9 @@ overflow: hidden; text-overflow: ellipsis; vertical-align: bottom; + /* AH */ + font-weight: 500; + font-size:14px; } .tabulator .tabulator-header .tabulator-col .tabulator-col-content .tabulator-col-title .tabulator-title-editor { @@ -76,13 +80,13 @@ .tabulator .tabulator-header .tabulator-col .tabulator-col-content .tabulator-arrow { display: inline-block; position: absolute; - top: 9px; + top: 11px; right: 8px; width: 0; height: 0; border-left: 6px solid transparent; border-right: 6px solid transparent; - border-bottom: 6px solid #bbb; + border-bottom: 6px solid #666; } .tabulator .tabulator-header .tabulator-col.tabulator-col-group .tabulator-col-group-cols { @@ -129,6 +133,7 @@ .tabulator .tabulator-header .tabulator-col.tabulator-sortable .tabulator-col-title { padding-right: 25px; + padding-left: 6px; } .tabulator .tabulator-header .tabulator-col.tabulator-sortable:hover { @@ -137,7 +142,7 @@ .tabulator .tabulator-header .tabulator-col.tabulator-sortable[aria-sort="none"] .tabulator-col-content .tabulator-arrow { border-top: none; - border-bottom: 6px solid #bbb; + border-bottom: 6px solid #666; } .tabulator .tabulator-header .tabulator-col.tabulator-sortable[aria-sort="asc"] .tabulator-col-content .tabulator-arrow { @@ -723,7 +728,7 @@ max-height: 200px; background: #fff; border: 1px solid #333; - font-size: 14px; + font-size: 13px; overflow-y: auto; -webkit-overflow-scrolling: touch; z-index: 10000; diff --git a/site/content/pages/about/credits.md b/site/content/pages/about/credits.md deleted file mode 100644 index bc2283fd..00000000 --- a/site/content/pages/about/credits.md +++ /dev/null @@ -1,48 +0,0 @@ ------------- - -status: published -title: MegaPixels Press and News -desc: MegaPixels Press and News -slug: press -cssclass: about -published: 2018-12-04 -updated: 2018-12-04 -authors: Adam Harvey - ------------- - -# Credits - -<section class="about-menu"> -<ul> - <li><a href="/about/">About</a></li> - <li><a href="/about/press/">Press</a></li> - <li><a class="current" 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> -</section> - - -#### Team - -- Research and image analysis: Adam Harvey -- Development and visualizations: Jules LaPlace -- Produced in Partnership with Mozilla -- Contributing researchers: Berit Gilma, Mathana Stender - -#### Code - -<<<<<<< HEAD -- This site uses D3.js, C3.js, and ThreeJS for visualizations. -- Data aggregation uses Pandas and PDFMiner.Six. -======= -- This site uses D3 and C2 for visuzations -- Add more here ->>>>>>> 26646e6adf3833f6282e9515c14ad61e485440c0 - -#### Data - -- link to github -- how it was gathered
\ No newline at end of file diff --git a/site/content/pages/about/disclaimer.md b/site/content/pages/about/disclaimer.md deleted file mode 100644 index f82a09a0..00000000 --- a/site/content/pages/about/disclaimer.md +++ /dev/null @@ -1,41 +0,0 @@ ------------- - -status: published -title: Disclaimer -desc: MegaPixels Disclaimer -slug: disclaimer -cssclass: about -published: 2018-12-04 -updated: 2018-12-04 -authors: Adam Harvey - ------------- - -# Disclaimer - -<section class="about-menu"> -<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 class="current" 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> - -(TEMPORARY PAGE) - -Last updated: December 04, 2018 - -The information contained on MegaPixels.cc website (the "Service") is for academic and artistic purposes only. - -MegaPixels.cc assumes no responsibility for errors or omissions in the contents on the Service. - -In no event shall MegaPixels.cc be liable for any special, direct, indirect, consequential, or incidental damages or any damages whatsoever, whether in an action of contract, negligence or other tort, arising out of or in connection with the use of the Service or the contents of the Service. MegaPixels.cc reserves the right to make additions, deletions, or modification to the contents on the Service at any time without prior notice. - -## External links disclaimer - -MegaPixels.cc website may contain links to external websites that are not provided or maintained by or in any way affiliated with MegaPixels.cc - -Please note that the MegaPixels.cc does not guarantee the accuracy, relevance, timeliness, or completeness of any information on these external websites. diff --git a/site/content/pages/about/faq.md b/site/content/pages/about/faq.md new file mode 100644 index 00000000..8b780262 --- /dev/null +++ b/site/content/pages/about/faq.md @@ -0,0 +1,26 @@ +------------ + +status: published +title: MegaPixels Press and News +desc: MegaPixels Press and News +slug: faqs +cssclass: about +published: 2018-12-04 +updated: 2018-12-04 +authors: Adam Harvey + +------------ + +# FAQs + +<section class="about-menu"> +<ul> +<li><a href="/about/">About</a></li> +<li><a class="current" href="/about/faq/">FAQs</a></li> +<li><a href="/about/press/">Press</a></li> +<li><a href="/about/terms/">Terms</a></li> +<li><a href="/about/privacy/">Privacy</a></li> +</ul> +</section> + +[ page under development ] diff --git a/site/content/pages/about/index.md b/site/content/pages/about/index.md index 4fec0777..5fc147c9 100644 --- a/site/content/pages/about/index.md +++ b/site/content/pages/about/index.md @@ -16,41 +16,63 @@ authors: Adam Harvey <section class="about-menu"> <ul> <li><a class="current" href="/about/">About</a></li> +<li><a href="/about/faq/">FAQs</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> +<li><a href="/about/terms/">Terms</a></li> +<li><a href="/about/privacy/">Privacy</a></li> </ul> </section> -(PAGE UNDER DEVELOPMENT) +MegaPixels is an independent art and research project by Adam Harvey and Jules LaPlace investigating the ethics and individual privacy implications of publicly available face recognition datasets, and their role in industry and governmental expansion into biometric surveillance technologies. -<p><div style="font-size:20px;line-height:36px">Ever since government agencies began developing face recognition in the early 1960's, datasets of face images have always been central to technological advancements. Today, these datasets no longer originate in labs, but instead from family photo albums posted on photo sharing sites, surveillance cameras on college campuses, search engine queries for celebrities, cafe livestreams, and <a href="https://www.theverge.com/2017/8/22/16180080/transgender-youtubers-ai-facial-recognition-dataset">personal videos</a> posted on YouTube. </div></p> - -Collectively, facial recognition datasets are now gathered "in the wild". - -<p>MegaPixels is art and research by <a href="https://ahprojects.com">Adam Harvey</a> about facial recognition datasets that unravels their histories, futures, geographies, and meanings. Throughout 2019 this site this site will publish research reports, visualizations, raw data, and interactive tools to explore how publicly available facial recognition datasets contribute to a global supply chain of biometric data that powers the global facial recognition industry.</p> - -During the last year, hundreds of these facial analysis datasets created "in the wild" have been collected to understand how they contribute to a global supply chain of biometric data that is powering the global facial recognition industry. - -The MegaPixels website is produced in partnership with [Mozilla](https://mozilla.org). +The MegaPixels site is made possible with support from <a href="http://mozilla.org">Mozilla</a> <div class="flex-container team-photos-container"> <div class="team-member"> - <img src="https://nyc3.digitaloceanspaces.com/megapixels/v1/site/about/assets/adam-harvey-3d.jpg" /> <h3>Adam Harvey</h3> - <p>is Berlin-based American artist and researcher. 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 grants, and is a researcher in residence at Karlsruhe HfG. - <br> - <a href="https://ahprojects.com">ahprojects.com</a> + <p>is Berlin-based American artist and researcher. His previous projects (CV Dazzle, Stealth Wear, and SkyLift) explore the potential for counter-surveillance as artwork. He is the founder of VFRAME (visual forensics software for human rights groups) and is a currently researcher in residence at Karlsruhe HfG.</p> + <p><a href="https://ahprojects.com">ahprojects.com</a></p> </p> </div> <div class="team-member"> - <img src="https://nyc3.digitaloceanspaces.com/megapixels/v1/site/about/assets/jules-laplace-3d.jpg" /> <h3>Jules LaPlace</h3> - <p>is an American creative technologist also based in Berlin. He was previously the CTO of a digital agency in NYC and now also works at VFRAME, developing computer vision for human rights groups. Jules also builds creative software for artists and musicians. - <br> - <a href="https://asdf.us/">asdf.us</a> + <p>is an American technologist and artist also based in Berlin. He was previously the CTO of a digital agency in NYC and now also works at VFRAME, developing computer vision and data analysis software for human rights groups. Jules also builds experimental software for artists and musicians. </p> + <p><a href="https://asdf.us/">asdf.us</a></p> </div> </div> + +MegaPixels.cc is an independent research project about publicly available face recognition datasets. This website is based, in part, on earlier installations and research projects about facial recognition datasets in 2016-2018, which focused particularly on the MegaFace dataset. Since then it has evolved into a large-scale survey of publicly-available face and person analysis datasets, covering their usage, geographies, and ethics. + +An academic report and presentation on the findings is forthcoming. This site is published to make the research more accessible to a wider audience and to include visualizations and interactive features not possible in PDF publications. Continued research on MegaPixels is supported by a 1 year Researcher-in-Residence grant from Karlsruhe HfG. + +When possible, and once thoroughly verified, data generated for MegaPixels will be made available for download on [github.com/adamhrv/megapixels](https://github.com/adamhrv/megapixels) + +=== columns 3 + +#### Team + +- Adam Harvey: Concept, research, design, computer vision +- Jules LaPlace: Information and systems architecture, data retrieval, web applications + +=========== + +#### Contributing Researchers + +- Berit Gilma: Dataset statistics and discovery +- Beth (aka Ms. Celeb): Dataset usage verification and research +- Mathana Stender: Commercial usage verification and research on LFW + +=========== + +#### Code and Libraries + +- [Semantic Scholar](https://semanticscholar.org) for citation aggregation +- Leaflet.js for maps +- C3.js for charts +- ThreeJS for 3D visualizations +- PDFMiner.Six and Pandas for research paper data analysis + +=== end columns + +Please direct questions, comments, or feedback to [mastodon.social/@adamhrv](https://mastodon.social/@adamhrv)
\ No newline at end of file diff --git a/site/content/pages/about/press.md b/site/content/pages/about/press.md index 47e1af52..a0780d64 100644 --- a/site/content/pages/about/press.md +++ b/site/content/pages/about/press.md @@ -16,11 +16,10 @@ authors: Adam Harvey <section class="about-menu"> <ul> <li><a href="/about/">About</a></li> +<li><a href="/about/faq/">FAQs</a></li> <li><a class="current" 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> +<li><a href="/about/terms/">Terms</a></li> +<li><a href="/about/privacy/">Privacy</a></li> </ul> </section> diff --git a/site/content/pages/about/privacy.md b/site/content/pages/about/privacy.md index e36daf2a..48598623 100644 --- a/site/content/pages/about/privacy.md +++ b/site/content/pages/about/privacy.md @@ -16,11 +16,10 @@ authors: Adam Harvey <section class="about-menu"> <ul> <li><a href="/about/">About</a></li> +<li><a href="/about/faq/">FAQs</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 class="current" href="/about/privacy/">Privacy Policy</a></li> +<li><a href="/about/terms/">Terms</a></li> +<li><a class="current" href="/about/privacy/">Privacy</a></li> </ul> </section> diff --git a/site/content/pages/about/terms.md b/site/content/pages/about/terms.md index 7ae6dac7..e03bafaa 100644 --- a/site/content/pages/about/terms.md +++ b/site/content/pages/about/terms.md @@ -17,11 +17,10 @@ authors: Adam Harvey <section class="about-menu"> <ul> <li><a href="/about/">About</a></li> +<li><a href="/about/faq/">FAQs</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 class="current" href="/about/terms/">Terms and Conditions</a></li> -<li><a href="/about/privacy/">Privacy Policy</a></li> +<li><a class="current" href="/about/terms/">Terms</a></li> +<li><a href="/about/privacy/">Privacy</a></li> </ul> </section> diff --git a/site/content/pages/datasets/brainwash/assets/00818000_640x480.jpg b/site/content/pages/datasets/brainwash/assets/00818000_640x480.jpg Binary files differdeleted file mode 100644 index 30c0fcb1..00000000 --- a/site/content/pages/datasets/brainwash/assets/00818000_640x480.jpg +++ /dev/null diff --git a/site/content/pages/datasets/brainwash/assets/background_540.jpg b/site/content/pages/datasets/brainwash/assets/background_540.jpg Binary files differdeleted file mode 100644 index 5c8c0ad4..00000000 --- a/site/content/pages/datasets/brainwash/assets/background_540.jpg +++ /dev/null diff --git a/site/content/pages/datasets/brainwash/assets/background_600.jpg b/site/content/pages/datasets/brainwash/assets/background_600.jpg Binary files differdeleted file mode 100755 index 8f2de697..00000000 --- a/site/content/pages/datasets/brainwash/assets/background_600.jpg +++ /dev/null diff --git a/site/content/pages/datasets/brainwash/assets/brainwash_mean_overlay.jpg b/site/content/pages/datasets/brainwash/assets/brainwash_mean_overlay.jpg Binary files differnew file mode 100755 index 00000000..2f5917e3 --- /dev/null +++ b/site/content/pages/datasets/brainwash/assets/brainwash_mean_overlay.jpg diff --git a/site/content/pages/datasets/brainwash/assets/brainwash_mean_overlay_wm.jpg b/site/content/pages/datasets/brainwash/assets/brainwash_mean_overlay_wm.jpg Binary files differnew file mode 100755 index 00000000..790dbb79 --- /dev/null +++ b/site/content/pages/datasets/brainwash/assets/brainwash_mean_overlay_wm.jpg diff --git a/site/content/pages/datasets/brainwash/index.md b/site/content/pages/datasets/brainwash/index.md index 0bf67455..6d90e78f 100644 --- a/site/content/pages/datasets/brainwash/index.md +++ b/site/content/pages/datasets/brainwash/index.md @@ -2,8 +2,8 @@ status: published title: Brainwash -desc: Brainwash is a dataset of webcam images taken from the Brainwash Cafe in San Francisco -subdesc: The Brainwash dataset includes 11,918 images of "everyday life of a busy downtown cafe" and is used for training head detection algorithms +desc: Brainwash is a dataset of webcam images taken from the Brainwash Cafe in San Francisco in 2014 +subdesc: The Brainwash dataset includes 11,918 images of "everyday life of a busy downtown cafe" and is used for training head detection surveillance algorithms slug: brainwash cssclass: dataset image: assets/background.jpg @@ -19,28 +19,23 @@ authors: Adam Harvey + Published: 2015 + Images: 11,918 + Faces: 91,146 -+ Created by: Stanford Department of Computer Science ++ Created by: Stanford University (US)<br>Max Planck Institute for Informatics (DE) + Funded by: Max Planck Center for Visual Computing and Communication -+ Location: Brainwash Cafe, San Franscisco -+ Purpose: Training face detection ++ Purpose: Head detection ++ Download Size: 4.1GB + 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> -+ Explicit Consent: No ## Brainwash Dataset -(PAGE UNDER DEVELOPMENT) +*Brainwash* is a head detection dataset created from San Francisco's Brainwash Cafe livecam footage. It includes 11,918 images of "everyday life of a busy downtown cafe"[^readme] captured at 100 second intervals throught the entire day. Brainwash dataset was captured during 3 days in 2014: October 27, November 13, and November 24. According the author's reserach paper introducing the dataset, the images were acquired with the help of Angelcam.com [cite orig paper]. -*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. +Brainwash is not a widely used dataset but since its publication by Stanford University in 2015, it has notably appeared in several research papers from the National University of Defense Technology in Changsha, China. In 2016 and in 2017 researchers there conducted studies on detecting people's heads in crowded scenes for the purpose of surveillance [^localized_region_context] [^replacement_algorithm]. -Before closing in 2017, Brainwash Cafe was a "cafe and laundromat" located in San Francisco's SoMA district. The cafe published a publicy available livestream from the cafe with a view of the cash register, performance stage, and seating area. +If you happen to have been at Brainwash cafe in San Franscisco at any time on October 26, November 13, or November 24 in 2014 you are most likely included in the Brainwash dataset. -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]". + - - - {% include 'chart.html' %} @@ -48,19 +43,27 @@ Since it's publication by Stanford in 2015, the Brainwash dataset has appeared i {% include 'map.html' %} -Add more analysis here - +{% include 'citations.html' %} {% include 'supplementary_header.html' %} -{% include 'citations.html' %} + + -### Additional Information +#### Additional Resources - The dataset author spoke about his research at the CVPR conference in 2016 <https://www.youtube.com/watch?v=Nl2fBKxwusQ> +TODO + +- add bounding boxes to the header image +- remake montage with randomized images, with bboxes +- clean up intro text +- verify quote citations + + ### Footnotes [^readme]: "readme.txt" https://exhibits.stanford.edu/data/catalog/sx925dc9385. diff --git a/site/content/pages/datasets/duke_mtmc/assets/duke_mtmc_cam5_average_comp.jpg b/site/content/pages/datasets/duke_mtmc/assets/duke_mtmc_cam5_average_comp.jpg Binary files differnew file mode 100755 index 00000000..3cd64df1 --- /dev/null +++ b/site/content/pages/datasets/duke_mtmc/assets/duke_mtmc_cam5_average_comp.jpg diff --git a/site/content/pages/datasets/duke_mtmc/index.md b/site/content/pages/datasets/duke_mtmc/index.md index de1fa14c..c626ef4e 100644 --- a/site/content/pages/datasets/duke_mtmc/index.md +++ b/site/content/pages/datasets/duke_mtmc/index.md @@ -2,8 +2,8 @@ status: published title: Duke Multi-Target, Multi-Camera Tracking -desc: <span class="dataset-name">Duke MTMC</span> is a dataset of CCTV footage of students at Duke University -subdesc: Duke MTMC contains over 2 million video frames and 2,000 unique identities collected from 8 cameras at Duke University campus in March 2014 +desc: <span class="dataset-name">Duke MTMC</span> is a dataset of surveillance camera footage of students on Duke University campus +subdesc: Duke MTMC contains over 2 million video frames and 2,000 unique identities collected from 8 HD cameras at Duke University campus in March 2014 slug: duke_mtmc cssclass: dataset image: assets/background.jpg @@ -15,17 +15,27 @@ authors: Adam Harvey ### sidebar -+ Collected: March 19, 2014 -+ Cameras: 8 -+ Video Frames: 2,000,000 -+ Identities: Over 2,000 -+ Used for: Person re-identification, <br>face recognition -+ Sector: Academic ++ Created: 2014 ++ Identities: Over 2,700 ++ Used for: Face recognition, person re-identification ++ Created by: Computer Science Department, Duke University, Durham, US + Website: <a href="http://vision.cs.duke.edu/DukeMTMC/">duke.edu</a> ## Duke Multi-Target, Multi-Camera Tracking Dataset (Duke MTMC) -(PAGE UNDER DEVELOPMENT) +[ PAGE UNDER DEVELOPMENT ] + +Duke MTMC is a dataset of video recorded on Duke University campus during for the purpose of training, evaluating, and improving *multi-target multi-camera tracking*. The videos were recorded during February and March 2014 and cinclude + +Includes a total of 888.8 minutes of video (ind. verified) + +"We make available a new data set that has more than 2 million frames and more than 2,700 identities. It consists of 8×85 minutes of 1080p video recorded at 60 frames per second from 8 static cameras deployed on the Duke University campus during periods between lectures, when pedestrian traffic is heavy." + +The dataset includes approximately 2,000 annotated identities appearing in 85 hours of video from 8 cameras located throughout Duke University's campus. + + + +According to the dataset authors, {% include 'map.html' %} diff --git a/site/content/pages/datasets/index.md b/site/content/pages/datasets/index.md index 2e943fbe..c0373d60 100644 --- a/site/content/pages/datasets/index.md +++ b/site/content/pages/datasets/index.md @@ -13,4 +13,4 @@ sync: false # Facial Recognition Datasets -### Survey +Explore publicly available facial recognition datasets. More datasets will be added throughout 2019. diff --git a/site/content/pages/datasets/msceleb/assets/background.jpg b/site/content/pages/datasets/msceleb/assets/background.jpg Binary files differnew file mode 100644 index 00000000..c1cd486e --- /dev/null +++ b/site/content/pages/datasets/msceleb/assets/background.jpg diff --git a/site/content/pages/datasets/msceleb/assets/index.jpg b/site/content/pages/datasets/msceleb/assets/index.jpg Binary files differnew file mode 100644 index 00000000..fb3a934a --- /dev/null +++ b/site/content/pages/datasets/msceleb/assets/index.jpg diff --git a/site/content/pages/datasets/msceleb/index.md b/site/content/pages/datasets/msceleb/index.md new file mode 100644 index 00000000..eb084eaa --- /dev/null +++ b/site/content/pages/datasets/msceleb/index.md @@ -0,0 +1,56 @@ +------------ + +status: published +title: MS Celeb +desc: MS Celeb is a dataset of web images used for training and evaluating face recognition algorithms +subdesc: The MS Celeb dataset includes over 10,000,000 images and 93,000 identities of semi-public figures collected using the Bing search engine +slug: msceleb +cssclass: dataset +image: assets/background.jpg +year: 2015 +published: 2019-2-23 +updated: 2019-2-23 +authors: Adam Harvey + +------------ + +### sidebar + ++ Published: TBD ++ Images: TBD ++ Faces: TBD ++ Created by: TBD + + +## Microsoft Celeb Dataset (MS Celeb) + +(PAGE UNDER DEVELOPMENT) + +At vero eos et accusamus et iusto odio dignissimos ducimus, qui blanditiis praesentium voluptatum deleniti atque corrupti, quos dolores et quas molestias excepturi sint, obcaecati cupiditate non-provident, similique sunt in culpa, qui officia deserunt mollitia animi, id est laborum et dolorum fuga. Et harum quidem rerum facilis est et expedita distinctio. + +Nam libero tempore, cum soluta nobis est eligendi optio, cumque nihil impedit, quo minus id, quod maxime placeat, facere possimus, omnis voluptas assumenda est, omnis dolor repellendus. Temporibus autem quibusdam et aut officiis debitis aut rerum necessitatibus saepe eveniet, ut et voluptates repudiandae sint et molestiae non-recusandae. Itaque earum rerum hic tenetur a sapiente delectus, ut aut reiciendis voluptatibus maiores alias consequatur aut perferendis doloribus asperiores repellat + +{% include 'chart.html' %} + +{% include 'piechart.html' %} + +{% include 'map.html' %} + +Add more analysis here + + +{% include 'supplementary_header.html' %} + +{% include 'citations.html' %} + + +### Additional Information + +- The dataset author spoke about his research at the CVPR conference in 2016 <https://www.youtube.com/watch?v=Nl2fBKxwusQ> + + +### Footnotes + +[^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/uccs/assets/uccs_bboxes_clr_fill.jpg b/site/content/pages/datasets/uccs/assets/uccs_bboxes_clr_fill.jpg Binary files differdeleted file mode 100644 index c8002bb9..00000000 --- a/site/content/pages/datasets/uccs/assets/uccs_bboxes_clr_fill.jpg +++ /dev/null diff --git a/site/content/pages/datasets/uccs/assets/uccs_bboxes_grayscale.jpg b/site/content/pages/datasets/uccs/assets/uccs_bboxes_grayscale.jpg Binary files differdeleted file mode 100644 index 6e2833dd..00000000 --- a/site/content/pages/datasets/uccs/assets/uccs_bboxes_grayscale.jpg +++ /dev/null diff --git a/site/content/pages/datasets/uccs/assets/uccs_mean_bboxes_comp.jpg b/site/content/pages/datasets/uccs/assets/uccs_mean_bboxes_comp.jpg Binary files differnew file mode 100644 index 00000000..18f4c5ec --- /dev/null +++ b/site/content/pages/datasets/uccs/assets/uccs_mean_bboxes_comp.jpg diff --git a/site/content/pages/datasets/uccs/index.md b/site/content/pages/datasets/uccs/index.md index 092638c0..1e3ec097 100644 --- a/site/content/pages/datasets/uccs/index.md +++ b/site/content/pages/datasets/uccs/index.md @@ -2,11 +2,11 @@ status: published title: Unconstrained College Students -desc: <span class="dataset-name">Unconstrained College Students (UCCS)</span> is a dataset of images ... -subdesc: The UCCS dataset includes ... -slug: uccs +desc: <span class="dataset-name">Unconstrained College Students (UCCS)</span> is a dataset of long-range surveillance photos of students taken without their knowledge +subdesc: The UCCS dataset includes 16,149 images and 1,732 identities of students at University of Colorado Colorado Springs campus and is used for face recognition and face detection cssclass: dataset image: assets/background.jpg +slug: uccs published: 2019-2-23 updated: 2019-2-23 authors: Adam Harvey @@ -15,16 +15,22 @@ authors: Adam Harvey ### sidebar -+ Collected: TBD -+ Published: TBD -+ Images: TBD -+ Faces: TBD ++ Published: 2018 ++ Images: 16,149 ++ Identities: 1,732 ++ Used for: Face recognition, face detection ++ Created by: Unviversity of Colorado Colorado Springs (US) ++ Funded by: ODNI, IARPA, ONR MURI, Amry SBIR, SOCOM SBIR ++ Website: <a href="https://vast.uccs.edu/Opensetface/">vast.uccs.edu</a> ## Unconstrained College Students ... (PAGE UNDER DEVELOPMENT) + + + {% include 'map.html' %} {% include 'chart.html' %} @@ -36,7 +42,6 @@ authors: Adam Harvey {% include 'citations.html' %} - ### Research Notes @@ -55,4 +60,15 @@ The more recent UCCS version of the dataset received funding from [^funding_uccs [^funding_sb]: Sapkota, Archana and Boult, Terrance. "Large Scale Unconstrained Open Set Face Database." 2013. -[^funding_uccs]: Günther, M. et. al. "Unconstrained Face Detection and Open-Set Face Recognition Challenge," 2018. Arxiv 1708.02337v3.
\ No newline at end of file +[^funding_uccs]: Günther, M. et. al. "Unconstrained Face Detection and Open-Set Face Recognition Challenge," 2018. Arxiv 1708.02337v3. + + +" In most face detection/recognition datasets, the majority of images are “posed”, i.e. the subjects know they are being photographed, and/or the images are selected for publication in public media. Hence, blurry, occluded and badly illuminated images are generally uncommon in these datasets. In addition, most of these challenges are close-set, i.e. the list of subjects in the gallery is the same as the one used for testing. + +This challenge explores more unconstrained data, by introducing the new UnConstrained College Students (UCCS) dataset, where subjects are photographed using a long-range high-resolution surveillance camera without their knowledge. Faces inside these images are of various poses, and varied levels of blurriness and occlusion. The challenge also creates an open set recognition problem, where unknown people will be seen during testing and must be rejected. + +With this challenge, we hope to foster face detection and recognition research towards surveillance applications that are becoming more popular and more required nowadays, and where no automatic recognition algorithm has proven to be useful yet. + +UnConstrained College Students (UCCS) Dataset + +The UCCS dataset was collected over several months using Canon 7D camera fitted with Sigma 800mm F5.6 EX APO DG HSM lens, taking images at one frame per second, during times when many students were walking on the sidewalk. "
\ No newline at end of file diff --git a/site/content/pages/research/01_from_1_to_100_pixels/index.md b/site/content/pages/research/01_from_1_to_100_pixels/index.md index a7b863a9..b219dffb 100644 --- a/site/content/pages/research/01_from_1_to_100_pixels/index.md +++ b/site/content/pages/research/01_from_1_to_100_pixels/index.md @@ -56,3 +56,55 @@ Ideas: - "Note that we only keep the images with a minimal side length of 80 pixels." and "a face will be labeled as “Ignore” if it is very difficult to be detected due to blurring, severe deformation and unrecognizable eyes, or the side length of its bounding box is less than 32 pixels." Ge_Detecting_Masked_Faces_CVPR_2017_paper.pdf - IBM DiF: "Faces with region size less than 50x50 or inter-ocular distance of less than 30 pixels were discarded. Faces with non-frontal pose, or anything beyond being slightly tilted to the left or the right, were also discarded." + + + + +As the resolution +formatted as rectangular databases of 16 bit RGB-tuples or 8 bit grayscale values + + +To consider how visual privacy applies to real world surveillance situations, the first + +A single 8-bit grayscale pixel with 256 values is enough to represent the entire alphabet `a-Z0-9` with room to spare. + +A 2x2 pixels contains + +Using no more than a 42 pixel (6x7 image) face image researchers [cite] were able to correctly distinguish between a group of 50 people. Yet + +The likely outcome of face recognition research is that more data is needed to improve. Indeed, resolution is the determining factor for all biometric systems, both as training data to increase + +Pixels, typically considered the buiding blocks of images and vidoes, can also be plotted as a graph of sensor values corresponding to the intensity of RGB-calibrated sensors. + + +Wi-Fi and cameras presents elevated risks for transmitting videos and image documentation from conflict zones, high-risk situations, or even sharing on social media. How can new developments in computer vision also be used in reverse, as a counter-forensic tool, to minimize an individual's privacy risk? + +As the global Internet becomes increasingly effecient at turning the Internet into a giant dataset for machine learning, forensics, and data analysing, it would be prudent to also consider tools for decreasing the resolution. The Visual Defense module is just that. What are new ways to minimize the adverse effects of surveillance by dulling the blade. For example, a researcher paper showed that by decreasing a face size to 12x16 it was possible to do 98% accuracy with 50 people. This is clearly an example of + +This research module, tentatively called Visual Defense Tools, aims to explore the + + +### Prior Research + +- MPI visual privacy advisor +- NIST: super resolution +- YouTube blur tool +- WITNESS: blur tool +- Pixellated text +- CV Dazzle +- Bellingcat guide to geolocation +- Peng! magic passport + +### Notes + +- In China, out of the approximately 200 million surveillance cameras only about 15% have enough resolution for face recognition. +- In Apple's FaceID security guide, the probability of someone else's face unlocking your phone is 1 out of 1,000,000. +- In England, the Metropolitan Police reported a false-positive match rate of 98% when attempting to use face recognition to locate wanted criminals. +- In a face recognition trial at Berlin's Sudkreuz station, the false-match rate was 20%. + + +What all 3 examples illustrate is that face recognition is anything but absolute. In a 2017 talk, Jason Matheny the former directory of IARPA, admitted the face recognition is so brittle it can be subverted by using a magic marker and drawing "a few dots on your forehead". In fact face recognition is a misleading term. Face recognition is search engine for faces that can only ever show you the mos likely match. This presents real a real threat to privacy and lends + + +Globally, iPhone users unwittingly agree to 1/1,000,000 probably +relying on FaceID and TouchID to protect their information agree to a
\ No newline at end of file diff --git a/site/content/pages/research/02_what_computers_can_see/index.md b/site/content/pages/research/02_what_computers_can_see/index.md index ab4c7884..51621f46 100644 --- a/site/content/pages/research/02_what_computers_can_see/index.md +++ b/site/content/pages/research/02_what_computers_can_see/index.md @@ -100,6 +100,7 @@ A list of 100 things computer vision can see, eg: - Wearing Necktie - Wearing Necklace +for i in {1..9};do wget http://visiond1.cs.umbc.edu/webpage/codedata/ADLdataset/ADL_videos/P_0$i.MP4;done;for i in {10..20}; do wget http://visiond1.cs.umbc.edu/webpage/codedata/ADLdataset/ADL_videos/P_$i.MP4;done ## From Market 1501 @@ -149,4 +150,26 @@ Visibility boolean for each keypoint Region annotations (upper clothes, lower clothes, dress, socks, shoes, hands, gloves, neck, face, hair, hat, sunglasses, bag, occluder) Body type (male, female or child) -source: https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/shape/h3d/
\ No newline at end of file +source: https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/shape/h3d/ + +## From Leeds Sports Pose + +=INDEX(A2:A9,MATCH(datasets!D1,B2:B9,0)) +=VLOOKUP(A2, datasets!A:J, 7, FALSE) + +Right ankle +Right knee +Right hip +Left hip +Left knee +Left ankle +Right wrist +Right elbow +Right shoulder +Left shoulder +Left elbow +Left wrist +Neck +Head top + +source: http://web.archive.org/web/20170915023005/sam.johnson.io/research/lsp.html
\ No newline at end of file diff --git a/site/includes/chart.html b/site/includes/chart.html index 45c13493..01c2e83b 100644 --- a/site/includes/chart.html +++ b/site/includes/chart.html @@ -2,8 +2,7 @@ <h3>Who used {{ metadata.meta.dataset.name_display }}?</h3> <p> - This bar chart presents a ranking of the top countries where citations originated. Mouse over individual columns - to see yearly totals. These charts show at most the top 10 countries. + This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. </p> </section> diff --git a/site/includes/citations.html b/site/includes/citations.html index 058a1834..32558d4a 100644 --- a/site/includes/citations.html +++ b/site/includes/citations.html @@ -1,12 +1,11 @@ <section class="applet_container"> - <h3>Citations</h3> + <h3>Dataset Citations</h3> <p> - Citations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates - and indexes research papers. The citations were geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train and/or test machine learning algorithms. + The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. </p> <p> - Add [button/link] to download CSV. Add search input field to filter. Expand number of rows to 10. Reduce URL text to show only the domain (ie https://arxiv.org/pdf/123456 --> arxiv.org) + Add [button/link] to download CSV. Add search input field to filter. </p> <div class="applet" data-payload="{"command": "citations"}"></div> diff --git a/site/includes/map.html b/site/includes/map.html index 74771768..7511d4c7 100644 --- a/site/includes/map.html +++ b/site/includes/map.html @@ -1,6 +1,6 @@ <section> - <h3>Information Supply Chain</h3> + <h3>Biometric Trade Routes</h3> <!-- <div class="map-sidebar right-sidebar"> <h3>Legend</h3> @@ -12,27 +12,28 @@ </div> --> <p> - To understand how {{ metadata.meta.dataset.name_display }} has been used around the world... - affected global research on computer vision, surveillance, defense, and consumer technology, the and where this dataset has been used the locations of each organization that used or referenced the datast + To help understand how {{ metadata.meta.dataset.name_display }} has been used around the world for commercial, military and academic research; publicly available research citing {{ metadata.meta.dataset.name_full }} is collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal reserach projects at that location. </p> </section> -<section class="applet_container"> +<section class="applet_container fullwidth"> <div class="applet" data-payload="{"command": "map"}"></div> + </section> <div class="caption"> <ul class="map-legend"> <li class="edu">Academic</li> - <li class="com">Industry</li> - <li class="gov">Government / Military</li> + <li class="com">Commercial</li> + <li class="gov">Military / Government</li> <li class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</li> </ul> </div> -<section> +<!-- <section> <p class='subp'> [section under development] {{ metadata.meta.dataset.name_display }} ... Standardized paragraph of text about the map. 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. </p> </section> + -->
\ No newline at end of file diff --git a/site/includes/piechart.html b/site/includes/piechart.html index e739bb28..94c8aae7 100644 --- a/site/includes/piechart.html +++ b/site/includes/piechart.html @@ -1,10 +1,3 @@ -<section> - <p> - These pie charts show overall totals based on country and institution type. - </p> - - </section> - <section class="applet_container"> <div class="applet" data-payload="{"command": "piechart"}"></div> </section> diff --git a/site/includes/supplementary_header.html b/site/includes/supplementary_header.html index 5fd4b2b4..bcd84223 100644 --- a/site/includes/supplementary_header.html +++ b/site/includes/supplementary_header.html @@ -6,5 +6,6 @@ <div class="hr-wave-line hr-wave-line2"></div> </div> - <h2>Supplementary Information</h2> + <h3>Supplementary Information</h3> + </section> diff --git a/site/public/about/faq/index.html b/site/public/about/faq/index.html new file mode 100644 index 00000000..b86dac22 --- /dev/null +++ b/site/public/about/faq/index.html @@ -0,0 +1,59 @@ +<!doctype html> +<html> +<head> + <title>MegaPixels</title> + <meta charset="utf-8" /> + <meta name="author" content="Adam Harvey" /> + <meta name="description" content="MegaPixels Press and News" /> + <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="/about/">About</a> + </div> + </header> + <div class="content content-about"> + + <section><h1>FAQs</h1> +<section class="about-menu"> +<ul> +<li><a href="/about/">About</a></li> +<li><a class="current" href="/about/faq/">FAQs</a></li> +<li><a href="/about/press/">Press</a></li> +<li><a href="/about/terms/">Terms</a></li> +<li><a href="/about/privacy/">Privacy</a></li> +</ul> +</section><p>[ page under development ]</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 ©2017-19 Adam R. Harvey / + <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/index.html b/site/public/about/index.html index 3c270ee1..18ad797a 100644 --- a/site/public/about/index.html +++ b/site/public/about/index.html @@ -30,34 +30,50 @@ <section class="about-menu"> <ul> <li><a class="current" href="/about/">About</a></li> +<li><a href="/about/faq/">FAQs</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> +<li><a href="/about/terms/">Terms</a></li> +<li><a href="/about/privacy/">Privacy</a></li> </ul> -</section><p>(PAGE UNDER DEVELOPMENT)</p> -<p><div style="font-size:20px;line-height:36px">Ever since government agencies began developing face recognition in the early 1960's, datasets of face images have always been central to technological advancements. Today, these datasets no longer originate in labs, but instead from family photo albums posted on photo sharing sites, surveillance cameras on college campuses, search engine queries for celebrities, cafe livestreams, and <a href="https://www.theverge.com/2017/8/22/16180080/transgender-youtubers-ai-facial-recognition-dataset">personal videos</a> posted on YouTube. </div></p><p>Collectively, facial recognition datasets are now gathered "in the wild".</p> -<p>MegaPixels is art and research by <a href="https://ahprojects.com">Adam Harvey</a> about facial recognition datasets that unravels their histories, futures, geographies, and meanings. Throughout 2019 this site this site will publish research reports, visualizations, raw data, and interactive tools to explore how publicly available facial recognition datasets contribute to a global supply chain of biometric data that powers the global facial recognition industry.</p><p>During the last year, hundreds of these facial analysis datasets created "in the wild" have been collected to understand how they contribute to a global supply chain of biometric data that is powering the global facial recognition industry.</p> -<p>The MegaPixels website is produced in partnership with <a href="https://mozilla.org">Mozilla</a>.</p> +</section><p>MegaPixels is an independent art and research project by Adam Harvey and Jules LaPlace investigating the ethics and individual privacy implications of publicly available face recognition datasets, and their role in industry and governmental expansion into biometric surveillance technologies.</p> +<p>The MegaPixels site is made possible with support from <a href="http://mozilla.org">Mozilla</a></p> <div class="flex-container team-photos-container"> <div class="team-member"> - <img src="https://nyc3.digitaloceanspaces.com/megapixels/v1/site/about/assets/adam-harvey-3d.jpg" /> <h3>Adam Harvey</h3> - <p>is Berlin-based American artist and researcher. 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 grants, and is a researcher in residence at Karlsruhe HfG. - <br> - <a href="https://ahprojects.com">ahprojects.com</a> + <p>is Berlin-based American artist and researcher. His previous projects (CV Dazzle, Stealth Wear, and SkyLift) explore the potential for counter-surveillance as artwork. He is the founder of VFRAME (visual forensics software for human rights groups) and is a currently researcher in residence at Karlsruhe HfG.</p> + <p><a href="https://ahprojects.com">ahprojects.com</a></p> </p> </div> <div class="team-member"> - <img src="https://nyc3.digitaloceanspaces.com/megapixels/v1/site/about/assets/jules-laplace-3d.jpg" /> <h3>Jules LaPlace</h3> - <p>is an American creative technologist also based in Berlin. He was previously the CTO of a digital agency in NYC and now also works at VFRAME, developing computer vision for human rights groups. Jules also builds creative software for artists and musicians. - <br> - <a href="https://asdf.us/">asdf.us</a> + <p>is an American technologist and artist also based in Berlin. He was previously the CTO of a digital agency in NYC and now also works at VFRAME, developing computer vision and data analysis software for human rights groups. Jules also builds experimental software for artists and musicians. </p> + <p><a href="https://asdf.us/">asdf.us</a></p> </div> -</div></section> +</div><p>MegaPixels.cc is an independent research project about publicly available face recognition datasets. This website is based, in part, on earlier installations and research projects about facial recognition datasets in 2016-2018, which focused particularly on the MegaFace dataset. Since then it has evolved into a large-scale survey of publicly-available face and person analysis datasets, covering their usage, geographies, and ethics.</p> +<p>An academic report and presentation on the findings is forthcoming. This site is published to make the research more accessible to a wider audience and to include visualizations and interactive features not possible in PDF publications. Continued research on MegaPixels is supported by a 1 year Researcher-in-Residence grant from Karlsruhe HfG.</p> +<p>When possible, and once thoroughly verified, data generated for MegaPixels will be made available for download on <a href="https://github.com/adamhrv/megapixels">github.com/adamhrv/megapixels</a></p> +</section><section><div class='columns columns-3'><div class='column'><h4>Team</h4> +<ul> +<li>Adam Harvey: Concept, research, design, computer vision</li> +<li>Jules LaPlace: Information and systems architecture, data retrieval, web applications</li> +</ul> +</div><div class='column'><h4>Contributing Researchers</h4> +<ul> +<li>Berit Gilma: Dataset statistics and discovery</li> +<li>Beth (aka Ms. Celeb): Dataset usage verification and research</li> +<li>Mathana Stender: Commercial usage verification and research on LFW</li> +</ul> +</div><div class='column'><h4>Code and Libraries</h4> +<ul> +<li><a href="https://semanticscholar.org">Semantic Scholar</a> for citation aggregation</li> +<li>Leaflet.js for maps</li> +<li>C3.js for charts</li> +<li>ThreeJS for 3D visualizations</li> +<li>PDFMiner.Six and Pandas for research paper data analysis</li> +</ul> +</div></div></section><section><p>Please direct questions, comments, or feedback to <a href="https://mastodon.social/@adamhrv">mastodon.social/@adamhrv</a></p> +</section> </div> <footer> diff --git a/site/public/about/press/index.html b/site/public/about/press/index.html index e2e646da..3fc33969 100644 --- a/site/public/about/press/index.html +++ b/site/public/about/press/index.html @@ -30,11 +30,10 @@ <section class="about-menu"> <ul> <li><a href="/about/">About</a></li> +<li><a href="/about/faq/">FAQs</a></li> <li><a class="current" 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> +<li><a href="/about/terms/">Terms</a></li> +<li><a href="/about/privacy/">Privacy</a></li> </ul> </section><p>(TEMPORARY PAGE)</p> <ul> diff --git a/site/public/about/privacy/index.html b/site/public/about/privacy/index.html index f6915d66..2e1b3349 100644 --- a/site/public/about/privacy/index.html +++ b/site/public/about/privacy/index.html @@ -30,11 +30,10 @@ <section class="about-menu"> <ul> <li><a href="/about/">About</a></li> +<li><a href="/about/faq/">FAQs</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 class="current" href="/about/privacy/">Privacy Policy</a></li> +<li><a href="/about/terms/">Terms</a></li> +<li><a class="current" href="/about/privacy/">Privacy</a></li> </ul> </section><p>(TEMPORARY PAGE)</p> <p>A summary of our privacy policy is as follows:</p> diff --git a/site/public/about/terms/index.html b/site/public/about/terms/index.html index b86eae88..58e49b78 100644 --- a/site/public/about/terms/index.html +++ b/site/public/about/terms/index.html @@ -30,11 +30,10 @@ <section class="about-menu"> <ul> <li><a href="/about/">About</a></li> +<li><a href="/about/faq/">FAQs</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 class="current" href="/about/terms/">Terms and Conditions</a></li> -<li><a href="/about/privacy/">Privacy Policy</a></li> +<li><a class="current" href="/about/terms/">Terms</a></li> +<li><a href="/about/privacy/">Privacy</a></li> </ul> </section><p>(TEMPORARY PAGE)</p> <p>(FPO: this is only example text)</p> diff --git a/site/public/datasets/50_people_one_question/index.html b/site/public/datasets/50_people_one_question/index.html index bded7fbd..8e3d2d2b 100644 --- a/site/public/datasets/50_people_one_question/index.html +++ b/site/public/datasets/50_people_one_question/index.html @@ -33,7 +33,7 @@ <p>Nam libero tempore, cum soluta nobis est eligendi optio, cumque nihil impedit, quo minus id, quod maxime placeat, facere possimus, omnis voluptas assumenda est, omnis dolor repellendus. Temporibus autem quibusdam et aut officiis debitis aut rerum necessitatibus saepe eveniet, ut et voluptates repudiandae sint et molestiae non-recusandae. Itaque earum rerum hic tenetur a sapiente delectus, ut aut reiciendis voluptatibus maiores alias consequatur aut perferendis doloribus asperiores repellat</p> </section><section> - <h3>Information Supply Chain</h3> + <h3>Biometric Trade Routes</h3> <!-- <div class="map-sidebar right-sidebar"> <h3>Legend</h3> @@ -45,28 +45,31 @@ </div> --> <p> - To understand how 50 People One Question Dataset has been used around the world... - affected global research on computer vision, surveillance, defense, and consumer technology, the and where this dataset has been used the locations of each organization that used or referenced the datast + To help understand how 50 People One Question Dataset has been used around the world for commercial, military and academic research; publicly available research citing 50 People One Question is collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal reserach projects at that location. </p> </section> -<section class="applet_container"> +<section class="applet_container fullwidth"> <div class="applet" data-payload="{"command": "map"}"></div> + </section> <div class="caption"> - <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 has been manually verified to show usage of 50 People One Question Dataset. + <ul class="map-legend"> + <li class="edu">Academic</li> + <li class="com">Commercial</li> + <li class="gov">Military / Government</li> + <li class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</li> + </ul> </div> -<section> +<!-- <section> <p class='subp'> - Standardized paragraph of text about the map. 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. + [section under development] 50 People One Question Dataset ... Standardized paragraph of text about the map. 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. </p> -</section><section> +</section> + --><section> <div class="hr-wave-holder"> @@ -74,16 +77,16 @@ <div class="hr-wave-line hr-wave-line2"></div> </div> - <h2>Supplementary Information</h2> + <h3>Supplementary Information</h3> + </section><section class="applet_container"> - <h3>Citations</h3> + <h3>Dataset Citations</h3> <p> - Citations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates - and indexes research papers. The citations were geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train and/or test machine learning algorithms. + The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. </p> <p> - Add button/link to download CSV + Add [button/link] to download CSV. Add search input field to filter. </p> <div class="applet" data-payload="{"command": "citations"}"></div> diff --git a/site/public/datasets/brainwash/index.html b/site/public/datasets/brainwash/index.html index 41484257..c97349aa 100644 --- a/site/public/datasets/brainwash/index.html +++ b/site/public/datasets/brainwash/index.html @@ -4,7 +4,7 @@ <title>MegaPixels</title> <meta charset="utf-8" /> <meta name="author" content="Adam Harvey" /> - <meta name="description" content="Brainwash is a dataset of webcam images taken from the Brainwash Cafe in San Francisco" /> + <meta name="description" content="Brainwash is a dataset of webcam images taken from the Brainwash Cafe in San Francisco in 2014" /> <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' /> @@ -26,36 +26,29 @@ </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'>Brainwash is a dataset of webcam images taken from the Brainwash Cafe in San Francisco</span></div><div class='hero_subdesc'><span class='bgpad'>The Brainwash dataset includes 11,918 images of "everyday life of a busy downtown cafe" and is used for training head detection algorithms -</span></div></div></section><section><div class='left-sidebar'><div class='meta'><div><div class='gray'>Published</div><div>2015</div></div><div><div class='gray'>Images</div><div>11,918</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'>Location</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><div class='gray'>Paper</div><div><a href="http://arxiv.org/abs/1506.04878">End-to-End People Detection in Crowded Scenes</a></div></div><div><div class='gray'>Explicit Consent</div><div>No</div></div></div></div><h2>Brainwash Dataset</h2> -<p>(PAGE UNDER DEVELOPMENT)</p> -<p><em>Brainwash</em> 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<a class="footnote_shim" name="[^readme]_1"> </a><a href="#[^readme]" class="footnote" title="Footnote 1">1</a>". The images are used to develop face detection algorithms for the "challenging task of detecting people in crowded scenes" and tracking them.</p> -<p>Before closing in 2017, Brainwash Cafe was a "cafe and laundromat" located in San Francisco's SoMA district. The cafe published a publicy available livestream from the cafe with a view of the cash register, performance stage, and seating area.</p> -<p>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<a class="footnote_shim" name="[^localized_region_context]_1"> </a><a href="#[^localized_region_context]" class="footnote" title="Footnote 2">2</a>". 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<a class="footnote_shim" name="[^replacement_algorithm]_1"> </a><a href="#[^replacement_algorithm]" class="footnote" title="Footnote 3">3</a>".</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 and head detection algorithms for surveillance. The datset contains about 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 and head detection algorithms for surveillance. The datset contains about 12,000 images. License: Open Data Commons Public Domain Dedication (PDDL)</div></div></section><section class='images'><div class='image'><img src='https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/brainwash/assets/brainwash_montage.jpg' alt=' 49 of the 11,918 images included in the Brainwash dataset. License: Open Data Commons Public Domain Dedication (PDDL)'><div class='caption'> 49 of the 11,918 images included in the Brainwash dataset. License: Open Data Commons Public Domain Dedication (PDDL)</div></div></section><section> + <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'>Brainwash is a dataset of webcam images taken from the Brainwash Cafe in San Francisco in 2014</span></div><div class='hero_subdesc'><span class='bgpad'>The Brainwash dataset includes 11,918 images of "everyday life of a busy downtown cafe" and is used for training head detection surveillance algorithms +</span></div></div></section><section><div class='left-sidebar'><div class='meta'><div><div class='gray'>Published</div><div>2015</div></div><div><div class='gray'>Images</div><div>11,918</div></div><div><div class='gray'>Faces</div><div>91,146</div></div><div><div class='gray'>Created by</div><div>Stanford University (US)<br>Max Planck Institute for Informatics (DE)</div></div><div><div class='gray'>Funded by</div><div>Max Planck Center for Visual Computing and Communication</div></div><div><div class='gray'>Purpose</div><div>Head detection</div></div><div><div class='gray'>Download Size</div><div>4.1GB</div></div><div><div class='gray'>Website</div><div><a href="https://exhibits.stanford.edu/data/catalog/sx925dc9385">stanford.edu</a></div></div></div></div><h2>Brainwash Dataset</h2> +<p><em>Brainwash</em> is a head detection dataset created from San Francisco's Brainwash Cafe livecam footage. It includes 11,918 images of "everyday life of a busy downtown cafe"<a class="footnote_shim" name="[^readme]_1"> </a><a href="#[^readme]" class="footnote" title="Footnote 1">1</a> captured at 100 second intervals throught the entire day. Brainwash dataset was captured during 3 days in 2014: October 27, November 13, and November 24. According the author's reserach paper introducing the dataset, the images were acquired with the help of Angelcam.com [cite orig paper].</p> +<p>Brainwash is not a widely used dataset but since its publication by Stanford University in 2015, it has notably appeared in several research papers from the National University of Defense Technology in Changsha, China. In 2016 and in 2017 researchers there conducted studies on detecting people's heads in crowded scenes for the purpose of surveillance <a class="footnote_shim" name="[^localized_region_context]_1"> </a><a href="#[^localized_region_context]" class="footnote" title="Footnote 2">2</a> <a class="footnote_shim" name="[^replacement_algorithm]_1"> </a><a href="#[^replacement_algorithm]" class="footnote" title="Footnote 3">3</a>.</p> +<p>If you happen to have been at Brainwash cafe in San Franscisco at any time on October 26, November 13, or November 24 in 2014 you are most likely included in the Brainwash dataset.</p> +</section><section class='images'><div class='image'><img src='https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/brainwash/assets/brainwash_mean_overlay.jpg' alt=' The pixel-averaged image of all Brainwash dataset images is shown with 81,973 head annotations drawn from the Brainwash training partition. (c) Adam Harvey'><div class='caption'> The pixel-averaged image of all Brainwash dataset images is shown with 81,973 head annotations drawn from the Brainwash training partition. (c) Adam Harvey</div></div></section><section> <h3>Who used Brainwash Dataset?</h3> <p> - This bar chart presents a ranking of the top countries where citations originated. Mouse over individual columns - to see yearly totals. These charts show at most the top 10 countries. + This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. </p> </section> <section class="applet_container"> +<!-- <div style="position: absolute;top: 0px;right: -55px;width: 180px;font-size: 14px;">Labeled Faces in the Wild Dataset<br><span class="numc" style="font-size: 11px;">20 citations</span> +</div> --> <div class="applet" data-payload="{"command": "chart"}"></div> -</section><section> - <p> - These pie charts show overall totals based on country and institution type. - </p> - - </section> - -<section class="applet_container"> +</section><section class="applet_container"> <div class="applet" data-payload="{"command": "piechart"}"></div> </section><section> - <h3>Information Supply Chain</h3> + <h3>Biometric Trade Routes</h3> <!-- <div class="map-sidebar right-sidebar"> <h3>Legend</h3> @@ -67,28 +60,41 @@ </div> --> <p> - To understand how Brainwash Dataset has been used around the world... - affected global research on computer vision, surveillance, defense, and consumer technology, the and where this dataset has been used the locations of each organization that used or referenced the datast + To help understand how Brainwash Dataset has been used around the world for commercial, military and academic research; publicly available research citing Brainwash Dataset is collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal reserach projects at that location. </p> </section> -<section class="applet_container"> +<section class="applet_container fullwidth"> <div class="applet" data-payload="{"command": "map"}"></div> + </section> <div class="caption"> - <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 has been manually verified to show usage of Brainwash Dataset. + <ul class="map-legend"> + <li class="edu">Academic</li> + <li class="com">Commercial</li> + <li class="gov">Military / Government</li> + <li class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</li> + </ul> </div> -<section> +<!-- <section> <p class='subp'> - Standardized paragraph of text about the map. 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. + [section under development] Brainwash Dataset ... Standardized paragraph of text about the map. 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. </p> -</section><section><p>Add more analysis here</p> +</section> + --><section class="applet_container"> + + <h3>Dataset Citations</h3> + <p> + The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. + </p> + <p> + Add [button/link] to download CSV. Add search input field to filter. + </p> + + <div class="applet" data-payload="{"command": "citations"}"></div> </section><section> @@ -97,23 +103,19 @@ <div class="hr-wave-line hr-wave-line2"></div> </div> - <h2>Supplementary Information</h2> -</section><section class="applet_container"> - - <h3>Citations</h3> - <p> - Citations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates - and indexes research papers. The citations were geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train and/or test machine learning algorithms. - </p> - <p> - Add button/link to download CSV - </p> - - <div class="applet" data-payload="{"command": "citations"}"></div> -</section><section><h3>Additional Information</h3> + <h3>Supplementary Information</h3> + +</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 and head detection algorithms for surveillance. The datset contains about 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 and head detection algorithms for surveillance. The datset contains about 12,000 images. License: Open Data Commons Public Domain Dedication (PDDL)</div></div></section><section class='images'><div class='image'><img src='https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/brainwash/assets/brainwash_montage.jpg' alt=' 49 of the 11,918 images included in the Brainwash dataset. License: Open Data Commons Public Domain Dedication (PDDL)'><div class='caption'> 49 of the 11,918 images included in the Brainwash dataset. License: Open Data Commons Public Domain Dedication (PDDL)</div></div></section><section><h4>Additional Resources</h4> <ul> <li>The dataset author spoke about his research at the CVPR conference in 2016 <a href="https://www.youtube.com/watch?v=Nl2fBKxwusQ">https://www.youtube.com/watch?v=Nl2fBKxwusQ</a></li> </ul> +<p>TODO</p> +<ul> +<li>add bounding boxes to the header image</li> +<li>remake montage with randomized images, with bboxes</li> +<li>clean up intro text</li> +<li>verify quote citations</li> +</ul> </section><section><ul class="footnotes"><li><a name="[^readme]" class="footnote_shim"></a><span class="backlinks"><a href="#[^readme]_1">a</a></span><p>"readme.txt" <a href="https://exhibits.stanford.edu/data/catalog/sx925dc9385">https://exhibits.stanford.edu/data/catalog/sx925dc9385</a>.</p> </li><li><a name="[^localized_region_context]" class="footnote_shim"></a><span class="backlinks"><a href="#[^localized_region_context]_1">a</a></span><p>Li, Y. and Dou, Y. and Liu, X. and Li, T. Localized Region Context and Object Feature Fusion for People Head Detection. ICIP16 Proceedings. 2016. Pages 594-598.</p> </li><li><a name="[^replacement_algorithm]" class="footnote_shim"></a><span class="backlinks"><a href="#[^replacement_algorithm]_1">a</a></span><p>Zhao. X, Wang Y, Dou, Y. A Replacement Algorithm of Non-Maximum Suppression Base on Graph Clustering.</p> diff --git a/site/public/datasets/celeba/index.html b/site/public/datasets/celeba/index.html index 09347f10..e958cbef 100644 --- a/site/public/datasets/celeba/index.html +++ b/site/public/datasets/celeba/index.html @@ -33,7 +33,7 @@ <p>Nam libero tempore, cum soluta nobis est eligendi optio, cumque nihil impedit, quo minus id, quod maxime placeat, facere possimus, omnis voluptas assumenda est, omnis dolor repellendus. Temporibus autem quibusdam et aut officiis debitis aut rerum necessitatibus saepe eveniet, ut et voluptates repudiandae sint et molestiae non-recusandae. Itaque earum rerum hic tenetur a sapiente delectus, ut aut reiciendis voluptatibus maiores alias consequatur aut perferendis doloribus asperiores repellat</p> </section><section> - <h3>Information Supply Chain</h3> + <h3>Biometric Trade Routes</h3> <!-- <div class="map-sidebar right-sidebar"> <h3>Legend</h3> @@ -45,28 +45,31 @@ </div> --> <p> - To understand how CelebA Dataset has been used around the world... - affected global research on computer vision, surveillance, defense, and consumer technology, the and where this dataset has been used the locations of each organization that used or referenced the datast + To help understand how CelebA Dataset has been used around the world for commercial, military and academic research; publicly available research citing Large-scale CelebFaces Attributes Dataset is collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal reserach projects at that location. </p> </section> -<section class="applet_container"> +<section class="applet_container fullwidth"> <div class="applet" data-payload="{"command": "map"}"></div> + </section> <div class="caption"> - <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 has been manually verified to show usage of CelebA Dataset. + <ul class="map-legend"> + <li class="edu">Academic</li> + <li class="com">Commercial</li> + <li class="gov">Military / Government</li> + <li class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</li> + </ul> </div> -<section> +<!-- <section> <p class='subp'> - Standardized paragraph of text about the map. 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. + [section under development] CelebA Dataset ... Standardized paragraph of text about the map. 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. </p> -</section><section> +</section> + --><section> <div class="hr-wave-holder"> @@ -74,16 +77,16 @@ <div class="hr-wave-line hr-wave-line2"></div> </div> - <h2>Supplementary Information</h2> + <h3>Supplementary Information</h3> + </section><section class="applet_container"> - <h3>Citations</h3> + <h3>Dataset Citations</h3> <p> - Citations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates - and indexes research papers. The citations were geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train and/or test machine learning algorithms. + The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. </p> <p> - Add button/link to download CSV + Add [button/link] to download CSV. Add search input field to filter. </p> <div class="applet" data-payload="{"command": "citations"}"></div> diff --git a/site/public/datasets/cofw/index.html b/site/public/datasets/cofw/index.html index eac1f7a6..7ac30579 100644 --- a/site/public/datasets/cofw/index.html +++ b/site/public/datasets/cofw/index.html @@ -43,7 +43,7 @@ To increase the number of training images, and since COFW has the exact same la <p><a href="https://www.cs.cmu.edu/~peiyunh/topdown/">https://www.cs.cmu.edu/~peiyunh/topdown/</a></p> </section><section> - <h3>Information Supply Chain</h3> + <h3>Biometric Trade Routes</h3> <!-- <div class="map-sidebar right-sidebar"> <h3>Legend</h3> @@ -55,28 +55,31 @@ To increase the number of training images, and since COFW has the exact same la </div> --> <p> - To understand how COFW Dataset has been used around the world... - affected global research on computer vision, surveillance, defense, and consumer technology, the and where this dataset has been used the locations of each organization that used or referenced the datast + To help understand how COFW Dataset has been used around the world for commercial, military and academic research; publicly available research citing Caltech Occluded Faces in the Wild is collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal reserach projects at that location. </p> </section> -<section class="applet_container"> +<section class="applet_container fullwidth"> <div class="applet" data-payload="{"command": "map"}"></div> + </section> <div class="caption"> - <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 has been manually verified to show usage of COFW Dataset. + <ul class="map-legend"> + <li class="edu">Academic</li> + <li class="com">Commercial</li> + <li class="gov">Military / Government</li> + <li class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</li> + </ul> </div> -<section> +<!-- <section> <p class='subp'> - Standardized paragraph of text about the map. 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. + [section under development] COFW Dataset ... Standardized paragraph of text about the map. 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. </p> -</section><section> +</section> + --><section> <div class="hr-wave-holder"> @@ -84,16 +87,16 @@ To increase the number of training images, and since COFW has the exact same la <div class="hr-wave-line hr-wave-line2"></div> </div> - <h2>Supplementary Information</h2> + <h3>Supplementary Information</h3> + </section><section class="applet_container"> - <h3>Citations</h3> + <h3>Dataset Citations</h3> <p> - Citations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates - and indexes research papers. The citations were geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train and/or test machine learning algorithms. + The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. </p> <p> - Add button/link to download CSV + Add [button/link] to download CSV. Add search input field to filter. </p> <div class="applet" data-payload="{"command": "citations"}"></div> @@ -101,13 +104,14 @@ To increase the number of training images, and since COFW has the exact same la <h3>Who used COFW Dataset?</h3> <p> - This bar chart presents a ranking of the top countries where citations originated. Mouse over individual columns - to see yearly totals. These charts show at most the top 10 countries. + This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. </p> </section> <section class="applet_container"> +<!-- <div style="position: absolute;top: 0px;right: -55px;width: 180px;font-size: 14px;">Labeled Faces in the Wild Dataset<br><span class="numc" style="font-size: 11px;">20 citations</span> +</div> --> <div class="applet" data-payload="{"command": "chart"}"></div> </section><section><p>TODO</p> <h2>- replace graphic</h2> diff --git a/site/public/datasets/duke_mtmc/index.html b/site/public/datasets/duke_mtmc/index.html index 299331d7..9664181e 100644 --- a/site/public/datasets/duke_mtmc/index.html +++ b/site/public/datasets/duke_mtmc/index.html @@ -4,7 +4,7 @@ <title>MegaPixels</title> <meta charset="utf-8" /> <meta name="author" content="Adam Harvey" /> - <meta name="description" content="Duke MTMC is a dataset of CCTV footage of students at Duke University" /> + <meta name="description" content="Duke MTMC is a dataset of surveillance camera footage of students on Duke University campus" /> <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' /> @@ -26,12 +26,17 @@ </header> <div class="content content-dataset"> - <section class='intro_section' style='background-image: url(https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/duke_mtmc/assets/background.jpg)'><div class='inner'><div class='hero_desc'><span class='bgpad'><span class="dataset-name">Duke MTMC</span> is a dataset of CCTV footage of students at Duke University</span></div><div class='hero_subdesc'><span class='bgpad'>Duke MTMC contains over 2 million video frames and 2,000 unique identities collected from 8 cameras at Duke University campus in March 2014 -</span></div></div></section><section><div class='left-sidebar'><div class='meta'><div><div class='gray'>Collected</div><div>March 19, 2014</div></div><div><div class='gray'>Cameras</div><div>8</div></div><div><div class='gray'>Video Frames</div><div>2,000,000</div></div><div><div class='gray'>Identities</div><div>Over 2,000</div></div><div><div class='gray'>Used for</div><div>Person re-identification, <br>face recognition</div></div><div><div class='gray'>Sector</div><div>Academic</div></div><div><div class='gray'>Website</div><div><a href="http://vision.cs.duke.edu/DukeMTMC/">duke.edu</a></div></div></div></div><h2>Duke Multi-Target, Multi-Camera Tracking Dataset (Duke MTMC)</h2> -<p>(PAGE UNDER DEVELOPMENT)</p> + <section class='intro_section' style='background-image: url(https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/duke_mtmc/assets/background.jpg)'><div class='inner'><div class='hero_desc'><span class='bgpad'><span class="dataset-name">Duke MTMC</span> is a dataset of surveillance camera footage of students on Duke University campus</span></div><div class='hero_subdesc'><span class='bgpad'>Duke MTMC contains over 2 million video frames and 2,000 unique identities collected from 8 HD cameras at Duke University campus in March 2014 +</span></div></div></section><section><div class='left-sidebar'><div class='meta'><div><div class='gray'>Created</div><div>2014</div></div><div><div class='gray'>Identities</div><div>Over 2,700</div></div><div><div class='gray'>Used for</div><div>Face recognition, person re-identification</div></div><div><div class='gray'>Created by</div><div>Computer Science Department, Duke University, Durham, US</div></div><div><div class='gray'>Website</div><div><a href="http://vision.cs.duke.edu/DukeMTMC/">duke.edu</a></div></div></div></div><h2>Duke Multi-Target, Multi-Camera Tracking Dataset (Duke MTMC)</h2> +<p>[ PAGE UNDER DEVELOPMENT ]</p> +<p>Duke MTMC is a dataset of video recorded on Duke University campus during for the purpose of training, evaluating, and improving <em>multi-target multi-camera tracking</em>. The videos were recorded during February and March 2014 and cinclude</p> +<p>Includes a total of 888.8 minutes of video (ind. verified)</p> +<p>"We make available a new data set that has more than 2 million frames and more than 2,700 identities. It consists of 8×85 minutes of 1080p video recorded at 60 frames per second from 8 static cameras deployed on the Duke University campus during periods between lectures, when pedestrian traffic is heavy."</p> +<p>The dataset includes approximately 2,000 annotated identities appearing in 85 hours of video from 8 cameras located throughout Duke University's campus.</p> +</section><section class='images'><div class='image'><img src='https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/duke_mtmc/assets/duke_mtmc_cam5_average_comp.jpg' alt=' Duke MTMC pixel-averaged image of camera #5 is shown with the bounding boxes for each student drawn in white. (c) Adam Harvey'><div class='caption'> Duke MTMC pixel-averaged image of camera #5 is shown with the bounding boxes for each student drawn in white. (c) Adam Harvey</div></div></section><section><p>According to the dataset authors,</p> </section><section> - <h3>Information Supply Chain</h3> + <h3>Biometric Trade Routes</h3> <!-- <div class="map-sidebar right-sidebar"> <h3>Legend</h3> @@ -43,47 +48,44 @@ </div> --> <p> - To understand how Duke MTMC Dataset has been used around the world... - affected global research on computer vision, surveillance, defense, and consumer technology, the and where this dataset has been used the locations of each organization that used or referenced the datast + To help understand how Duke MTMC Dataset has been used around the world for commercial, military and academic research; publicly available research citing Duke Multi-Target, Multi-Camera Tracking Project is collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal reserach projects at that location. </p> </section> -<section class="applet_container"> +<section class="applet_container fullwidth"> <div class="applet" data-payload="{"command": "map"}"></div> + </section> <div class="caption"> - <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 has been manually verified to show usage of Duke MTMC Dataset. + <ul class="map-legend"> + <li class="edu">Academic</li> + <li class="com">Commercial</li> + <li class="gov">Military / Government</li> + <li class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</li> + </ul> </div> -<section> +<!-- <section> <p class='subp'> - Standardized paragraph of text about the map. 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. + [section under development] Duke MTMC Dataset ... Standardized paragraph of text about the map. 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. </p> -</section><section> +</section> + --><section> <h3>Who used Duke MTMC Dataset?</h3> <p> - This bar chart presents a ranking of the top countries where citations originated. Mouse over individual columns - to see yearly totals. These charts show at most the top 10 countries. + This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. </p> </section> <section class="applet_container"> +<!-- <div style="position: absolute;top: 0px;right: -55px;width: 180px;font-size: 14px;">Labeled Faces in the Wild Dataset<br><span class="numc" style="font-size: 11px;">20 citations</span> +</div> --> <div class="applet" data-payload="{"command": "chart"}"></div> -</section><section> - <p> - These pie charts show overall totals based on country and institution type. - </p> - - </section> - -<section class="applet_container"> +</section><section class="applet_container"> <div class="applet" data-payload="{"command": "piechart"}"></div> </section><section> @@ -93,21 +95,23 @@ <div class="hr-wave-line hr-wave-line2"></div> </div> - <h2>Supplementary Information</h2> + <h3>Supplementary Information</h3> + </section><section class="applet_container"> - <h3>Citations</h3> + <h3>Dataset Citations</h3> <p> - Citations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates - and indexes research papers. The citations were geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train and/or test machine learning algorithms. + The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. </p> <p> - Add button/link to download CSV + Add [button/link] to download CSV. Add search input field to filter. </p> <div class="applet" data-payload="{"command": "citations"}"></div> </section><section><h2>Research Notes</h2> <ul> +<li>"We make available a new data set that has more than 2 million frames and more than 2,700 identities. It consists of 8×85 minutes of 1080p video recorded at 60 frames per second from 8 static cameras deployed on the Duke University campus during periods between lectures, when pedestrian traffic is heavy." - 27a2fad58dd8727e280f97036e0d2bc55ef5424c</li> +<li>"This work was supported in part by the EPSRC Programme Grant (FACER2VM) EP/N007743/1, EPSRC/dstl/MURI project EP/R018456/1, the National Natural Science Foundation of China (61373055, 61672265, 61602390, 61532009, 61571313), Chinese Ministry of Education (Z2015101), Science and Technology Department of Sichuan Province (2017RZ0009 and 2017FZ0029), Education Department of Sichuan Province (15ZB0130), the Open Research Fund from Province Key Laboratory of Xihua University (szjj2015-056) and the NVIDIA GPU Grant Program." - ec9c20ed6cce15e9b63ac96bb5a6d55e69661e0b</li> <li>"DukeMTMC aims to accelerate advances in multi-target multi-camera tracking. It provides a tracking system that works within and across cameras, a new large scale HD video data set recorded by 8 synchronized cameras with more than 7,000 single camera trajectories and over 2,000 unique identities, and a new performance evaluation method that measures how often a system is correct about who is where"</li> <li><p>DukeMTMC is a new, manually annotated, calibrated, multi-camera data set recorded outdoors on the Duke University campus with 8 synchronized cameras. It consists of:</p> <p>8 static cameras x 85 minutes of 1080p 60 fps video diff --git a/site/public/datasets/hrt_transgender/index.html b/site/public/datasets/hrt_transgender/index.html index e38e134b..ed36abb5 100644 --- a/site/public/datasets/hrt_transgender/index.html +++ b/site/public/datasets/hrt_transgender/index.html @@ -32,26 +32,20 @@ <h3>Who used HRT Transgender?</h3> <p> - This bar chart presents a ranking of the top countries where citations originated. Mouse over individual columns - to see yearly totals. These charts show at most the top 10 countries. + This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. </p> </section> <section class="applet_container"> +<!-- <div style="position: absolute;top: 0px;right: -55px;width: 180px;font-size: 14px;">Labeled Faces in the Wild Dataset<br><span class="numc" style="font-size: 11px;">20 citations</span> +</div> --> <div class="applet" data-payload="{"command": "chart"}"></div> -</section><section> - <p> - These pie charts show overall totals based on country and institution type. - </p> - - </section> - -<section class="applet_container"> +</section><section class="applet_container"> <div class="applet" data-payload="{"command": "piechart"}"></div> </section><section> - <h3>Information Supply Chain</h3> + <h3>Biometric Trade Routes</h3> <!-- <div class="map-sidebar right-sidebar"> <h3>Legend</h3> @@ -63,28 +57,31 @@ </div> --> <p> - To understand how HRT Transgender has been used around the world... - affected global research on computer vision, surveillance, defense, and consumer technology, the and where this dataset has been used the locations of each organization that used or referenced the datast + To help understand how HRT Transgender has been used around the world for commercial, military and academic research; publicly available research citing HRT Transgender Dataset is collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal reserach projects at that location. </p> </section> -<section class="applet_container"> +<section class="applet_container fullwidth"> <div class="applet" data-payload="{"command": "map"}"></div> + </section> <div class="caption"> - <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 has been manually verified to show usage of HRT Transgender. + <ul class="map-legend"> + <li class="edu">Academic</li> + <li class="com">Commercial</li> + <li class="gov">Military / Government</li> + <li class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</li> + </ul> </div> -<section> +<!-- <section> <p class='subp'> - Standardized paragraph of text about the map. 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. + [section under development] HRT Transgender ... Standardized paragraph of text about the map. 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. </p> -</section><section> +</section> + --><section> <div class="hr-wave-holder"> @@ -92,16 +89,16 @@ <div class="hr-wave-line hr-wave-line2"></div> </div> - <h2>Supplementary Information</h2> + <h3>Supplementary Information</h3> + </section><section class="applet_container"> - <h3>Citations</h3> + <h3>Dataset Citations</h3> <p> - Citations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates - and indexes research papers. The citations were geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train and/or test machine learning algorithms. + The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. </p> <p> - Add button/link to download CSV + Add [button/link] to download CSV. Add search input field to filter. </p> <div class="applet" data-payload="{"command": "citations"}"></div> diff --git a/site/public/datasets/index.html b/site/public/datasets/index.html index f618e86b..1d2630e1 100644 --- a/site/public/datasets/index.html +++ b/site/public/datasets/index.html @@ -28,7 +28,7 @@ <section><h1>Facial Recognition Datasets</h1> -<h3>Survey</h3> +<p>Explore publicly available facial recognition datasets. More datasets will be added throughout 2019.</p> </section> <section class='applet_container autosize'><div class='applet' data-payload='{"command":"dataset_list"}'></div></section> @@ -85,6 +85,18 @@ </div> </a> + <a href="/datasets/msceleb/" style="background-image: url(https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/msceleb/assets/index.jpg)"> + <div class="dataset"> + <span class='title'>MS Celeb</span> + <div class='fields'> + <div class='year visible'><span>2016</span></div> + <div class='purpose'><span>face recognition</span></div> + <div class='images'><span>1,000,000 images</span></div> + <div class='identities'><span>100,000 </span></div> + </div> + </div> + </a> + <a href="/datasets/pipa/" style="background-image: url(https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/pipa/assets/index.jpg)"> <div class="dataset"> <span class='title'>People in Photo Albums</span> diff --git a/site/public/datasets/lfw/index.html b/site/public/datasets/lfw/index.html index b4923877..22384d77 100644 --- a/site/public/datasets/lfw/index.html +++ b/site/public/datasets/lfw/index.html @@ -46,7 +46,7 @@ <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>Information Supply Chain</h3> + <h3>Biometric Trade Routes</h3> <!-- <div class="map-sidebar right-sidebar"> <h3>Legend</h3> @@ -58,47 +58,44 @@ </div> --> <p> - To understand how LFW has been used around the world... - affected global research on computer vision, surveillance, defense, and consumer technology, the and where this dataset has been used the locations of each organization that used or referenced the datast + To help understand how LFW has been used around the world for commercial, military and academic research; publicly available research citing Labeled Faces in the Wild is collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal reserach projects at that location. </p> </section> -<section class="applet_container"> +<section class="applet_container fullwidth"> <div class="applet" data-payload="{"command": "map"}"></div> + </section> <div class="caption"> - <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 has been manually verified to show usage of LFW. + <ul class="map-legend"> + <li class="edu">Academic</li> + <li class="com">Commercial</li> + <li class="gov">Military / Government</li> + <li class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</li> + </ul> </div> -<section> +<!-- <section> <p class='subp'> - Standardized paragraph of text about the map. 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. + [section under development] LFW ... Standardized paragraph of text about the map. 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. </p> -</section><section> +</section> + --><section> <h3>Who used LFW?</h3> <p> - This bar chart presents a ranking of the top countries where citations originated. Mouse over individual columns - to see yearly totals. These charts show at most the top 10 countries. + This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. </p> </section> <section class="applet_container"> +<!-- <div style="position: absolute;top: 0px;right: -55px;width: 180px;font-size: 14px;">Labeled Faces in the Wild Dataset<br><span class="numc" style="font-size: 11px;">20 citations</span> +</div> --> <div class="applet" data-payload="{"command": "chart"}"></div> -</section><section> - <p> - These pie charts show overall totals based on country and institution type. - </p> - - </section> - -<section class="applet_container"> +</section><section class="applet_container"> <div class="applet" data-payload="{"command": "piechart"}"></div> </section><section> @@ -108,16 +105,16 @@ <div class="hr-wave-line hr-wave-line2"></div> </div> - <h2>Supplementary Information</h2> + <h3>Supplementary Information</h3> + </section><section class="applet_container"> - <h3>Citations</h3> + <h3>Dataset Citations</h3> <p> - Citations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates - and indexes research papers. The citations were geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train and/or test machine learning algorithms. + The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. </p> <p> - Add button/link to download CSV + Add [button/link] to download CSV. Add search input field to filter. </p> <div class="applet" data-payload="{"command": "citations"}"></div> diff --git a/site/public/datasets/market_1501/index.html b/site/public/datasets/market_1501/index.html index a80c23fa..9a05d20e 100644 --- a/site/public/datasets/market_1501/index.html +++ b/site/public/datasets/market_1501/index.html @@ -31,7 +31,7 @@ <p>(PAGE UNDER DEVELOPMENT)</p> </section><section> - <h3>Information Supply Chain</h3> + <h3>Biometric Trade Routes</h3> <!-- <div class="map-sidebar right-sidebar"> <h3>Legend</h3> @@ -43,28 +43,31 @@ </div> --> <p> - To understand how Market 1501 has been used around the world... - affected global research on computer vision, surveillance, defense, and consumer technology, the and where this dataset has been used the locations of each organization that used or referenced the datast + To help understand how Market 1501 has been used around the world for commercial, military and academic research; publicly available research citing Market 1501 Dataset is collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal reserach projects at that location. </p> </section> -<section class="applet_container"> +<section class="applet_container fullwidth"> <div class="applet" data-payload="{"command": "map"}"></div> + </section> <div class="caption"> - <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 has been manually verified to show usage of Market 1501. + <ul class="map-legend"> + <li class="edu">Academic</li> + <li class="com">Commercial</li> + <li class="gov">Military / Government</li> + <li class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</li> + </ul> </div> -<section> +<!-- <section> <p class='subp'> - Standardized paragraph of text about the map. 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. + [section under development] Market 1501 ... Standardized paragraph of text about the map. 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. </p> -</section><section> +</section> + --><section> <div class="hr-wave-holder"> @@ -72,16 +75,16 @@ <div class="hr-wave-line hr-wave-line2"></div> </div> - <h2>Supplementary Information</h2> + <h3>Supplementary Information</h3> + </section><section class="applet_container"> - <h3>Citations</h3> + <h3>Dataset Citations</h3> <p> - Citations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates - and indexes research papers. The citations were geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train and/or test machine learning algorithms. + The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. </p> <p> - Add button/link to download CSV + Add [button/link] to download CSV. Add search input field to filter. </p> <div class="applet" data-payload="{"command": "citations"}"></div> diff --git a/site/public/datasets/msceleb/index.html b/site/public/datasets/msceleb/index.html new file mode 100644 index 00000000..0ddf0c68 --- /dev/null +++ b/site/public/datasets/msceleb/index.html @@ -0,0 +1,136 @@ +<!doctype html> +<html> +<head> + <title>MegaPixels</title> + <meta charset="utf-8" /> + <meta name="author" content="Adam Harvey" /> + <meta name="description" content="MS Celeb is a dataset of web images used for training and evaluating face recognition 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="/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/msceleb/assets/background.jpg)'><div class='inner'><div class='hero_desc'><span class='bgpad'>MS Celeb is a dataset of web images used for training and evaluating face recognition algorithms</span></div><div class='hero_subdesc'><span class='bgpad'>The MS Celeb dataset includes over 10,000,000 images and 93,000 identities of semi-public figures collected using the Bing search engine +</span></div></div></section><section><div class='left-sidebar'><div class='meta'><div><div class='gray'>Published</div><div>TBD</div></div><div><div class='gray'>Images</div><div>TBD</div></div><div><div class='gray'>Faces</div><div>TBD</div></div><div><div class='gray'>Created by</div><div>TBD</div></div></div></div><h2>Microsoft Celeb Dataset (MS Celeb)</h2> +<p>(PAGE UNDER DEVELOPMENT)</p> +<p>At vero eos et accusamus et iusto odio dignissimos ducimus, qui blanditiis praesentium voluptatum deleniti atque corrupti, quos dolores et quas molestias excepturi sint, obcaecati cupiditate non-provident, similique sunt in culpa, qui officia deserunt mollitia animi, id est laborum et dolorum fuga. Et harum quidem rerum facilis est et expedita distinctio.</p> +<p>Nam libero tempore, cum soluta nobis est eligendi optio, cumque nihil impedit, quo minus id, quod maxime placeat, facere possimus, omnis voluptas assumenda est, omnis dolor repellendus. Temporibus autem quibusdam et aut officiis debitis aut rerum necessitatibus saepe eveniet, ut et voluptates repudiandae sint et molestiae non-recusandae. Itaque earum rerum hic tenetur a sapiente delectus, ut aut reiciendis voluptatibus maiores alias consequatur aut perferendis doloribus asperiores repellat</p> +</section><section> + <h3>Who used MsCeleb?</h3> + + <p> + This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. + </p> + + </section> + +<section class="applet_container"> +<!-- <div style="position: absolute;top: 0px;right: -55px;width: 180px;font-size: 14px;">Labeled Faces in the Wild Dataset<br><span class="numc" style="font-size: 11px;">20 citations</span> +</div> --> + <div class="applet" data-payload="{"command": "chart"}"></div> +</section><section class="applet_container"> + <div class="applet" data-payload="{"command": "piechart"}"></div> +</section><section> + + <h3>Biometric Trade Routes</h3> +<!-- + <div class="map-sidebar right-sidebar"> + <h3>Legend</h3> + <ul> + <li><span style="color: #f2f293">■</span> Industry</li> + <li><span style="color: #f30000">■</span> Academic</li> + <li><span style="color: #3264f6">■</span> Government</li> + </ul> + </div> + --> + <p> + To help understand how MsCeleb has been used around the world for commercial, military and academic research; publicly available research citing Microsoft Celebrity Dataset is collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal reserach projects at that location. + </p> + + </section> + +<section class="applet_container fullwidth"> + <div class="applet" data-payload="{"command": "map"}"></div> + +</section> + +<div class="caption"> + <ul class="map-legend"> + <li class="edu">Academic</li> + <li class="com">Commercial</li> + <li class="gov">Military / Government</li> + <li class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</li> + </ul> +</div> + +<!-- <section> + <p class='subp'> + [section under development] MsCeleb ... Standardized paragraph of text about the map. 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. + </p> +</section> + --><section><p>Add more analysis here</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> + + <h3>Supplementary Information</h3> + +</section><section class="applet_container"> + + <h3>Dataset Citations</h3> + <p> + The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. + </p> + <p> + Add [button/link] to download CSV. Add search input field to filter. + </p> + + <div class="applet" data-payload="{"command": "citations"}"></div> +</section><section><h3>Additional Information</h3> +<ul> +<li>The dataset author spoke about his research at the CVPR conference in 2016 <a href="https://www.youtube.com/watch?v=Nl2fBKxwusQ">https://www.youtube.com/watch?v=Nl2fBKxwusQ</a></li> +</ul> +</section><section><ul class="footnotes"><li><a name="[^readme]" class="footnote_shim"></a><span class="backlinks"></span><p>"readme.txt" <a href="https://exhibits.stanford.edu/data/catalog/sx925dc9385">https://exhibits.stanford.edu/data/catalog/sx925dc9385</a>.</p> +</li><li><a name="[^localized_region_context]" class="footnote_shim"></a><span class="backlinks"></span><p>Li, Y. and Dou, Y. and Liu, X. and Li, T. Localized Region Context and Object Feature Fusion for People Head Detection. ICIP16 Proceedings. 2016. Pages 594-598.</p> +</li><li><a name="[^replacement_algorithm]" class="footnote_shim"></a><span class="backlinks"></span><p>Zhao. X, Wang Y, Dou, Y. A Replacement Algorithm of Non-Maximum Suppression Base on Graph Clustering.</p> +</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 ©2017-19 Adam R. Harvey / + <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/pipa/index.html b/site/public/datasets/pipa/index.html index 62754070..9e7eb164 100644 --- a/site/public/datasets/pipa/index.html +++ b/site/public/datasets/pipa/index.html @@ -31,7 +31,7 @@ <p>(PAGE UNDER DEVELOPMENT)</p> </section><section> - <h3>Information Supply Chain</h3> + <h3>Biometric Trade Routes</h3> <!-- <div class="map-sidebar right-sidebar"> <h3>Legend</h3> @@ -43,28 +43,31 @@ </div> --> <p> - To understand how PIPA Dataset has been used around the world... - affected global research on computer vision, surveillance, defense, and consumer technology, the and where this dataset has been used the locations of each organization that used or referenced the datast + To help understand how PIPA Dataset has been used around the world for commercial, military and academic research; publicly available research citing People in Photo Albums Dataset is collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal reserach projects at that location. </p> </section> -<section class="applet_container"> +<section class="applet_container fullwidth"> <div class="applet" data-payload="{"command": "map"}"></div> + </section> <div class="caption"> - <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 has been manually verified to show usage of PIPA Dataset. + <ul class="map-legend"> + <li class="edu">Academic</li> + <li class="com">Commercial</li> + <li class="gov">Military / Government</li> + <li class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</li> + </ul> </div> -<section> +<!-- <section> <p class='subp'> - Standardized paragraph of text about the map. 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. + [section under development] PIPA Dataset ... Standardized paragraph of text about the map. 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. </p> -</section><section> +</section> + --><section> <div class="hr-wave-holder"> @@ -72,16 +75,16 @@ <div class="hr-wave-line hr-wave-line2"></div> </div> - <h2>Supplementary Information</h2> + <h3>Supplementary Information</h3> + </section><section class="applet_container"> - <h3>Citations</h3> + <h3>Dataset Citations</h3> <p> - Citations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates - and indexes research papers. The citations were geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train and/or test machine learning algorithms. + The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. </p> <p> - Add button/link to download CSV + Add [button/link] to download CSV. Add search input field to filter. </p> <div class="applet" data-payload="{"command": "citations"}"></div> diff --git a/site/public/datasets/uccs/index.html b/site/public/datasets/uccs/index.html index 08000c6e..2477c9f8 100644 --- a/site/public/datasets/uccs/index.html +++ b/site/public/datasets/uccs/index.html @@ -4,7 +4,7 @@ <title>MegaPixels</title> <meta charset="utf-8" /> <meta name="author" content="Adam Harvey" /> - <meta name="description" content="Unconstrained College Students (UCCS) is a dataset of images ..." /> + <meta name="description" content="Unconstrained College Students (UCCS) is a dataset of long-range surveillance photos of students taken without their knowledge" /> <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' /> @@ -26,12 +26,12 @@ </header> <div class="content content-dataset"> - <section class='intro_section' style='background-image: url(https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/uccs/assets/background.jpg)'><div class='inner'><div class='hero_desc'><span class='bgpad'><span class="dataset-name">Unconstrained College Students (UCCS)</span> is a dataset of images ...</span></div><div class='hero_subdesc'><span class='bgpad'>The UCCS dataset includes ... -</span></div></div></section><section><div class='left-sidebar'><div class='meta'><div><div class='gray'>Collected</div><div>TBD</div></div><div><div class='gray'>Published</div><div>TBD</div></div><div><div class='gray'>Images</div><div>TBD</div></div><div><div class='gray'>Faces</div><div>TBD</div></div></div></div><h2>Unconstrained College Students ...</h2> + <section class='intro_section' style='background-image: url(https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/uccs/assets/background.jpg)'><div class='inner'><div class='hero_desc'><span class='bgpad'><span class="dataset-name">Unconstrained College Students (UCCS)</span> is a dataset of long-range surveillance photos of students taken without their knowledge</span></div><div class='hero_subdesc'><span class='bgpad'>The UCCS dataset includes 16,149 images and 1,732 identities of students at University of Colorado Colorado Springs campus and is used for face recognition and face detection +</span></div></div></section><section><div class='left-sidebar'><div class='meta'><div><div class='gray'>Published</div><div>2018</div></div><div><div class='gray'>Images</div><div>16,149</div></div><div><div class='gray'>Identities</div><div>1,732</div></div><div><div class='gray'>Used for</div><div>Face recognition, face detection</div></div><div><div class='gray'>Created by</div><div>Unviversity of Colorado Colorado Springs (US)</div></div><div><div class='gray'>Funded by</div><div>ODNI, IARPA, ONR MURI, Amry SBIR, SOCOM SBIR</div></div><div><div class='gray'>Website</div><div><a href="https://vast.uccs.edu/Opensetface/">vast.uccs.edu</a></div></div></div></div><h2>Unconstrained College Students ...</h2> <p>(PAGE UNDER DEVELOPMENT)</p> -</section><section> +</section><section class='images'><div class='image'><img src='https://nyc3.digitaloceanspaces.com/megapixels/v1/datasets/uccs/assets/uccs_mean_bboxes_comp.jpg' alt=' The pixel-average of all Uconstrained College Students images is shown with all 51,838 face annotations. (c) Adam Harvey'><div class='caption'> The pixel-average of all Uconstrained College Students images is shown with all 51,838 face annotations. (c) Adam Harvey</div></div></section><section> - <h3>Information Supply Chain</h3> + <h3>Biometric Trade Routes</h3> <!-- <div class="map-sidebar right-sidebar"> <h3>Legend</h3> @@ -43,47 +43,44 @@ </div> --> <p> - To understand how UCCS has been used around the world... - affected global research on computer vision, surveillance, defense, and consumer technology, the and where this dataset has been used the locations of each organization that used or referenced the datast + To help understand how UCCS has been used around the world for commercial, military and academic research; publicly available research citing UnConstrained College Students Dataset is collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal reserach projects at that location. </p> </section> -<section class="applet_container"> +<section class="applet_container fullwidth"> <div class="applet" data-payload="{"command": "map"}"></div> + </section> <div class="caption"> - <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 has been manually verified to show usage of UCCS. + <ul class="map-legend"> + <li class="edu">Academic</li> + <li class="com">Commercial</li> + <li class="gov">Military / Government</li> + <li class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</li> + </ul> </div> -<section> +<!-- <section> <p class='subp'> - Standardized paragraph of text about the map. 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. + [section under development] UCCS ... Standardized paragraph of text about the map. 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. </p> -</section><section> +</section> + --><section> <h3>Who used UCCS?</h3> <p> - This bar chart presents a ranking of the top countries where citations originated. Mouse over individual columns - to see yearly totals. These charts show at most the top 10 countries. + This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. </p> </section> <section class="applet_container"> +<!-- <div style="position: absolute;top: 0px;right: -55px;width: 180px;font-size: 14px;">Labeled Faces in the Wild Dataset<br><span class="numc" style="font-size: 11px;">20 citations</span> +</div> --> <div class="applet" data-payload="{"command": "chart"}"></div> -</section><section> - <p> - These pie charts show overall totals based on country and institution type. - </p> - - </section> - -<section class="applet_container"> +</section><section class="applet_container"> <div class="applet" data-payload="{"command": "piechart"}"></div> </section><section> @@ -93,16 +90,16 @@ <div class="hr-wave-line hr-wave-line2"></div> </div> - <h2>Supplementary Information</h2> + <h3>Supplementary Information</h3> + </section><section class="applet_container"> - <h3>Citations</h3> + <h3>Dataset Citations</h3> <p> - Citations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates - and indexes research papers. The citations were geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train and/or test machine learning algorithms. + The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. </p> <p> - Add button/link to download CSV + Add [button/link] to download CSV. Add search input field to filter. </p> <div class="applet" data-payload="{"command": "citations"}"></div> @@ -119,6 +116,11 @@ <li>ODNI (Office of Director of National Intelligence)</li> <li>IARPA (Intelligence Advance Research Projects Activity) R&D contract 2014-14071600012</li> </ul> +<p>" In most face detection/recognition datasets, the majority of images are “posed”, i.e. the subjects know they are being photographed, and/or the images are selected for publication in public media. Hence, blurry, occluded and badly illuminated images are generally uncommon in these datasets. In addition, most of these challenges are close-set, i.e. the list of subjects in the gallery is the same as the one used for testing.</p> +<p>This challenge explores more unconstrained data, by introducing the new UnConstrained College Students (UCCS) dataset, where subjects are photographed using a long-range high-resolution surveillance camera without their knowledge. Faces inside these images are of various poses, and varied levels of blurriness and occlusion. The challenge also creates an open set recognition problem, where unknown people will be seen during testing and must be rejected.</p> +<p>With this challenge, we hope to foster face detection and recognition research towards surveillance applications that are becoming more popular and more required nowadays, and where no automatic recognition algorithm has proven to be useful yet.</p> +<p>UnConstrained College Students (UCCS) Dataset</p> +<p>The UCCS dataset was collected over several months using Canon 7D camera fitted with Sigma 800mm F5.6 EX APO DG HSM lens, taking images at one frame per second, during times when many students were walking on the sidewalk. "</p> <div class="footnotes"> <hr> <ol><li id="fn-funding_sb"><p>Sapkota, Archana and Boult, Terrance. "Large Scale Unconstrained Open Set Face Database." 2013.<a href="#fnref-funding_sb" class="footnote">↩</a></p></li> diff --git a/site/public/datasets/viper/index.html b/site/public/datasets/viper/index.html index 5acd0845..e94568a3 100644 --- a/site/public/datasets/viper/index.html +++ b/site/public/datasets/viper/index.html @@ -35,26 +35,20 @@ <h3>Who used VIPeR?</h3> <p> - This bar chart presents a ranking of the top countries where citations originated. Mouse over individual columns - to see yearly totals. These charts show at most the top 10 countries. + This bar chart presents a ranking of the top countries where dataset citations originated. Mouse over individual columns to see yearly totals. These charts show at most the top 10 countries. </p> </section> <section class="applet_container"> +<!-- <div style="position: absolute;top: 0px;right: -55px;width: 180px;font-size: 14px;">Labeled Faces in the Wild Dataset<br><span class="numc" style="font-size: 11px;">20 citations</span> +</div> --> <div class="applet" data-payload="{"command": "chart"}"></div> -</section><section> - <p> - These pie charts show overall totals based on country and institution type. - </p> - - </section> - -<section class="applet_container"> +</section><section class="applet_container"> <div class="applet" data-payload="{"command": "piechart"}"></div> </section><section> - <h3>Information Supply Chain</h3> + <h3>Biometric Trade Routes</h3> <!-- <div class="map-sidebar right-sidebar"> <h3>Legend</h3> @@ -66,28 +60,31 @@ </div> --> <p> - To understand how VIPeR has been used around the world... - affected global research on computer vision, surveillance, defense, and consumer technology, the and where this dataset has been used the locations of each organization that used or referenced the datast + To help understand how VIPeR has been used around the world for commercial, military and academic research; publicly available research citing Viewpoint Invariant Pedestrian Recognition is collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal reserach projects at that location. </p> </section> -<section class="applet_container"> +<section class="applet_container fullwidth"> <div class="applet" data-payload="{"command": "map"}"></div> + </section> <div class="caption"> - <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 has been manually verified to show usage of VIPeR. + <ul class="map-legend"> + <li class="edu">Academic</li> + <li class="com">Commercial</li> + <li class="gov">Military / Government</li> + <li class="source">Citation data is collected using <a href="https://semanticscholar.org" target="_blank">SemanticScholar.org</a> then dataset usage verified and geolocated.</li> + </ul> </div> -<section> +<!-- <section> <p class='subp'> - Standardized paragraph of text about the map. 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. + [section under development] VIPeR ... Standardized paragraph of text about the map. 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. </p> -</section><section> +</section> + --><section> <div class="hr-wave-holder"> @@ -95,16 +92,16 @@ <div class="hr-wave-line hr-wave-line2"></div> </div> - <h2>Supplementary Information</h2> + <h3>Supplementary Information</h3> + </section><section class="applet_container"> - <h3>Citations</h3> + <h3>Dataset Citations</h3> <p> - Citations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates - and indexes research papers. The citations were geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train and/or test machine learning algorithms. + The dataset citations used in the visualizations were collected from <a href="https://www.semanticscholar.org">Semantic Scholar</a>, a website which aggregates and indexes research papers. Each citation was geocoded using names of institutions found in the PDF front matter, or as listed on other resources. These papers have been manually verified to show that researchers downloaded and used the dataset to train or test machine learning algorithms. </p> <p> - Add button/link to download CSV + Add [button/link] to download CSV. Add search input field to filter. </p> <div class="applet" data-payload="{"command": "citations"}"></div> diff --git a/site/public/research/01_from_1_to_100_pixels/index.html b/site/public/research/01_from_1_to_100_pixels/index.html index c91d17ad..37fc367f 100644 --- a/site/public/research/01_from_1_to_100_pixels/index.html +++ b/site/public/research/01_from_1_to_100_pixels/index.html @@ -80,6 +80,38 @@ <li>"Note that we only keep the images with a minimal side length of 80 pixels." and "a face will be labeled as “Ignore” if it is very difficult to be detected due to blurring, severe deformation and unrecognizable eyes, or the side length of its bounding box is less than 32 pixels." Ge_Detecting_Masked_Faces_CVPR_2017_paper.pdf </li> <li>IBM DiF: "Faces with region size less than 50x50 or inter-ocular distance of less than 30 pixels were discarded. Faces with non-frontal pose, or anything beyond being slightly tilted to the left or the right, were also discarded."</li> </ul> +<p>As the resolution +formatted as rectangular databases of 16 bit RGB-tuples or 8 bit grayscale values</p> +<p>To consider how visual privacy applies to real world surveillance situations, the first</p> +<p>A single 8-bit grayscale pixel with 256 values is enough to represent the entire alphabet <code>a-Z0-9</code> with room to spare.</p> +<p>A 2x2 pixels contains</p> +<p>Using no more than a 42 pixel (6x7 image) face image researchers [cite] were able to correctly distinguish between a group of 50 people. Yet</p> +<p>The likely outcome of face recognition research is that more data is needed to improve. Indeed, resolution is the determining factor for all biometric systems, both as training data to increase</p> +<p>Pixels, typically considered the buiding blocks of images and vidoes, can also be plotted as a graph of sensor values corresponding to the intensity of RGB-calibrated sensors.</p> +<p>Wi-Fi and cameras presents elevated risks for transmitting videos and image documentation from conflict zones, high-risk situations, or even sharing on social media. How can new developments in computer vision also be used in reverse, as a counter-forensic tool, to minimize an individual's privacy risk?</p> +<p>As the global Internet becomes increasingly effecient at turning the Internet into a giant dataset for machine learning, forensics, and data analysing, it would be prudent to also consider tools for decreasing the resolution. The Visual Defense module is just that. What are new ways to minimize the adverse effects of surveillance by dulling the blade. For example, a researcher paper showed that by decreasing a face size to 12x16 it was possible to do 98% accuracy with 50 people. This is clearly an example of</p> +<p>This research module, tentatively called Visual Defense Tools, aims to explore the</p> +<h3>Prior Research</h3> +<ul> +<li>MPI visual privacy advisor</li> +<li>NIST: super resolution</li> +<li>YouTube blur tool</li> +<li>WITNESS: blur tool</li> +<li>Pixellated text </li> +<li>CV Dazzle</li> +<li>Bellingcat guide to geolocation</li> +<li>Peng! magic passport</li> +</ul> +<h3>Notes</h3> +<ul> +<li>In China, out of the approximately 200 million surveillance cameras only about 15% have enough resolution for face recognition. </li> +<li>In Apple's FaceID security guide, the probability of someone else's face unlocking your phone is 1 out of 1,000,000. </li> +<li>In England, the Metropolitan Police reported a false-positive match rate of 98% when attempting to use face recognition to locate wanted criminals. </li> +<li>In a face recognition trial at Berlin's Sudkreuz station, the false-match rate was 20%. </li> +</ul> +<p>What all 3 examples illustrate is that face recognition is anything but absolute. In a 2017 talk, Jason Matheny the former directory of IARPA, admitted the face recognition is so brittle it can be subverted by using a magic marker and drawing "a few dots on your forehead". In fact face recognition is a misleading term. Face recognition is search engine for faces that can only ever show you the mos likely match. This presents real a real threat to privacy and lends</p> +<p>Globally, iPhone users unwittingly agree to 1/1,000,000 probably +relying on FaceID and TouchID to protect their information agree to a</p> <div class="footnotes"> <hr> <ol><li id="fn-nist_sres"><p>NIST 906932. Performance Assessment of Face Recognition Using Super-Resolution. Shuowen Hu, Robert Maschal, S. Susan Young, Tsai Hong Hong, Jonathon P. Phillips<a href="#fnref-nist_sres" class="footnote">↩</a></p></li> diff --git a/site/public/research/02_what_computers_can_see/index.html b/site/public/research/02_what_computers_can_see/index.html index 9389bf84..0fce1373 100644 --- a/site/public/research/02_what_computers_can_see/index.html +++ b/site/public/research/02_what_computers_can_see/index.html @@ -126,6 +126,7 @@ <li>Wearing Necktie</li> <li>Wearing Necklace</li> </ul> +<p>for i in {1..9};do wget <a href="http://visiond1.cs.umbc.edu/webpage/codedata/ADLdataset/ADL_videos/P_0$i.MP4;done;for">http://visiond1.cs.umbc.edu/webpage/codedata/ADLdataset/ADL_videos/P_0$i.MP4;done;for</a> i in {10..20}; do wget <a href="http://visiond1.cs.umbc.edu/webpage/codedata/ADLdataset/ADL_videos/P_$i.MP4;done">http://visiond1.cs.umbc.edu/webpage/codedata/ADLdataset/ADL_videos/P_$i.MP4;done</a></p> <h2>From Market 1501</h2> <p>The 27 attributes are:</p> <table> @@ -269,6 +270,24 @@ Visibility boolean for each keypoint Region annotations (upper clothes, lower clothes, dress, socks, shoes, hands, gloves, neck, face, hair, hat, sunglasses, bag, occluder) Body type (male, female or child)</p> <p>source: <a href="https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/shape/h3d/">https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/shape/h3d/</a></p> +<h2>From Leeds Sports Pose</h2> +<p>=INDEX(A2:A9,MATCH(datasets!D1,B2:B9,0)) +=VLOOKUP(A2, datasets!A:J, 7, FALSE)</p> +<p>Right ankle +Right knee +Right hip +Left hip +Left knee +Left ankle +Right wrist +Right elbow +Right shoulder +Left shoulder +Left elbow +Left wrist +Neck +Head top</p> +<p>source: <a href="http://web.archive.org/web/20170915023005/sam.johnson.io/research/lsp.html">http://web.archive.org/web/20170915023005/sam.johnson.io/research/lsp.html</a></p> </section> </div> @@ -1,43 +1,35 @@ # TODO -## Paper Review - -- build and deploy paper verification tool to publicly (but password protected) URL -- add field for name (no site registration needed) -- user can maually add their name, so it can be used for double-verification, accountability -- top priority datasets will probably be: DukeMTMC, UCCS, MegaFace, Brainwash, HRT Transgender, IJB-C, VGG Face 2, MS Celeb, Pipa, - ## Splash - AH: work on CTA overlay design -- AH: render one head from each activate dataset +- AH: render heads from IJB-C, and MS Celeb +- AH: create psuedo-ranomized list of names from combined datasets for word/name cloud - JL: add "Name \n Dataset Name" below head? and make linkable to dataset? - change animation to be only colored vertices <---> colored landmarks - add scripted slow-slow-zoom out effect ## Datasets Index -- AH: add more datasets -- AH: finalize intro text +- AH: add dataset analysis for MS Celeb, Duke, UCCS, IJB-C, Brainwash, HRT Transgender +- AH: increase sizes of dataset thumbnails +- AH: add license information to each dataset page ## Datasets -- AH: Try creating another google doc to manually review each citation and send to FT to maybe help with review +Higher priority: + - AH: finalize text for map include, beta disclaimer - JL: add download (button) and search option for CSV? or link to github - JL: remove pointer rollover on tabulators - JL: change PDF url to only show domain (ie https:/arxiv.org/12345/ --> arxiv.org) -- JL: check footnotes (it shows an 'a' next to the numbers on bottom. is this right?) -- JL: Add 'sticky' title appear in header zone when scrolling down page (like NYT) -- JL: add total number of citations next to country "China (1,234)" -- JL: possible to add country with most citations in the "Who Used Dataset" paragraph? -- JL: time permitting, add C3 Pie Graph include: - - one pie graph for citations by country - - one pie graph for citations by sector (academic, commericial, military) -- Integrate verified citations and show only verified citations -- JL/AH: integrate new sidebar JSON or CSV data (AH, working on this...) -- NB: skipping synthetic faces for now +- JL/AH: integrate new sidebar JSON or CSV data (AH, working on this...) to show dataset statistics + +Lower priority: + +- JL: Add 'sticky' title with Dataset appear in header zone when scrolling down page (like NYT) + ## About - AH: update bio images |
