From 57fba037d519e45488599288f7753cb7a3cd32aa Mon Sep 17 00:00:00 2001 From: adamhrv Date: Fri, 12 Apr 2019 09:09:13 +0200 Subject: merging --- site/public/about/faq/index.html | 59 ---- site/public/about/index.html | 93 ------- site/public/about/legal/index.html | 85 ------ site/public/about/press/index.html | 58 ---- .../datasets/50_people_one_question/index.html | 114 -------- site/public/datasets/afad/index.html | 127 --------- site/public/datasets/aflw/index.html | 53 ---- site/public/datasets/brainwash/index.html | 146 ---------- site/public/datasets/caltech_10k/index.html | 124 --------- site/public/datasets/celeba/index.html | 126 --------- site/public/datasets/cofw/index.html | 179 ------------ site/public/datasets/duke_mtmc/index.html | 144 ---------- site/public/datasets/facebook/index.html | 54 ---- site/public/datasets/feret/index.html | 87 ------ site/public/datasets/hrt_transgender/index.html | 67 ----- site/public/datasets/index.html | 145 ---------- site/public/datasets/lfpw/index.html | 116 -------- site/public/datasets/lfw/index.html | 166 ----------- site/public/datasets/market_1501/index.html | 132 --------- site/public/datasets/msceleb/index.html | 139 --------- site/public/datasets/oxford_town_centre/index.html | 146 ---------- site/public/datasets/pipa/index.html | 120 -------- site/public/datasets/pubfig/index.html | 117 -------- site/public/datasets/uccs/index.html | 255 ----------------- site/public/datasets/vgg_face2/index.html | 142 ---------- site/public/datasets/viper/index.html | 122 -------- .../public/datasets/youtube_celebrities/index.html | 113 -------- site/public/index.html | 39 --- site/public/info/index.html | 50 ---- site/public/research/00_introduction/index.html | 101 ------- .../research/01_from_1_to_100_pixels/index.html | 139 --------- .../research/02_what_computers_can_see/index.html | 310 --------------------- site/public/research/index.html | 49 ---- site/public/test/chart/index.html | 50 ---- site/public/test/citations/index.html | 50 ---- site/public/test/csv/index.html | 50 ---- site/public/test/datasets/index.html | 50 ---- site/public/test/face_search/index.html | 50 ---- site/public/test/gallery/index.html | 68 ----- site/public/test/index.html | 61 ---- site/public/test/map/index.html | 50 ---- site/public/test/name_search/index.html | 50 ---- site/public/test/pie_chart/index.html | 50 ---- 43 files changed, 4446 deletions(-) delete mode 100644 site/public/about/faq/index.html delete mode 100644 site/public/about/index.html delete mode 100644 site/public/about/legal/index.html delete mode 100644 site/public/about/press/index.html delete mode 100644 site/public/datasets/50_people_one_question/index.html delete mode 100644 site/public/datasets/afad/index.html delete mode 100644 site/public/datasets/aflw/index.html delete mode 100644 site/public/datasets/brainwash/index.html delete mode 100644 site/public/datasets/caltech_10k/index.html delete mode 100644 site/public/datasets/celeba/index.html delete mode 100644 site/public/datasets/cofw/index.html delete mode 100644 site/public/datasets/duke_mtmc/index.html delete mode 100644 site/public/datasets/facebook/index.html delete mode 100644 site/public/datasets/feret/index.html delete mode 100644 site/public/datasets/hrt_transgender/index.html delete mode 100644 site/public/datasets/index.html delete mode 100644 site/public/datasets/lfpw/index.html delete mode 100644 site/public/datasets/lfw/index.html delete mode 100644 site/public/datasets/market_1501/index.html delete mode 100644 site/public/datasets/msceleb/index.html delete mode 100644 site/public/datasets/oxford_town_centre/index.html delete mode 100644 site/public/datasets/pipa/index.html delete mode 100644 site/public/datasets/pubfig/index.html delete mode 100644 site/public/datasets/uccs/index.html delete mode 100644 site/public/datasets/vgg_face2/index.html delete mode 100644 site/public/datasets/viper/index.html delete mode 100644 site/public/datasets/youtube_celebrities/index.html delete mode 100644 site/public/index.html delete mode 100644 site/public/info/index.html delete mode 100644 site/public/research/00_introduction/index.html delete mode 100644 site/public/research/01_from_1_to_100_pixels/index.html delete mode 100644 site/public/research/02_what_computers_can_see/index.html delete mode 100644 site/public/research/index.html delete mode 100644 site/public/test/chart/index.html delete mode 100644 site/public/test/citations/index.html delete mode 100644 site/public/test/csv/index.html delete mode 100644 site/public/test/datasets/index.html delete mode 100644 site/public/test/face_search/index.html delete mode 100644 site/public/test/gallery/index.html delete mode 100644 site/public/test/index.html delete mode 100644 site/public/test/map/index.html delete mode 100644 site/public/test/name_search/index.html delete mode 100644 site/public/test/pie_chart/index.html (limited to 'site/public') diff --git a/site/public/about/faq/index.html b/site/public/about/faq/index.html deleted file mode 100644 index 168abd0b..00000000 --- a/site/public/about/faq/index.html +++ /dev/null @@ -1,59 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
- - -
- Datasets - About -
-
-
- -

FAQs

-
- -

[ page under development ]

-
- -
- - - - - \ No newline at end of file diff --git a/site/public/about/index.html b/site/public/about/index.html deleted file mode 100644 index 64dded77..00000000 --- a/site/public/about/index.html +++ /dev/null @@ -1,93 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
- - -
- Datasets - About -
-
-
- -

About MegaPixels

-
- -

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.

-

The MegaPixels site is made possible with support from Mozilla

-
-
-

Adam Harvey

-

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.

-

ahprojects.com

-

-
-
-

Jules LaPlace

-

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. -

-

asdf.us

-
-

MegaPixels.cc is a research project about publicly available face recognition datasets. This website is based, in part, on an earlier installations and research about facial recognition datasets. Since then it has evolved into a large-scale survey of publicly-available face and person analysis datasets. Initially this site was planned as a facial recognition tool to search the datasets. After building several prototypes using over 1 million face images from these datasets, it became clear that facial recognition was mereley a face similar search. The results were not accurate enough to align with goals of this website: to promote responsible use of data and expose existing and past ethical breaches.

-

An academic report and presentation on the findings of this project is forthcoming. Throughout 2019, this site will be updated with more datasets and research reports on the general themes of remote biometric analysis and media collected "in the wild". The continued research on MegaPixels is supported by a 1 year Researcher-in-Residence grant from Karlsruhe HfG (2019-2020).

-

When possible, and once thoroughly verified, data generated for MegaPixels will be made available for download on github.com/adamhrv/megapixels

-

Team

-
    -
  • Adam Harvey: Concept, research and analysis, design, computer vision
    • -
  • Jules LaPlace: Information and systems architecture, data management, web applications
    • -
-

Contributing Researchers

-
    -
  • Berit Gilma: Dataset statistics
    • -
  • Beth (aka Ms. Celeb): Dataset usage verification
    • -
  • Mathana Stender: Commercial usage verification
    • -
-

Code and Libraries

-
    -
  • Semantic Scholar for citation aggregation
    • -
  • Leaflet.js for maps
    • -
  • C3.js for charts
    • -
  • ThreeJS for 3D visualizations
    • -
  • PDFMiner.Six and Pandas for research paper data analysis
    • -
-

Please direct questions, comments, or feedback to mastodon.social/@adamhrv

-
- -
- - - - - \ No newline at end of file diff --git a/site/public/about/legal/index.html b/site/public/about/legal/index.html deleted file mode 100644 index a603f999..00000000 --- a/site/public/about/legal/index.html +++ /dev/null @@ -1,85 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
- - -
- Datasets - About -
-
-
- -

Legal

-
- -

MegaPixels.cc Terms and Privacy

-

MegaPixels is an independent and academic art and research project about the origins and ethics of publicly available face analysis image datasets. By accessing MegaPixels (the Service or Services) you agree to the terms and conditions set forth below.

-

Privacy

-

The MegaPixels site has been designed to minimize the amount of network requests to 3rd party services and therefore prioritize the privacy of the viewer. This site does not use any local or external analytics programs to monitor site viewers. In fact, the only data collected are the necessary server logs used only for preventing misuse, which are deleted at short-term intervals.

-

3rd Party Services

-

In order to provide certain features of the site, some 3rd party services are needed. Currently, the MegaPixels.cc site uses two 3rd party services: (1) Leaflet.js for the interactive map and (2) Digital Ocean Spaces as a content delivery network. Both services encrypt your requests to their server using HTTPS and neither service requires storing any cookies or authentication. However, both services will store files in your web browser's local cache (local storage) to improve loading performance. None of these local storage files are using for analytics, tracking, or any similar purpose.

-

Links To Other Web Sites

-

The MegaPixels.cc contains many links to 3rd party websites, especially in the list of citations that are provided for each dataset. This website has no control over and assumes no responsibility for, the content, privacy policies, or practices of any third party web sites or services. You acknowledge and agree that megapixels.cc shall not be responsible or liable, directly or indirectly, for any damage or loss caused or alleged to be caused by or in connection with use of or reliance on any such content, goods or services available on or through any such web sites or services.

-

We advise you to read the terms and conditions and privacy policies of any third-party web sites or services that you visit.

-

The Information We Provide

-

While every intention is made to publish only verifiable information, at times existing information may be revised or deleted and new information may be added for clarity or correction. In no event will the operators of this site be liable for your use or misuse of the information provided.

-

We may terminate or suspend access to our Service immediately without prior notice or liability, for any reason whatsoever, including without limitation if you breach the Terms.

-

All provisions of the Terms which by their nature should survive termination shall survive termination, including, without limitation, ownership provisions, warranty disclaimers, indemnity and limitations of liability.

-

Prohibited Uses

-

You may not access or use, or attempt to access or use, the Services to take any action that could harm us or a third party. You may not use the Services in violation of applicable laws or in violation of our or any third party’s intellectual property or other proprietary or legal rights. You further agree that you shall not attempt (or encourage or support anyone else's attempt) to circumvent, reverse engineer, decrypt, or otherwise alter or interfere with the Services, or any content thereof, or make any unauthorized use thereof.

-

Without prior written consent, you shall not:

-

(i) access any part of the Services, Content, data or information you do not have permission or authorization to access;

-

(ii) use robots, spiders, scripts, service, software or any manual or automatic device, tool, or process designed to data mine or scrape the Content, data or information from the Services, or otherwise access or collect the Content, data or information from the Services using automated means;

-

(iii) use services, software or any manual or automatic device, tool, or process designed to circumvent any restriction, condition, or technological measure that controls access to the Services in any way, including overriding any security feature or bypassing or circumventing any access controls or use limits of the Services;

-

(iv) cache or archive the Content (except for a public search engine’s use of spiders for creating search indices) with prior written consent;

-

(v) take action that imposes an unreasonable or disproportionately large load on our network or infrastructure; and

-

(vi) do anything that could disable, damage or change the functioning or appearance of the Services, including the presentation of advertising.

-

Engaging in a prohibited use of the Services may result in civil, criminal, and/or administrative penalties, fines, or sanctions against the user and those assisting the user.

-

Governing Law

-

These Terms shall be governed and construed in accordance with the laws of Berlin, Germany, without regard to its conflict of law provisions.

-

Our failure to enforce any right or provision of these Terms will not be considered a waiver of those rights. If any provision of these Terms is held to be invalid or unenforceable by a court, the remaining provisions of these Terms will remain in effect. These Terms constitute the entire agreement between us regarding our Service, and supersede and replace any prior agreements we might have between us regarding the Service.

-

Indemnity

-

You hereby indemnify, defend and hold harmless MegaPixels (and its creators) and all officers, directors, owners, agents, information providers, affiliates, licensors and licensees (collectively, the "Indemnified Parties") from and against any and all liability and costs, including, without limitation, reasonable attorneys' fees, incurred by the Indemnified Parties in connection with any claim arising out of any breach by you or any user of your account of these Terms of Service or the foregoing representations, warranties and covenants. You shall cooperate as fully as reasonably required in the defense of any such claim. We reserves the right, at its own expense, to assume the exclusive defense and control of any matter subject to indemnification by you.

-

Changes

-

We reserve the right, at our sole discretion, to modify or replace these Terms at any time. By continuing to use or access our Service after revisions become effective, you agree to be bound by the revised terms. If you do not agree to revised terms, please do not use the Service.

-
- -
- - - - - \ No newline at end of file diff --git a/site/public/about/press/index.html b/site/public/about/press/index.html deleted file mode 100644 index 3e5a5f8e..00000000 --- a/site/public/about/press/index.html +++ /dev/null @@ -1,58 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
- - -
- Datasets - About -
-
-
- -

Press

-
- -
-
- -
- - - - - \ No newline at end of file diff --git a/site/public/datasets/50_people_one_question/index.html b/site/public/datasets/50_people_one_question/index.html deleted file mode 100644 index b27fa3e5..00000000 --- a/site/public/datasets/50_people_one_question/index.html +++ /dev/null @@ -1,114 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
-
50 People One Question Dataset
- -
- Datasets - About -
-
-
- -
People One Question is a dataset of people from an online video series on YouTube and Vimeo used for building facial recogntion algorithms
People One Question dataset includes ... -
-
Published
-
2013
-
-
Videos
-
33
-
-
Purpose
-
Facial landmark estimation in the wild
-
-
Website
- -

50 People 1 Question

-

[ page under development ]

-
-

Who used 50 People One Question Dataset?

- -

- 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. -

- -
- -
- -
-
- -
-
-
- -
- -

Biometric Trade Routes

- -

- To help understand how 50 People One Question Dataset has been used around the world by commercial, military, and academic organizations; existing publicly available research citing 50 People One Question was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. -

- -
- -
-
-
- -
-
    -
  • Academic
    • -
  • Commercial
    • -
  • Military / Government
    • -
-
Citation data is collected using SemanticScholar.org then dataset usage verified and geolocated.
-
- - -
- -

Dataset Citations

-

- The dataset citations used in the visualizations were collected from Semantic Scholar, 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. -

- -
-
- -
- - - - - \ No newline at end of file diff --git a/site/public/datasets/afad/index.html b/site/public/datasets/afad/index.html deleted file mode 100644 index 67a4e981..00000000 --- a/site/public/datasets/afad/index.html +++ /dev/null @@ -1,127 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
-
Asian Face Age Dataset
- -
- Datasets - About -
-
-
- -
-
Published
-
2017
-
-
Images
-
164,432
-
-
Purpose
-
age estimation on Asian Faces
-
-
Funded by
-
NSFC, the Fundamental Research Funds for the Central Universities, the Program for Changjiang Scholars and Innovative Research Team in University of China, the Shaanxi Innovative Research Team for Key Science and Technology, and China Postdoctoral Science Foundation
-
-
Website
- -

Asian Face Age Dataset

-

[ page under development ]

-
-

Who used Asian Face Age Dataset?

- -

- 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. -

- -
- -
- -
-
- -
-
-
- -
- -

Biometric Trade Routes

- -

- To help understand how Asian Face Age Dataset has been used around the world by commercial, military, and academic organizations; existing publicly available research citing The Asian Face Age Dataset was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. -

- -
- -
-
-
- -
-
    -
  • Academic
    • -
  • Commercial
    • -
  • Military / Government
    • -
-
Citation data is collected using SemanticScholar.org then dataset usage verified and geolocated.
-
- - -
- -

Dataset Citations

-

- The dataset citations used in the visualizations were collected from Semantic Scholar, 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. -

- -
-

(ignore) research notes

-

The Asian Face Age Dataset (AFAD) is a new dataset proposed for evaluating the performance of age estimation, which contains more than 160K facial images and the corresponding age and gender labels. This dataset is oriented to age estimation on Asian faces, so all the facial images are for Asian faces. It is noted that the AFAD is the biggest dataset for age estimation to date. It is well suited to evaluate how deep learning methods can be adopted for age estimation. -Motivation

-

For age estimation, there are several public datasets for evaluating the performance of a specific algorithm, such as FG-NET [1] (1002 face images), MORPH I (1690 face images), and MORPH II[2] (55,608 face images). Among them, the MORPH II is the biggest public dataset to date. On the other hand, as we know it is necessary to collect a large scale dataset to train a deep Convolutional Neural Network. Therefore, the MORPH II dataset is extensively used to evaluate how deep learning methods can be adopted for age estimation [3][4].

-

However, the ethnic is very unbalanced for the MORPH II dataset, i.e., it has only less than 1% Asian faces. In order to evaluate the previous methods for age estimation on Asian Faces, the Asian Face Age Dataset (AFAD) was proposed.

-

There are 164,432 well-labeled photos in the AFAD dataset. It consist of 63,680 photos for female as well as 100,752 photos for male, and the ages range from 15 to 40. The distribution of photo counts for distinct ages are illustrated in the figure above. Some samples are shown in the Figure on the top. Its download link is provided in the "Download" section.

-

In addition, we also provide a subset of the AFAD dataset, called AFAD-Lite, which only contains PLACEHOLDER well-labeled photos. It consist of PLACEHOLDER photos for female as well as PLACEHOLDER photos for male, and the ages range from 15 to 40. The distribution of photo counts for distinct ages are illustrated in Fig. PLACEHOLDER. Its download link is also provided in the "Download" section.

-

The AFAD dataset is built by collecting selfie photos on a particular social network -- RenRen Social Network (RSN) [5]. The RSN is widely used by Asian students including middle school, high school, undergraduate, and graduate students. Even after leaving from school, some people still access their RSN account to connect with their old classmates. So, the age of the RSN user crosses a wide range from 15-years to more than 40-years old.

-

Please notice that this dataset is made available for academic research purpose only.

-
-

https://afad-dataset.github.io/

-
- -
- - - - - \ No newline at end of file diff --git a/site/public/datasets/aflw/index.html b/site/public/datasets/aflw/index.html deleted file mode 100644 index 81fb7335..00000000 --- a/site/public/datasets/aflw/index.html +++ /dev/null @@ -1,53 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
- - -
- Datasets - About -
-
-
- -

Annotated Facial Landmarks in The Wild

-
Years
1993-1996
Images
25,993
Identities
1,199
Origin
Flickr

RESEARCH below this line

-

The motivation for the AFLW database is the need for a large-scale, multi-view, real-world face database with annotated facial features. We gathered the images on Flickr using a wide range of face relevant tags (e.g., face, mugshot, profile face). The downloaded set of images was manually scanned for images containing faces. The key data and most important properties of the database are:

-
-

https://www.tugraz.at/institute/icg/research/team-bischof/lrs/downloads/aflw/

-
- -
- - - - - \ No newline at end of file diff --git a/site/public/datasets/brainwash/index.html b/site/public/datasets/brainwash/index.html deleted file mode 100644 index 10ee577c..00000000 --- a/site/public/datasets/brainwash/index.html +++ /dev/null @@ -1,146 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
-
Brainwash Dataset
- -
- Datasets - About -
-
-
- -
Brainwash is a dataset of webcam images taken from the Brainwash Cafe in San Francisco in 2014
The Brainwash dataset includes 11,918 images of "everyday life of a busy downtown cafe" and is used for training head detection surveillance algorithms -
-
Published
-
2015
-
-
Images
-
11,917
-
-
Purpose
-
Head detection
-
-
Created by
-
Stanford University (US), Max Planck Institute for Informatics (DE)
-
-
Funded by
-
Max Planck Center for Visual Computing and Communication
-
-
Download Size
-
4.1 GB
-
-
Website
- -

Brainwash Dataset

-

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" 1 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. 2

-

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. 3 4

-

If you happen to have been at Brainwash cafe in San Francisco at any time on October 26, November 13, or November 24 in 2014 you are most likely included in the Brainwash dataset and have unwittingly contributed to surveillance research.

-
-

Who used Brainwash Dataset?

- -

- 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. -

- -
- -
- -
-
- -
-
-
- -
- -

Biometric Trade Routes

- -

- To help understand how Brainwash Dataset has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Brainwash Dataset was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. -

- -
- -
-
-
- -
-
    -
  • Academic
    • -
  • Commercial
    • -
  • Military / Government
    • -
-
Citation data is collected using SemanticScholar.org then dataset usage verified and geolocated.
-
- - -
- -

Dataset Citations

-

- The dataset citations used in the visualizations were collected from Semantic Scholar, 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. -

- -
-
- -
-
-
-
- -

Supplementary Information

- -
A visualization of 81,973 head annotations from the Brainwash dataset training partition. © megapixels.cc
A visualization of 81,973 head annotations from the Brainwash dataset training partition. © megapixels.cc
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)
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)
49 of the 11,918 images included in the Brainwash dataset. License: Open Data Commons Public Domain Dedication (PDDL)
49 of the 11,918 images included in the Brainwash dataset. License: Open Data Commons Public Domain Dedication (PDDL)

TODO

-
    -
  • change supp images to 2x2 grid with bboxes
    • -
  • add bounding boxes to the header image
    • -
  • remake montage with randomized images, with bboxes
    • -
  • add ethics link to Stanford
    • -
  • add optout info
    • -
-
  • a

    "readme.txt" https://exhibits.stanford.edu/data/catalog/sx925dc9385.

    -
  • a

    Stewart, Russel. Andriluka, Mykhaylo. "End-to-end people detection in crowded scenes". 2016.

    -
  • a

    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.

    -
  • a

    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/public/datasets/caltech_10k/index.html b/site/public/datasets/caltech_10k/index.html deleted file mode 100644 index 10925b09..00000000 --- a/site/public/datasets/caltech_10k/index.html +++ /dev/null @@ -1,124 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
-
Brainwash Dataset
- -
- Datasets - About -
-
-
- -
-
Published
-
2015
-
-
Images
-
11,917
-
-
Purpose
-
Head detection
-
-
Created by
-
Stanford University (US), Max Planck Institute for Informatics (DE)
-
-
Funded by
-
Max Planck Center for Visual Computing and Communication
-
-
Download Size
-
4.1 GB
-
-
Website
- -

Caltech 10K Faces Dataset

-

[ page under development ]

-
-

Who used Brainwash Dataset?

- -

- 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. -

- -
- -
- -
-
- -
-
-
- -
- -

Biometric Trade Routes

- -

- To help understand how Brainwash Dataset has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Brainwash Dataset was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. -

- -
- -
-
-
- -
-
    -
  • Academic
    • -
  • Commercial
    • -
  • Military / Government
    • -
-
Citation data is collected using SemanticScholar.org then dataset usage verified and geolocated.
-
- - -
- -

Dataset Citations

-

- The dataset citations used in the visualizations were collected from Semantic Scholar, 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. -

- -
-

(ignore) research notes

-

The dataset contains images of people collected from the web by typing common given names into Google Image Search. The coordinates of the eyes, the nose and the center of the mouth for each frontal face are provided in a ground truth file. This information can be used to align and crop the human faces or as a ground truth for a face detection algorithm. The dataset has 10,524 human faces of various resolutions and in different settings, e.g. portrait images, groups of people, etc. Profile faces or very low resolution faces are not labeled.

-
- -
- - - - - \ No newline at end of file diff --git a/site/public/datasets/celeba/index.html b/site/public/datasets/celeba/index.html deleted file mode 100644 index 3b9883dc..00000000 --- a/site/public/datasets/celeba/index.html +++ /dev/null @@ -1,126 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
-
CelebA Dataset
- -
- Datasets - About -
-
-
- -
CelebA is a dataset of people...
CelebA includes... -
-
Published
-
2015
-
-
Images
-
202,599
-
-
Identities
-
10,177
-
-
Purpose
-
face attribute recognition, face detection, and landmark (or facial part) localization
-
-
Download Size
-
1.4 GB
-
-
Website
- -

CelebA Dataset

-

[ PAGE UNDER DEVELOPMENT ]

-
-

Who used CelebA Dataset?

- -

- 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. -

- -
- -
- -
-
- -
-
-
- -
- -

Biometric Trade Routes

- -

- To help understand how CelebA Dataset has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Large-scale CelebFaces Attributes Dataset was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. -

- -
- -
-
-
- -
-
    -
  • Academic
    • -
  • Commercial
    • -
  • Military / Government
    • -
-
Citation data is collected using SemanticScholar.org then dataset usage verified and geolocated.
-
- - -
- -

Dataset Citations

-

- The dataset citations used in the visualizations were collected from Semantic Scholar, 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. -

- -
-

Research

-
    -
  • "An Unsupervised Approach to Solving Inverse Problems using Generative Adversarial Networks" mentions use by sponsored by an agency of the United States government. Neither the United States government nor Lawrence Livermore National Security, LLC, nor any of their"
    • -
  • 7dab6fbf42f82f0f5730fc902f72c3fb628ef2f0
    • -
  • principal responsibility is ensuring the safety, security and reliability of the nation's nuclear weapons NNSA ( National Nuclear Security Administration )
    • -
-
- -
- - - - - \ No newline at end of file diff --git a/site/public/datasets/cofw/index.html b/site/public/datasets/cofw/index.html deleted file mode 100644 index f335442c..00000000 --- a/site/public/datasets/cofw/index.html +++ /dev/null @@ -1,179 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
-
COFW Dataset
- -
- Datasets - About -
-
-
- -
-
Published
-
2013
-
-
Images
-
1,007
-
-
Purpose
-
challenging dataset (sunglasses, hats, interaction with objects)
-
-
Website
- -

Caltech Occluded Faces in the Wild

-

[ PAGE UNDER DEVELOPMENT ]

-
-

Who used COFW Dataset?

- -

- 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. -

- -
- -
- -
-
- -
-
-
- -
- -

Biometric Trade Routes

- -

- To help understand how COFW Dataset has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Caltech Occluded Faces in the Wild was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. -

- -
- -
-
-
- -
-
    -
  • Academic
    • -
  • Commercial
    • -
  • Military / Government
    • -
-
Citation data is collected using SemanticScholar.org then dataset usage verified and geolocated.
-
- - -
- -

Dataset Citations

-

- The dataset citations used in the visualizations were collected from Semantic Scholar, 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. -

- -
-

(ignore) research notes

-
Years
1993-1996
Images
14,126
Identities
1,199
Origin
Web Searches
Funded by
ODNI, IARPA, Microsoft

COFW is "is designed to benchmark face landmark algorithms in realistic conditions, which include heavy occlusions and large shape variations" [Robust face landmark estimation under occlusion].

-

We asked four people with different levels of computer vision knowledge to each collect 250 faces representative of typical real-world images, with the clear goal of challenging computer vision methods. -The result is 1,007 images of faces obtained from a variety of sources.

-
-

Robust face landmark estimation under occlusion

-

Our face dataset is designed to present faces in real-world conditions. Faces show large variations in shape and occlusions due to differences in pose, expression, use of accessories such as sunglasses and hats and interactions with objects (e.g. food, hands, microphones, etc.). All images were hand annotated in our lab using the same 29 landmarks as in LFPW. We annotated both the landmark positions as well as their occluded/unoccluded state. The faces are occluded to different degrees, with large variations in the type of occlusions encountered. COFW has an average occlusion of over 23%. -To increase the number of training images, and since COFW has the exact same landmarks as LFPW, for training we use the original non-augmented 845 LFPW faces + 500 COFW faces (1345 total), and for testing the remaining 507 COFW faces. To make sure all images had occlusion labels, we annotated occlusion on the available 845 LFPW training images, finding an average of only 2% occlusion.

-
-

http://www.vision.caltech.edu/xpburgos/ICCV13/

-

This research is supported by NSF Grant 0954083 and by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via IARPA R&D Contract No. 2014-14071600012.

-
-

https://www.cs.cmu.edu/~peiyunh/topdown/

-
- -

Biometric Trade Routes

- -

- To help understand how COFW Dataset has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Caltech Occluded Faces in the Wild was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the location markers to reveal research projects at that location. -

- -
- -
-
-
- -
-
    -
  • Academic
    • -
  • Commercial
    • -
  • Military / Government
    • -
-
Citation data is collected using SemanticScholar.org and then dataset usage verified and geolocated.
-
- -
-
-
-
- -

Supplementary Information

- -
- -

Dataset Citations

-

- The dataset citations used in the visualizations were collected from Semantic Scholar, 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. -

- -
-
-

Who used COFW Dataset?

- -

- 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. -

- -
- -
- -
-

TODO

-

- replace graphic

-
- -
- - - - - \ No newline at end of file diff --git a/site/public/datasets/duke_mtmc/index.html b/site/public/datasets/duke_mtmc/index.html deleted file mode 100644 index 0d082c15..00000000 --- a/site/public/datasets/duke_mtmc/index.html +++ /dev/null @@ -1,144 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
-
Duke MTMC Dataset
- -
- Datasets - About -
-
-
- -
Duke MTMC is a dataset of surveillance camera footage of students on Duke University campus
Duke MTMC contains over 2 million video frames and 2,700 unique identities collected from 8 HD cameras at Duke University campus in March 2014 -
-
Published
-
2016
-
-
Images
-
2,000,000
-
-
Identities
-
1,812
-
-
Purpose
-
Person re-identification and multi-camera tracking
-
-
Created by
-
Computer Science Department, Duke University, Durham, US
-
-
Website
- -

Duke MTMC

-

The Duke Multi-Target, Multi-Camera Tracking Dataset (MTMC) is a dataset of video recorded on Duke University campus for research and development of networked camera surveillance systems. MTMC tracking is used for citywide dragnet surveillance systems such as those used throughout China by SenseTime 1 and the oppressive monitoring of 2.5 million Uyghurs in Xinjiang by SenseNets 2. In fact researchers from both SenseTime 4 5 and SenseNets 3 used the Duke MTMC dataset for their research.

-

The Duke MTMC dataset is unique because it is the largest publicly available MTMC and person re-identification dataset and has the longest duration of annotated video. In total, the Duke MTMC dataset provides over 14 hours of 1080p video from 8 synchronized surveillance cameras. 6 It is among the most widely used person re-identification datasets in the world. The approximately 2,700 unique people in the Duke MTMC videos, most of whom are students, are used for research and development of surveillance technologies by commercial, academic, and even defense organizations.

-
A collection of 1,600 out of the 2,700 students and passersby captured into the Duke MTMC surveillance research dataset. These students were also included in the Duke MTMC Re-ID dataset extension used for person re-identification. © megapixels.cc
A collection of 1,600 out of the 2,700 students and passersby captured into the Duke MTMC surveillance research dataset. These students were also included in the Duke MTMC Re-ID dataset extension used for person re-identification. © megapixels.cc

The creation and publication of the Duke MTMC dataset in 2016 was originally funded by the U.S. Army Research Laboratory and the National Science Foundation 6. Since 2016 use of the Duke MTMC dataset images have been publicly acknowledged in research funded by or on behalf of the Chinese National University of Defense 7 8, IARPA and IBM 9, and U.S. Department of Homeland Security 10.

-

The 8 cameras deployed on Duke's campus were specifically setup to capture students "during periods between lectures, when pedestrian traffic is heavy". 6 Camera 7 and 2 capture large groups of prospective students and children. Camera 5 was positioned to capture students as they enter and exit Duke University's main chapel. Each camera's location is documented below.

-
Duke MTMC camera locations on Duke University campus © megapixels.cc
Duke MTMC camera locations on Duke University campus © megapixels.cc
Duke MTMC camera views for 8 cameras deployed on campus © megapixels.cc
Duke MTMC camera views for 8 cameras deployed on campus © megapixels.cc
Duke MTMC pedestrian detection saliency maps for 8 cameras deployed on campus © megapixels.cc
Duke MTMC pedestrian detection saliency maps for 8 cameras deployed on campus © megapixels.cc
-

Who used Duke MTMC Dataset?

- -

- 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. -

- -
- -
- -
-
- -
-
-
- -
- -

Biometric Trade Routes

- -

- To help understand how Duke MTMC Dataset has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Duke Multi-Target, Multi-Camera Tracking Project was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. -

- -
- -
-
-
- -
-
    -
  • Academic
    • -
  • Commercial
    • -
  • Military / Government
    • -
-
Citation data is collected using SemanticScholar.org then dataset usage verified and geolocated.
-
- - -
- -

Dataset Citations

-

- The dataset citations used in the visualizations were collected from Semantic Scholar, 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. -

- -
-
- -
-
-
-
- -

Supplementary Information

- -

Notes

-

The Duke MTMC dataset paper mentions 2,700 identities, but their ground truth file only lists annotations for 1,812

-
- -
- - - - - \ No newline at end of file diff --git a/site/public/datasets/facebook/index.html b/site/public/datasets/facebook/index.html deleted file mode 100644 index be413510..00000000 --- a/site/public/datasets/facebook/index.html +++ /dev/null @@ -1,54 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
- - -
- Datasets - About -
-
-
- -
TBD
TBD -
TBD

Statistics

-
Years
2002-2004
Images
13,233
Identities
5,749
Origin
Yahoo News Images
Funding
(Possibly, partially CIA)

Ignore content below these lines

- -
- -
- - - - - \ No newline at end of file diff --git a/site/public/datasets/feret/index.html b/site/public/datasets/feret/index.html deleted file mode 100644 index 5cd29c4c..00000000 --- a/site/public/datasets/feret/index.html +++ /dev/null @@ -1,87 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
-
LFW
- -
- Datasets - About -
-
-
- -
-
Published
-
2007
-
-
Images
-
13,233
-
-
Identities
-
5,749
-
-
Purpose
-
face recognition
-
-
Website
- -

FacE REcognition Dataset (FERET)

-

[ page under development ]

-

{% include 'dashboard.html' %}

-

(ignore) RESEARCH below this line

-
    -
  • Years: 1993-1996
    • -
  • Images: 14,126
    • -
  • Identities: 1,199
    • -
  • Origin: Fairfax, MD
    • -
  • Facial Recognition Evaluation (FERET) is develop, test, and evaluate face recognition algorithms
    • -
  • The goal of the FERET program was to develop automatic face recognition capabilities that could be employed to assist security, intelligence, and law enforcement personnel in the performance of their duties.
    • -
  • https://www.nist.gov/programs-projects/face-recognition-technology-feret
    • -
-

"The FERET database and evaluation procedure for face-recognition algorithms"

-
    -
  • Images were captured using Kodak Ultra film
    • -
  • The facial images were collected in 11 sessions from August 1993 to December 1994. Conducted at George Mason University and at US Army Research Laboratory facilities,
    • -
-

FERET (Face Recognition Technology) Recognition Algorithm Development and Test Results

-
    -
  • "A release form is necessary because of the privacy laws in the United States."
    • -
-

Funding

-

The FERET program is sponsored by the U.S. Depart- ment of Defense’s Counterdrug Technology Development Program Office. The U.S. Army Research Laboratory (ARL) is the technical agent for the FERET program. ARL designed, administered, and scored the FERET tests. George Mason University collected, processed, and main- tained the FERET database. Inquiries regarding the FERET database or test should be directed to P. Jonathon Phillips.

-
- -
- - - - - \ No newline at end of file diff --git a/site/public/datasets/hrt_transgender/index.html b/site/public/datasets/hrt_transgender/index.html deleted file mode 100644 index 099dea4e..00000000 --- a/site/public/datasets/hrt_transgender/index.html +++ /dev/null @@ -1,67 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
-
HRT Transgender
- -
- Datasets - About -
-
-
- -
TBD
TBD -
-
Published
-
2013
-
-
Images
-
10,564
-
-
Identities
-
38
-
-
Purpose
-
gender transition and facial recognition
-
-
Website
- -

HRT Transgender Dataset

-

[ page under development ]

-

{% include 'dashboard.html' }

-
- -
- - - - - \ No newline at end of file diff --git a/site/public/datasets/index.html b/site/public/datasets/index.html deleted file mode 100644 index 6f87ff68..00000000 --- a/site/public/datasets/index.html +++ /dev/null @@ -1,145 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
- - -
- Datasets - About -
-
-
- - -

Facial Recognition Datasets

-

Explore publicly available facial recognition datasets. More datasets will be added throughout 2019.

-
- -
- -
- -
- - -
- Brainwash -
-
2015
-
Head detection
-
11,917 images
-
-
-
- - - -
- Duke MTMC -
-
2016
-
Person re-identification, multi-camera tracking
-
2,000,000 images
-
1,812
-
-
- - - -
- Market-1501 -
-
2015
-
Person re-identification
-
32,668 images
-
1,501
-
-
- - - -
- Microsoft Celeb -
-
2016
-
Large-scale face recognition
-
1,000,000 images
-
100,000
-
-
- - - -
- Oxford Town Centre -
-
2011
-
Person detection, gaze estimation
-
images
-
-
-
- - - -
- UnConstrained College Students -
-
2016
-
Face recognition, face detection
-
16,149 images
-
1,732
-
-
- - - -
- VIPeR -
-
2007
-
Person re-identification
-
1,264 images
-
632
-
-
- - -
-
- - -
- - - - - \ No newline at end of file diff --git a/site/public/datasets/lfpw/index.html b/site/public/datasets/lfpw/index.html deleted file mode 100644 index 005b7aaa..00000000 --- a/site/public/datasets/lfpw/index.html +++ /dev/null @@ -1,116 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
-
LFWP
- -
- Datasets - About -
-
-
- -
-
Published
-
2011
-
-
Funded by
-
CIA
-
-
Website
- -

Labeled Face Parts in The Wild

-
-

Who used LFWP?

- -

- 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. -

- -
- -
- -
-
- -
-
-
- -
- -

Biometric Trade Routes

- -

- To help understand how LFWP has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Labeled Face Parts in the Wild was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. -

- -
- -
-
-
- -
-
    -
  • Academic
    • -
  • Commercial
    • -
  • Military / Government
    • -
-
Citation data is collected using SemanticScholar.org then dataset usage verified and geolocated.
-
- - -
- -

Dataset Citations

-

- The dataset citations used in the visualizations were collected from Semantic Scholar, 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. -

- -
-

RESEARCH below this line

-

Release 1 of LFPW consists of 1,432 faces from images downloaded from the web using simple text queries on sites such as google.com, flickr.com, and yahoo.com. Each image was labeled by three MTurk workers, and 29 fiducial points, shown below, are included in dataset. LFPW was originally described in the following publication:

-

Due to copyright issues, we cannot distribute image files in any format to anyone. Instead, we have made available a list of image URLs where you can download the images yourself. We realize that this makes it impossible to exactly compare numbers, as image links will slowly disappear over time, but we have no other option. This seems to be the way other large web-based databases seem to be evolving.

-
-

https://neerajkumar.org/databases/lfpw/

-

This research was performed at Kriegman-Belhumeur Vision Technologies and was funded by the CIA through the Office of the Chief Scientist. https://www.cs.cmu.edu/~peiyunh/topdown/ (nk_cvpr2011_faceparts.pdf)

-
-
- -
- - - - - \ No newline at end of file diff --git a/site/public/datasets/lfw/index.html b/site/public/datasets/lfw/index.html deleted file mode 100644 index cb487913..00000000 --- a/site/public/datasets/lfw/index.html +++ /dev/null @@ -1,166 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
-
LFW
- -
- Datasets - About -
-
-
- -
Labeled Faces in The Wild (LFW) is the first facial recognition dataset created entirely from online photos
It includes 13,456 images of 4,432 people's images copied from the Internet during 2002-2004 and is the most frequently used dataset in the world for benchmarking face recognition algorithms. -
-
Published
-
2007
-
-
Images
-
13,233
-
-
Identities
-
5,749
-
-
Purpose
-
face recognition
-
-
Website
- -

Labeled Faces in the Wild

-

[ PAGE UNDER DEVELOPMENT ]

-

Labeled Faces in The Wild (LFW) is "a database of face photographs designed for studying the problem of unconstrained face recognition 1. It is used to evaluate and improve the performance of facial recognition algorithms in academic, commercial, and government research. According to BiometricUpdate.com 3, LFW is "the most widely used evaluation set in the field of facial recognition, LFW attracts a few dozen teams from around the globe including Google, Facebook, Microsoft Research Asia, Baidu, Tencent, SenseTime, Face++ and Chinese University of Hong Kong."

-

The LFW dataset includes 13,233 images of 5,749 people that were collected between 2002-2004. LFW is a subset of Names of Faces and is part of the first facial recognition training dataset created entirely from images appearing on the Internet. The people appearing in LFW are...

-

The Names and Faces dataset was the first face recognition dataset created entire from online photos. However, Names and Faces and LFW are not the first face recognition dataset created entirely "in the wild". That title belongs to the UCD dataset. Images obtained "in the wild" means using an image without explicit consent or awareness from the subject or photographer.

-

The Names and Faces dataset was the first face recognition dataset created entire from online photos. However, Names and Faces and LFW are not the first face recognition dataset created entirely "in the wild". That title belongs to the UCD dataset. Images obtained "in the wild" means using an image without explicit consent or awareness from the subject or photographer.

-
All 5,379 people in the Labeled Faces in The Wild Dataset. Showing one face per person
All 5,379 people in the Labeled Faces in The Wild Dataset. Showing one face per person

The Names and Faces dataset was the first face recognition dataset created entire from online photos. However, Names and Faces and LFW are not the first face recognition dataset created entirely "in the wild". That title belongs to the UCD dataset. Images obtained "in the wild" means using an image without explicit consent or awareness from the subject or photographer.

-

The Names and Faces dataset was the first face recognition dataset created entire from online photos. However, Names and Faces and LFW are not the first face recognition dataset created entirely "in the wild". That title belongs to the UCD dataset. Images obtained "in the wild" means using an image without explicit consent or awareness from the subject or photographer.

-
-

Who used LFW?

- -

- 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. -

- -
- -
- -
-
- -
-
-
- -
- -

Biometric Trade Routes

- -

- To help understand how LFW has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Labeled Faces in the Wild was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. -

- -
- -
-
-
- -
-
    -
  • Academic
    • -
  • Commercial
    • -
  • Military / Government
    • -
-
Citation data is collected using SemanticScholar.org then dataset usage verified and geolocated.
-
- - -
- -

Dataset Citations

-

- The dataset citations used in the visualizations were collected from Semantic Scholar, 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. -

- -
-
- -
-
-
-
- -

Supplementary Information

- -

Commercial Use

-

Add a paragraph about how usage extends far beyond academia into research centers for largest companies in the world. And even funnels into CIA funded research in the US and defense industry usage in China.

-

Research

-
    -
  • "In our experiments, we used 10000 images and associated captions from the Faces in the wilddata set [3]."
    • -
  • "This work was supported in part by the Center for Intelligent Information Retrieval, the Central Intelligence Agency, the National Security Agency and National Science Foundation under CAREER award IIS-0546666 and grant IIS-0326249."
    • -
  • From: "People-LDA: Anchoring Topics to People using Face Recognition" https://www.semanticscholar.org/paper/People-LDA%3A-Anchoring-Topics-to-People-using-Face-Jain-Learned-Miller/10f17534dba06af1ddab96c4188a9c98a020a459 and https://ieeexplore.ieee.org/document/4409055
    • -
  • This paper was presented at IEEE 11th ICCV conference Oct 14-21 and the main LFW paper "Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments" was also published that same year
    • -
  • 10f17534dba06af1ddab96c4188a9c98a020a459
    • -
  • This research is based upon work supported in part by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via contract number 2014-14071600010.
    • -
  • From "Labeled Faces in the Wild: Updates and New Reporting Procedures"
    • -
  • 70% of people in the dataset have only 1 image and 29% have 2 or more images
    • -
  • The LFW dataset is considered the "most popular benchmark for face recognition" 2
    • -
  • The LFW dataset is "the most widely used evaluation set in the field of facial recognition" 3
    • -
  • All images in LFW dataset were obtained "in the wild" meaning without any consent from the subject or from the photographer
    • -
  • The faces in the LFW dataset were detected using the Viola-Jones haarcascade face detector [^lfw_website] [^lfw-survey]
    • -
  • The LFW dataset is used by several of the largest tech companies in the world including "Google, Facebook, Microsoft Research Asia, Baidu, Tencent, SenseTime, Face++ and Chinese University of Hong Kong." 3
    • -
  • All images in the LFW dataset were copied from Yahoo News between 2002 - 2004
    • -
  • In 2014, two of the four original authors of the LFW dataset received funding from IARPA and ODNI for their followup paper Labeled Faces in the Wild: Updates and New Reporting Procedures via IARPA contract number 2014-14071600010
    • -
  • The dataset includes 2 images of George Tenet, the former Director of Central Intelligence (DCI) for the Central Intelligence Agency whose facial biometrics were eventually used to help train facial recognition software in China and Russia
    • -
  • ./15/155205b8e288fd49bf203135871d66de879c8c04/paper.txt shows usage by DSTO Australia, supported parimal@iisc.ac.in
    • -
-
Created
2002 – 2004
Images
13,233
Identities
5,749
Origin
Yahoo! News Images
Used by
Facebook, Google, Microsoft, Baidu, Tencent, SenseTime, Face++, CIA, NSA, IARPA
Website
    -
  • There are about 3 men for every 1 woman in the LFW dataset 1
    • -
  • The person with the most images is George W. Bush with 530
    • -
  • There are about 3 George W. Bush's for every 1 Tony Blair
    • -
  • The LFW dataset includes over 500 actors, 30 models, 10 presidents, 124 basketball players, 24 football players, 11 kings, 7 queens, and 1 Moby
    • -
  • In all 3 of the LFW publications [^lfw_original_paper], [^lfw_survey], [^lfw_tech_report] the words "ethics", "consent", and "privacy" appear 0 times
    • -
  • The word "future" appears 71 times
    • -
  • * denotes partial funding for related research
    • -
-
- -
- - - - - \ No newline at end of file diff --git a/site/public/datasets/market_1501/index.html b/site/public/datasets/market_1501/index.html deleted file mode 100644 index 059b1a49..00000000 --- a/site/public/datasets/market_1501/index.html +++ /dev/null @@ -1,132 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
-
Market 1501
- -
- Datasets - About -
-
-
- -
Market-1501 is a dataset is collection of CCTV footage from Tsinghua University
The Market-1501 dataset includes 1,261 people from 5 HD surveillance cameras located on campus -
-
Published
-
2015
-
-
Images
-
32,668
-
-
Identities
-
1,501
-
-
Purpose
-
Person re-identification
-
-
Website
- -

Market-1501 Dataset

-

[ PAGE UNDER DEVELOPMENT]

-
-

Who used Market 1501?

- -

- 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. -

- -
- -
- -
-
- -
-
-
- -
- -

Biometric Trade Routes

- -

- To help understand how Market 1501 has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Market 1501 Dataset was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. -

- -
- -
-
-
- -
-
    -
  • Academic
    • -
  • Commercial
    • -
  • Military / Government
    • -
-
Citation data is collected using SemanticScholar.org then dataset usage verified and geolocated.
-
- - -
- -

Dataset Citations

-

- The dataset citations used in the visualizations were collected from Semantic Scholar, 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. -

- -
-

(ignore) research Notes

-
    -
  • "MARS is an extension of the Market-1501 dataset. During collection, we placed six near synchronized cameras in the campus of Tsinghua university. There were Five 1,0801920 HD cameras and one 640480 SD camera. MARS consists of 1,261 different pedestrians whom are captured by at least 2 cameras. Given a query tracklet, MARS aims to retrieve tracklets that contain the same ID." - main paper
    • -
  • bbox "0065C1T0002F0016.jpg", "0065" is the ID of the pedestrian. "C1" denotes the first -camera (there are totally 6 cameras). "T0002" means the 2th tracklet. "F016" is the 16th frame -within this tracklet. For the tracklets, their names are accumulated for each ID; but for frames, -they start from "F001" in each tracklet.
    • -
-

@proceedings{zheng2016mars, -title={MARS: A Video Benchmark for Large-Scale Person Re-identification}, -author={Zheng, Liang and Bie, Zhi and Sun, Yifan and Wang, Jingdong and Su, Chi and Wang, Shengjin and Tian, Qi}, -booktitle={European Conference on Computer Vision}, -year={2016}, -organization={Springer} -}

-
- -
- - - - - \ No newline at end of file diff --git a/site/public/datasets/msceleb/index.html b/site/public/datasets/msceleb/index.html deleted file mode 100644 index fd64189c..00000000 --- a/site/public/datasets/msceleb/index.html +++ /dev/null @@ -1,139 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
-
Microsoft Celeb
- -
- Datasets - About -
-
-
- -
MS Celeb is a dataset of web images used for training and evaluating face recognition algorithms
The MS Celeb dataset includes over 10,000,000 images and 93,000 identities of semi-public figures collected using the Bing search engine -
-
Published
-
2016
-
-
Images
-
1,000,000
-
-
Identities
-
100,000
-
-
Purpose
-
Large-scale face recognition
-
-
Created by
-
Microsoft Research
-
-
Funded by
-
Microsoft Research
-
-
Website
- -

Microsoft Celeb Dataset (MS Celeb)

-

[ PAGE UNDER DEVELOPMENT ]

-
-

Who used Microsoft Celeb?

- -

- 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. -

- -
- -
- -
-
- -
-
-
- -
- -

Biometric Trade Routes

- -

- To help understand how Microsoft Celeb has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Microsoft Celebrity Dataset was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. -

- -
- -
-
-
- -
-
    -
  • Academic
    • -
  • Commercial
    • -
  • Military / Government
    • -
-
Citation data is collected using SemanticScholar.org then dataset usage verified and geolocated.
-
- - -
- -

Dataset Citations

-

- The dataset citations used in the visualizations were collected from Semantic Scholar, 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. -

- -
-
- -
-
-
-
- -

Supplementary Information

- -

Additional Information

- -

  • "readme.txt" https://exhibits.stanford.edu/data/catalog/sx925dc9385.

    -

  • 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.

    -

  • 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/public/datasets/oxford_town_centre/index.html b/site/public/datasets/oxford_town_centre/index.html deleted file mode 100644 index 5379682c..00000000 --- a/site/public/datasets/oxford_town_centre/index.html +++ /dev/null @@ -1,146 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
-
TownCentre
- -
- Datasets - About -
-
-
- -
Oxford Town Centre is a dataset of surveillance camera footage from Cornmarket St Oxford, England
The Oxford Town Centre dataset includes approximately 2,200 identities and is used for research and development of face recognition systems -
-
Published
-
2011
-
-
Videos
-
1
-
-
Purpose
-
Person detection, gaze estimation
-
-
Funded by
-
EU FP6 Hermes project and Oxford Risk
-
-
Download Size
-
0.118 GB
-
-
Website
- -

Oxford Town Centre

-

The Oxford Town Centre dataset is a CCTV video of pedestrians in a busy downtown area in Oxford used for research and development of activity and face recognition systems. 1 The CCTV video was obtained from a public surveillance camera at the corner of Cornmarket and Market St. in Oxford, England and includes approximately 2,200 people. Since its publication in 2009 2 the Oxford Town Centre dataset has been used in over 80 verified research projects including commercial research by Amazon, Disney, OSRAM, and Huawei; and academic research in China, Israel, Russia, Singapore, the US, and Germany among dozens more.

-

The Oxford Town Centre dataset is unique in that it uses footage from a public surveillance camera that would otherwise be designated for public safety. The video shows that the pedestrians act normally and unrehearsed indicating they neither knew of or consented to participation in the research project.

-
-

Who used TownCentre?

- -

- 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. -

- -
- -
- -
-
- -
-
-
- -
- -

Biometric Trade Routes

- -

- To help understand how TownCentre has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Oxford Town Centre was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. -

- -
- -
-
-
- -
-
    -
  • Academic
    • -
  • Commercial
    • -
  • Military / Government
    • -
-
Citation data is collected using SemanticScholar.org then dataset usage verified and geolocated.
-
- - -
- -

Dataset Citations

-

- The dataset citations used in the visualizations were collected from Semantic Scholar, 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. -

- -
-
- -
-
-
-
- -

Supplementary Information

- -

Location

-

The street location of the camera used for the Oxford Town Centre dataset was confirmed by matching the road, benches, and store signs source. At that location, two public CCTV cameras exist mounted on the side of the Northgate House building at 13-20 Cornmarket St. Because of the lower camera's mounting pole directionality, a view from a private camera in the building across the street can be ruled out because it would have to show more of silhouette of the lower camera's mounting pole. Two options remain: either the public CCTV camera mounted to the side of the building was used or the researchers mounted their own camera to the side of the building in the same location. Because the researchers used many other existing public CCTV cameras for their research projects it is likely that they would also be able to access to this camera.

-

To discredit the theory that this public CCTV is only seen pointing the other way in Google Street View images, at least one public photo shows the upper CCTV camera pointing in the same direction as the Oxford Town Centre dataset proving the camera can and has been rotated before.

-

As for the capture date, the text on the storefront display shows a sale happening from December 2nd – 7th indicating the capture date was between or just before those dates. The capture year is either 2008 or 2007 since prior to 2007 the Carphone Warehouse (photo, history) did not exist at this location. Since the sweaters in the GAP window display are more similar to those in a GAP website snapshot from November 2007, our guess is that the footage was obtained during late November or early December 2007. The lack of street vendors and slight waste residue near the bench suggests that is was probably a weekday after rubbish removal.

-
Footage from this public CCTV camera was used to create the Oxford Town Centre dataset. Image sources: Google Street View (<a href="https://www.google.com/maps/@51.7528162,-1.2581152,3a,50.3y,310.59h,87.23t/data=!3m7!1e1!3m5!1s3FsGN-PqYC-VhQGjWgmBdQ!2e0!5s20120601T000000!7i13312!8i6656">map</a>)
Footage from this public CCTV camera was used to create the Oxford Town Centre dataset. Image sources: Google Street View (map)
Heat map body visualization of the pedestrians detected in the Oxford Town Centre dataset © megapixels.cc
Heat map body visualization of the pedestrians detected in the Oxford Town Centre dataset © megapixels.cc
Heat map face visualization of the pedestrians detected in the Oxford Town Centre dataset © megapixels.cc
Heat map face visualization of the pedestrians detected in the Oxford Town Centre dataset © megapixels.cc

Demo Videos Using Oxford Town Centre Dataset

-

Several researchers have posted their demo videos using the Oxford Town Centre dataset on YouTube:

- -
  • a

    Benfold, Ben and Reid, Ian. "Stable Multi-Target Tracking in Real-Time Surveillance Video". CVPR 2011. Pages 3457-3464.

    -
  • a

    "Guiding Visual Surveillance by Tracking Human Attention". 2009.

    -
- -
- - - - - \ No newline at end of file diff --git a/site/public/datasets/pipa/index.html b/site/public/datasets/pipa/index.html deleted file mode 100644 index 7a4fbc0e..00000000 --- a/site/public/datasets/pipa/index.html +++ /dev/null @@ -1,120 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
-
PIPA Dataset
- -
- Datasets - About -
-
-
- -
People in Photo Albums (PIPA) is a dataset...
[ add subdescrition ] -
-
Published
-
2015
-
-
Images
-
37,107
-
-
Identities
-
2,356
-
-
Purpose
-
Face recognition
-
-
Download Size
-
12 GB
-
-
Website
- -

People in Photo Albums

-

[ PAGE UNDER DEVELOPMENT ]

-
-

Who used PIPA Dataset?

- -

- 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. -

- -
- -
- -
-
- -
-
-
- -
- -

Biometric Trade Routes

- -

- To help understand how PIPA Dataset has been used around the world by commercial, military, and academic organizations; existing publicly available research citing People in Photo Albums Dataset was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. -

- -
- -
-
-
- -
-
    -
  • Academic
    • -
  • Commercial
    • -
  • Military / Government
    • -
-
Citation data is collected using SemanticScholar.org then dataset usage verified and geolocated.
-
- - -
- -

Dataset Citations

-

- The dataset citations used in the visualizations were collected from Semantic Scholar, 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. -

- -
-
- -
- - - - - \ No newline at end of file diff --git a/site/public/datasets/pubfig/index.html b/site/public/datasets/pubfig/index.html deleted file mode 100644 index c46eeea3..00000000 --- a/site/public/datasets/pubfig/index.html +++ /dev/null @@ -1,117 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
-
PubFig
- -
- Datasets - About -
-
-
- -
PubFig is a dataset...
[ add subdescrition ] -
-
Published
-
2009
-
-
Images
-
58,797
-
-
Identities
-
200
-
-
Purpose
-
mostly names from LFW but includes new names. large variation in pose, lighting, expression, scene, camera, imaging conditions and parameters
-
-
Website
- -

PubFig

-

[ PAGE UNDER DEVELOPMENT ]

-
-

Who used PubFig?

- -

- 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. -

- -
- -
- -
-
- -
-
-
- -
- -

Biometric Trade Routes

- -

- To help understand how PubFig has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Public Figures Face Dataset was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. -

- -
- -
-
-
- -
-
    -
  • Academic
    • -
  • Commercial
    • -
  • Military / Government
    • -
-
Citation data is collected using SemanticScholar.org then dataset usage verified and geolocated.
-
- - -
- -

Dataset Citations

-

- The dataset citations used in the visualizations were collected from Semantic Scholar, 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. -

- -
-
- -
- - - - - \ No newline at end of file diff --git a/site/public/datasets/uccs/index.html b/site/public/datasets/uccs/index.html deleted file mode 100644 index c9faac68..00000000 --- a/site/public/datasets/uccs/index.html +++ /dev/null @@ -1,255 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
-
UCCS
- -
- Datasets - About -
-
-
- -
UnConstrained College Students is a dataset of long-range surveillance photos of students at University of Colorado in Colorado Springs
The UnConstrained College Students dataset includes 16,149 images and 1,732 identities of subjects on University of Colorado Colorado Springs campus and is used for making face recognition and face detection algorithms -
-
Published
-
2018
-
-
Images
-
16,149
-
-
Identities
-
1,732
-
-
Purpose
-
Face recognition, face detection
-
-
Created by
-
University of Colorado Colorado Springs (US)
-
-
Funded by
-
ODNI, IARPA, ONR MURI, Amry SBIR, SOCOM SBIR
-
-
Website
- -

UnConstrained College Students

-

[ page under development ]

-

UnConstrained College Students (UCCS) is a dataset of long-range surveillance photos captured at University of Colorado Colorado Springs. According to the authors of two papers associated with the dataset, subjects were "photographed using a long-range high-resolution surveillance camera without their knowledge" 2. To create the dataset, the researchers used a Canon 7D digital camera fitted with a Sigma 800mm telephoto lens and photographed students 150–200m away through their office window. Photos were taken during the morning and afternoon while students were walking to and from classes. The primary uses of this dataset are to train, validate, and build recognition and face detection algorithms for realistic surveillance scenarios.

-

What makes the UCCS dataset unique is that it includes the highest resolution images of any publicly available face recognition dataset discovered so far (18MP), that it was captured on a campus without consent or awareness using a long-range telephoto lens, and that it was funded by United States defense and intelligence agencies.

-

Combined funding sources for the creation of the initial and final release of the dataset include ODNI (Office of Director of National Intelligence), IARPA (Intelligence Advance Research Projects Activity), ONR MURI (Office of Naval Research and The Department of Defense Multidisciplinary University Research Initiative), Army SBIR (Small Business Innovation Research), SOCOM SBIR (Special Operations Command and Small Business Innovation Research), and the National Science Foundation. 1 2

-

In 2017 the UCCS face dataset was used for a defense and intelligence agency funded face recognition challenge at the International Joint Biometrics Conference in Denver, CO. And in 2018 the dataset was used for the 2nd Unconstrained Face Detection and Open Set Recognition Challenge at the European Computer Vision Conference (ECCV) in Munich, Germany. Additional research projects that have used the UCCS dataset are included below in the list of verified citations.

-
-

Who used UCCS?

- -

- 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. -

- -
- -
- -
-
- -
-
-
- -
- -

Biometric Trade Routes

- -

- To help understand how UCCS has been used around the world by commercial, military, and academic organizations; existing publicly available research citing UnConstrained College Students Dataset was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. -

- -
- -
-
-
- -
-
    -
  • Academic
    • -
  • Commercial
    • -
  • Military / Government
    • -
-
Citation data is collected using SemanticScholar.org then dataset usage verified and geolocated.
-
- - -
- -

Dataset Citations

-

- The dataset citations used in the visualizations were collected from Semantic Scholar, 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. -

- -
-
- -
-
-
-
- -

Supplementary Information

- -

Dates and Times

-

The images in UCCS were taken on 18 non-consecutive days during 2012–2013. Analysis of the EXIF data embedded in original images reveal that most of the images were taken on Tuesdays, and the most frequent capture time throughout the week was 12:30PM.

-
UCCS photos captured per weekday © megapixels.cc
UCCS photos captured per weekday © megapixels.cc
UCCS photos captured per 10-minute intervals per weekday © megapixels.cc
UCCS photos captured per 10-minute intervals per weekday © megapixels.cc

UCCS photos taken in 2012

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
DatePhotos
Feb 23, 2012132
March 6, 2012288
March 8, 2012506
March 13, 2012160
March 20, 20121,840
March 22, 2012445
April 3, 20121,639
April 12, 201214
April 17, 201219
April 24, 201263
April 25, 201211
April 26, 201220
-

UCCS photos taken in 2013

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
DatePhotos
Jan 28, 20131,056
Jan 29, 20131,561
Feb 13, 2013739
Feb 19, 2013723
Feb 20, 2013965
Feb 26, 2013736
-

Location

-

The location of the camera and subjects can confirmed using several visual cues in the dataset images: the unique pattern of the sidewalk that is only used on the UCCS Pedestrian Spine near the West Lawn, the two UCCS sign poles with matching graphics still visible in Google Street View, the no parking sign and directionality of its arrow, the back of street sign next to it, the slight bend in the sidewalk, the presence of cars passing in the background of the image, and the far wall of the parking garage all match images in the dataset. The original papers also provides another clue: a picture of the camera inside the office that was used to create the dataset. The window view in this image provides another match for the brick pattern on the north facade of the Kraember Family Library and the green metal fence along the sidewalk. View the location on Google Maps

-
Location on campus where students were unknowingly photographed with a telephoto lens to be used for defense and intelligence agency funded research on face recognition. Image: Google Maps
Location on campus where students were unknowingly photographed with a telephoto lens to be used for defense and intelligence agency funded research on face recognition. Image: Google Maps
3D view showing the angle of view of the surveillance camera used for UCCS dataset. Image: Google Maps
3D view showing the angle of view of the surveillance camera used for UCCS dataset. Image: Google Maps

Funding

-

The UnConstrained College Students dataset is associated with two main research papers: "Large Scale Unconstrained Open Set Face Database" and "Unconstrained Face Detection and Open-Set Face Recognition Challenge". Collectively, these papers and the creation of the dataset have received funding from the following organizations:

-
    -
  • ONR (Office of Naval Research) MURI (The Department of Defense Multidisciplinary University Research Initiative) grant N00014-08-1-0638
    • -
  • Army SBIR (Small Business Innovation Research) grant W15P7T-12-C-A210
    • -
  • SOCOM (Special Operations Command) SBIR (Small Business Innovation Research) grant H92222-07-P-0020
    • -
  • National Science Foundation Grant IIS-1320956
    • -
  • ODNI (Office of Director of National Intelligence)
    • -
  • IARPA (Intelligence Advance Research Projects Activity) R&D contract 2014-14071600012
    • -
-

Opting Out

-

If you attended University of Colorado Colorado Springs and were captured by the long range surveillance camera used to create this dataset, there is unfortunately currently no way to be removed. The authors do not provide any options for students to opt-out nor were students informed they would be used for training face recognition. According to the authors, the lack of any consent or knowledge of participation is what provides part of the value of Unconstrained College Students Dataset.

-

Ethics

-

Please direct any questions about the ethics of the dataset to the University of Colorado Colorado Springs Ethics and Compliance Office

-

Technical Details

-

For further technical information about the dataset, visit the UCCS dataset project page.

-

Under Development

-
    -
  • adding more verified locations to map and charts
    • -
  • add EXIF file to CDN
    • -
-
  • a

    Sapkota, Archana and Boult, Terrance. "Large Scale Unconstrained Open Set Face Database." 2013.

    -
  • ab

    Günther, M. et. al. "Unconstrained Face Detection and Open-Set Face Recognition Challenge," 2018. Arxiv 1708.02337v3.

    -
- -
- - - - - \ No newline at end of file diff --git a/site/public/datasets/vgg_face2/index.html b/site/public/datasets/vgg_face2/index.html deleted file mode 100644 index 321fb203..00000000 --- a/site/public/datasets/vgg_face2/index.html +++ /dev/null @@ -1,142 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
-
Brainwash Dataset
- -
- Datasets - About -
-
-
- -
-
Published
-
2015
-
-
Images
-
11,917
-
-
Purpose
-
Head detection
-
-
Created by
-
Stanford University (US), Max Planck Institute for Informatics (DE)
-
-
Funded by
-
Max Planck Center for Visual Computing and Communication
-
-
Download Size
-
4.1 GB
-
-
Website
- -

VGG Face 2

-

[ page under development ]

-
-

Who used Brainwash Dataset?

- -

- 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. -

- -
- -
- -
-
- -
-
-
- -
- -

Biometric Trade Routes

- -

- To help understand how Brainwash Dataset has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Brainwash Dataset was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. -

- -
- -
-
-
- -
-
    -
  • Academic
    • -
  • Commercial
    • -
  • Military / Government
    • -
-
Citation data is collected using SemanticScholar.org then dataset usage verified and geolocated.
-
- - -
- -

Dataset Citations

-

- The dataset citations used in the visualizations were collected from Semantic Scholar, 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. -

- -
-

(ignore) research notes

-
    -
  • The VGG Face 2 dataset includes approximately 1,331 actresses, 139 presidents, 16 wives, 3 husbands, 2 snooker player, and 1 guru
    • -
  • The original VGGF2 name list has been updated with the results returned from Google Knowledge
    • -
  • Names with a similarity score greater than 0.75 where automatically updated. Scores computed using import difflib; seq = difflib.SequenceMatcher(a=a.lower(), b=b.lower()); score = seq.ratio()
    • -
  • The 97 names with a score of 0.75 or lower were manually reviewed and includes name changes validating using Wikipedia.org results for names such as "Bruce Jenner" to "Caitlyn Jenner", spousal last-name changes, and discretionary changes to improve search results such as combining nicknames with full name when appropriate, for example changing "Aleksandar Petrović" to "Aleksandar 'Aco' Petrović" and minor changes such as "Mohammad Ali" to "Muhammad Ali"
    • -
  • The 'Description' text was automatically added when the Knowledge Graph score was greater than 250
    • -
-

TODO

-
    -
  • create name list, and populate with Knowledge graph information like LFW
    • -
  • make list of interesting number stats, by the numbers
    • -
  • make list of interesting important facts
    • -
  • write intro abstract
    • -
  • write analysis of usage
    • -
  • find examples, citations, and screenshots of useage
    • -
  • find list of companies using it for table
    • -
  • create montages of the dataset, like LFW
    • -
  • create right to removal information
    • -
-
- -
- - - - - \ No newline at end of file diff --git a/site/public/datasets/viper/index.html b/site/public/datasets/viper/index.html deleted file mode 100644 index ffce01fe..00000000 --- a/site/public/datasets/viper/index.html +++ /dev/null @@ -1,122 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
-
VIPeR
- -
- Datasets - About -
-
-
- -
VIPeR is a person re-identification dataset of images captured at UC Santa Cruz in 2007
VIPeR contains 1,264 images and 632 persons on the UC Santa Cruz campus and is used to train person re-identification algorithms for surveillance -
-
Published
-
2007
-
-
Images
-
1,264
-
-
Identities
-
632
-
-
Purpose
-
Person re-identification
-
-
Created by
-
University of California Santa Cruz
-
-
Website
- -

VIPeR Dataset

-

[ page under development ]

-

VIPeR (Viewpoint Invariant Pedestrian Recognition) is a dataset of pedestrian images captured at University of California Santa Cruz in 2007. Accoriding to the reserachers 2 "cameras were placed in different locations in an academic setting and subjects were notified of the presence of cameras, but were not coached or instructed in any way."

-

VIPeR is amongst the most widely used publicly available person re-identification datasets. In 2017 the VIPeR dataset was combined into a larger person re-identification created by the Chinese University of Hong Kong called PETA (PEdesTrian Attribute).

-
-

Who used VIPeR?

- -

- 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. -

- -
- -
- -
-
- -
-
-
- -
- -

Biometric Trade Routes

- -

- To help understand how VIPeR has been used around the world by commercial, military, and academic organizations; existing publicly available research citing Viewpoint Invariant Pedestrian Recognition was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. -

- -
- -
-
-
- -
-
    -
  • Academic
    • -
  • Commercial
    • -
  • Military / Government
    • -
-
Citation data is collected using SemanticScholar.org then dataset usage verified and geolocated.
-
- - -
- -

Dataset Citations

-

- The dataset citations used in the visualizations were collected from Semantic Scholar, 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. -

- -
-
- -
- - - - - \ No newline at end of file diff --git a/site/public/datasets/youtube_celebrities/index.html b/site/public/datasets/youtube_celebrities/index.html deleted file mode 100644 index b19add4e..00000000 --- a/site/public/datasets/youtube_celebrities/index.html +++ /dev/null @@ -1,113 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
-
YouTube Celebrities
- -
- Datasets - About -
-
-
- -

YouTube Celebrities

-

[ page under development ]

-
-

Who used YouTube Celebrities?

- -

- 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. -

- -
- -
- -
-
- -
-
-
- -
- -

Biometric Trade Routes

- -

- To help understand how YouTube Celebrities has been used around the world by commercial, military, and academic organizations; existing publicly available research citing YouTube Celebrities was collected, verified, and geocoded to show the biometric trade routes of people appearing in the images. Click on the markers to reveal research projects at that location. -

- -
- -
-
-
- -
-
    -
  • Academic
    • -
  • Commercial
    • -
  • Military / Government
    • -
-
Citation data is collected using SemanticScholar.org then dataset usage verified and geolocated.
-
- - -
- -

Dataset Citations

-

- The dataset citations used in the visualizations were collected from Semantic Scholar, 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. -

- -
-

Notes...

-
    -
  • Selected dataset sequences: (a) MBGC, (b) CMU MoBo, (c) First -Honda/UCSD, and (d) YouTube Celebrities.
    • -
  • This research is supported by the Central Intelligence Agency, the Biometrics -Task Force and the Technical Support Working Group through US Army contract -W91CRB-08-C-0093. The opinions, (cid:12)ndings, and conclusions or recommendations -expressed in this publication are those of the authors and do not necessarily re(cid:13)ect -the views of our sponsors.
    • -
  • in "Face Recognition From Video Draft 17"
    • -
  • International Journal of Pattern Recognition and Artifcial Intelligence WorldScientific Publishing Company
    • -
-
- -
- - - - - \ No newline at end of file diff --git a/site/public/index.html b/site/public/index.html deleted file mode 100644 index 118814be..00000000 --- a/site/public/index.html +++ /dev/null @@ -1,39 +0,0 @@ - - - - MegaPixels - - - - - - - - - - -
- - -
MegaPixels
- -
- DATASETS - ABOUT -
-
-
-
-
- - - - \ No newline at end of file diff --git a/site/public/info/index.html b/site/public/info/index.html deleted file mode 100644 index 749c29ba..00000000 --- a/site/public/info/index.html +++ /dev/null @@ -1,50 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
- - -
- Datasets - About -
-
-
- -

Face Analysis

-

Results are only stored for the duration of the analysis and are deleted when you leave this page.

-
- -
- - - - - \ No newline at end of file diff --git a/site/public/research/00_introduction/index.html b/site/public/research/00_introduction/index.html deleted file mode 100644 index 353e3270..00000000 --- a/site/public/research/00_introduction/index.html +++ /dev/null @@ -1,101 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
- - -
- Datasets - About -
-
-
- -
-

00: Introduction

-
-
-
Posted
-
2018-12-15
-
-
-
By
-
Megapixels
-
- -
-
- -
Posted
Dec. 15
Author
Adam Harvey

Facial recognition is a scam.

-

During the last 20 years commericial, academic, and governmental agencies have promoted the false dream of a future with face recognition. This essay debunks the popular myth that such a thing ever existed.

-

There is no such thing as face recognition. For the last 20 years, government agencies, commercial organizations, and academic institutions have played the public as a fool, selling a roadmap of the future that simply does not exist. Facial recognition, as it is currently defined, promoted, and sold to the public, government, and commercial sector is a scam.

-

Committed to developing robust solutions with superhuman accuracy, the industry has repeatedly undermined itself by never actually developing anything close to "face recognition".

-

There is only biased feature vector clustering and probabilistic thresholding.

-

Motivation

-

Ever since government agencies began developing face recognition in the early 1960's, datasets of face images have always been central to developing and validating face recognition technologies. Today, these datasets no longer originate in labs, but instead from family photo albums posted on photo sharing sites, surveillance camera footage from college campuses, search engine queries for celebrities, cafe livestreams, or videos on YouTube.

-

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.

-

While many of these datasets include public figures such as politicians, athletes, and actors; they also include many non-public figures: digital activists, students, pedestrians, and semi-private shared photo albums are all considered "in the wild" and fair game for research projects. Some images are used with creative commons licenses, yet others were taken in unconstrained scenarios without awareness or consent. At first glance it appears many of the datasets were created for seemingly harmless academic research, but when examined further it becomes clear that they're also used by foreign defense agencies.

-

The MegaPixels site is based on an earlier installation (also supported by Mozilla) at the Tactical Tech Glassroom in London in 2017; and a commission from the Elevate arts festival curated by Berit Gilma about pedestrian recognition datasets in 2018, and research during CV Dazzle from 2010-2015. Through the many prototypes, conversations, pitches, PDFs, and false starts this project has endured during the last 5 years, it eventually evolved into something much different than originally imagined. Now, as datasets become increasingly influential in shaping the computational future, it's clear that they must be critically analyzed to understand the biases, shortcomings, funding sources, and contributions to the surveillance industry. However, it's misguided to only criticize these datasets for their flaws without also praising their contribution to society. Without publicly available facial analysis datasets there would be less public discourse, less open-source software, and less peer-reviewed research. Public datasets can indeed become a vital public good for the information economy but as this projects aims to illustrate, many ethical questions arise about consent, intellectual property, surveillance, and privacy.

- - - - - -

Ever since the first computational facial recognition research project by the CIA in the early 1960s, data has always played a vital role in the development of our biometric future. Without facial recognition datasets there would be no facial recognition. Datasets are an indispensable part of any artificial intelligence system because, as Geoffrey Hinton points out:

-

Our relationship to computers has changed. Instead of programming them, we now show them and they figure it out. - Geoffrey Hinton

-
-

Algorithms learn from datasets. And we program algorithms by building datasets. But datasets aren't like code. There's no programming language made of data except for the data itself.

-

Ignore content below these lines

-

It was the early 2000s. Face recognition was new and no one seemed sure exactly how well it was going to perform in practice. In theory, face recognition was poised to be a game changer, a force multiplier, a strategic military advantage, a way to make cities safer and to secure borders. This was the future John Ashcroft demanded with the Total Information Awareness act of the 2003 and that spooks had dreamed of for decades. It was a future that academics at Carnegie Mellon Universtiy and Colorado State University would help build. It was also a future that celebrities would play a significant role in building. And to the surprise of ordinary Internet users like myself and perhaps you, it was a future that millions of Internet users would unwittingly play role in creating.

-

Now the future has arrived and it doesn't make sense. Facial recognition works yet it doesn't actually work. Facial recognition is cheap and accessible but also expensive and out of control. Facial recognition research has achieved headline grabbing superhuman accuracies over 99.9% yet facial recognition is also dangerously inaccurate. During a trial installation at Sudkreuz station in Berlin in 2018, 20% of the matches were wrong, a number so low that it should not have any connection to law enforcement or justice. And in London, the Metropolitan police had been using facial recognition software that mistakenly identified an alarming 98% of people as criminals 1, which perhaps is a crime itself.

-

MegaPixels is an online art project that explores the history of facial recognition from the perspective of datasets. To paraphrase the artist Trevor Paglen, whoever controls the dataset controls the meaning. MegaPixels aims to unravel the meanings behind the data and expose the darker corners of the biometric industry that have contributed to its growth. MegaPixels does not start with a conclusion, a moralistic slant, or a

-

Whether or not to build facial recognition was a question that can no longer be asked. As an outspoken critic of face recognition I've developed, and hopefully furthered, my understanding during the last 10 years I've spent working with computer vision. Though I initially disagreed, I've come to see technocratic perspective as a non-negotiable reality. As Oren (nytimes article) wrote in NYT Op-Ed "the horse is out of the barn" and the only thing we can do collectively or individually is to steer towards the least worse outcome. Computational communication has entered a new era and it's both exciting and frightening to explore the potentials and opportunities. In 1997 getting access to 1 teraFLOPS of computational power would have cost you $55 million and required a strategic partnership with the Department of Defense. At the time of writing, anyone can rent 1 teraFLOPS on a cloud GPU marketplace for less than $1/day. 2.

-

I hope that this project will illuminate the darker areas of strange world of facial recognition that have not yet received attention and encourage discourse in academic, industry, and . By no means do I believe discourse can save the day. Nor do I think creating artwork can. In fact, I'm not exactly sure what the outcome of this project will be. The project is not so much what I publish here but what happens after. This entire project is only a prologue.

-

As McLuhan wrote, "You can't have a static, fixed position in the electric age". And in our hyper-connected age of mass surveillance, artificial intelligece, and unevenly distributed virtual futures the most irrational thing to be is rational. Increasingly the world is becoming a contradiction where people use surveillance to protest surveillance, use

-

Like many projects, MegaPixels had spent years meandering between formats, unfeasible budgets, and was generally too niche of a subject. The basic idea for this project, as proposed to the original Glass Room installation in 2016 in NYC, was to build an interactive mirror that showed people if they had been included in the LFW facial recognition dataset. The idea was based on my reaction to all the datasets I'd come across during research for the CV Dazzle project. I'd noticed strange datasets created for training and testing face detection algorithms. Most were created in labratory settings and their interpretation of face data was very strict.

-

for other post

-

It was the early 2000s. Face recognition was new and no one seemed sure how well it was going to perform in practice. In theory, face recognition was poised to be a game changer, a force multiplier, a strategic military advantage, a way to make cities safer and to secure the borders. It was the future that John Ashcroft demanded with the Total Information Awareness act of the 2003. It was a future that academics helped build. It was a future that celebrities helped build. And it was a future that

-

A decade earlier the Department of Homeland Security and the Counterdrug Technology Development Program Office initated a feasibilty study called FERET (FacE REcognition Technology) to "develop automatic face recognition capabilities that could be employed to assist security, intelligence, and law enforcement personnel in the performance of their duties [^feret_website]."

-

One problem with FERET dataset was that the photos were in controlled settings. For face recognition to work it would have to be used in uncontrolled settings. Even newer datasets such as the Multi-PIE (Pose, Illumination, and Expression) from Carnegie Mellon University included only indoor photos of cooperative subjects. Not only were the photos completely unrealistic, CMU's Multi-Pie included only 18 individuals and cost $500 for academic use [^cmu_multipie_cost], took years to create, and required consent from every participant.

-

Add progressive gan of FERET

-
-
-

  1. Sharman, Jon. "Metropolitan Police's facial recognition technology 98% inaccurate, figures show". 2018. https://www.independent.co.uk/news/uk/home-news/met-police-facial-recognition-success-south-wales-trial-home-office-false-positive-a8345036.html↩

    2. -

  2. Calle, Dan. "Supercomptuers". 1997. http://ei.cs.vt.edu/~history/SUPERCOM.Calle.HTML↩

    3. -
-
-
- -
- - - - - \ No newline at end of file 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 deleted file mode 100644 index 9426ef0f..00000000 --- a/site/public/research/01_from_1_to_100_pixels/index.html +++ /dev/null @@ -1,139 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
- - -
- Datasets - About -
-
-
- -
-

From 1 to 100 Pixels

-
-
-
Posted
-
2018-12-04
-
-
-
By
-
Adam Harvey
-
- -
-
- -

High resolution insights from low resolution data

-

This post will be about the meaning of "face". How do people define it? How to biometrics researchers define it? How has it changed during the last decade.

-

What can you know from a very small amount of information?

-
    -
  • 1 pixel grayscale
    • -
  • 2x2 pixels grayscale, font example, can encode letters
    • -
  • 3x3 pixels: can create a font
    • -
  • 4x4 pixels: how many variations
    • -
  • 8x8 yotta yotta, many more variations
    • -
  • 5x7 face recognition
    • -
  • 12x16 activity recognition
    • -
  • 6/5 (up to 124/106) pixels in height/width, and the average is 24/20 for QMUL SurvFace
    • -
  • (prepare a Progan render of the QMUL dataset and TinyFaces)
    • -
  • 20x16 tiny faces paper
    • -
  • 20x20 MNIST handwritten images http://yann.lecun.com/exdb/mnist/
    • -
  • 24x24 haarcascade detector idealized images
    • -
  • 32x32 CIFAR image dataset
    • -
  • 40x40 can do emotion detection, face recognition at scale, 3d modeling of the face. include datasets with faces at this resolution including pedestrian.
    • -
  • NIST standards begin to appear from 40x40, distinguish occular pixels
    • -
  • need more material from 60-100
    • -
  • 60x60 show how texture emerges and pupils, eye color, higher resolution of features and compare to lower resolution faces
    • -
  • 100x100 all you need for medical diagnosis
    • -
  • 100x100 0.5% of one Instagram photo
    • -
-

Ideas:

-
    -
  • Find specific cases of facial resolution being used in legal cases, forensic investigations, or military footage
    • -
  • resolution of boston bomber face
    • -
  • resolution of the state of the union image
    • -
-

Research

-
    -
  • NIST report on sres states several resolutions
    • -
  • "Results show that the tested face recognition systems yielded similar performance for query sets with eye-to-eye distance from 60 pixels to 30 pixels" 1
    • -
-
    -
  • "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

-
-
-

  1. NIST 906932. Performance Assessment of Face Recognition Using Super-Resolution. Shuowen Hu, Robert Maschal, S. Susan Young, Tsai Hong Hong, Jonathon P. Phillips↩

    2. -
-
-
- -
- - - - - \ No newline at end of file diff --git a/site/public/research/02_what_computers_can_see/index.html b/site/public/research/02_what_computers_can_see/index.html deleted file mode 100644 index 920f78cc..00000000 --- a/site/public/research/02_what_computers_can_see/index.html +++ /dev/null @@ -1,310 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
- - -
- Datasets - About -
-
-
- -
-

What Computers Can See

-
-
-
Posted
-
2018-12-15
-
-
-
By
-
Adam Harvey
-
- -
-
- -

A list of 100 things computer vision can see, eg:

-
    -
  • age, race, gender, ancestral origin, body mass index
    • -
  • eye color, hair color, facial hair, glasses
    • -
  • beauty score,
    • -
  • intelligence
    • -
  • what you're looking at
    • -
  • medical conditions
    • -
  • tired, drowsiness in car
    • -
  • affectiva: interest in product, intent to buy
    • -
-

From PubFig Dataset

-
    -
  • Male
    • -
  • Asian
    • -
  • White
    • -
  • Black
    • -
  • Baby
    • -
  • Child
    • -
  • Youth
    • -
  • Middle Aged
    • -
  • Senior
    • -
  • Black Hair
    • -
  • Blond Hair
    • -
  • Brown Hair
    • -
  • Bald
    • -
  • No Eyewear
    • -
  • Eyeglasses
    • -
  • Sunglasses
    • -
  • Mustache
    • -
  • Smiling Frowning
    • -
  • Chubby
    • -
  • Blurry
    • -
  • Harsh Lighting
    • -
  • Flash
    • -
  • Soft Lighting
    • -
  • Outdoor Curly Hair
    • -
  • Wavy Hair
    • -
  • Straight Hair
    • -
  • Receding Hairline
    • -
  • Bangs
    • -
  • Sideburns
    • -
  • Fully Visible Forehead
    • -
  • Partially Visible Forehead
    • -
  • Obstructed Forehead
    • -
  • Bushy Eyebrows
    • -
  • Arched Eyebrows
    • -
  • Narrow Eyes
    • -
  • Eyes Open
    • -
  • Big Nose
    • -
  • Pointy Nose
    • -
  • Big Lips
    • -
  • Mouth Closed
    • -
  • Mouth Slightly Open
    • -
  • Mouth Wide Open
    • -
  • Teeth Not Visible
    • -
  • No Beard
    • -
  • Goatee
    • -
  • Round Jaw
    • -
  • Double Chin
    • -
  • Wearing Hat
    • -
  • Oval Face
    • -
  • Square Face
    • -
  • Round Face
    • -
  • Color Photo
    • -
  • Posed Photo
    • -
  • Attractive Man
    • -
  • Attractive Woman
    • -
  • Indian
    • -
  • Gray Hair
    • -
  • Bags Under Eyes
    • -
  • Heavy Makeup
    • -
  • Rosy Cheeks
    • -
  • Shiny Skin
    • -
  • Pale Skin
    • -
  • 5 o' Clock Shadow
    • -
  • Strong Nose-Mouth Lines
    • -
  • Wearing Lipstick
    • -
  • Flushed Face
    • -
  • High Cheekbones
    • -
  • Brown Eyes
    • -
  • Wearing Earrings
    • -
  • 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

-

The 27 attributes are:

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
attributerepresentation in filelabel
gendergendermale(1), female(2)
hair lengthhairshort hair(1), long hair(2)
sleeve lengthuplong sleeve(1), short sleeve(2)
length of lower-body clothingdownlong lower body clothing(1), short(2)
type of lower-body clothingclothesdress(1), pants(2)
wearing hathatno(1), yes(2)
carrying backpackbackpackno(1), yes(2)
carrying bagbagno(1), yes(2)
carrying handbaghandbagno(1), yes(2)
ageageyoung(1), teenager(2), adult(3), old(4)
8 color of upper-body clothingupblack, upwhite, upred, uppurple, upyellow, upgray, upblue, upgreenno(1), yes(2)
9 color of lower-body clothingdownblack, downwhite, downpink, downpurple, downyellow, downgray, downblue, downgreen,downbrownno(1), yes(2)
-

source: https://github.com/vana77/Market-1501_Attribute/blob/master/README.md

-

From DukeMTMC

-

The 23 attributes are:

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
attributerepresentation in filelabel
gendergendermale(1), female(2)
length of upper-body clothingtopshort upper body clothing(1), long(2)
wearing bootsbootsno(1), yes(2)
wearing hathatno(1), yes(2)
carrying backpackbackpackno(1), yes(2)
carrying bagbagno(1), yes(2)
carrying handbaghandbagno(1), yes(2)
color of shoesshoesdark(1), light(2)
8 color of upper-body clothingupblack, upwhite, upred, uppurple, upgray, upblue, upgreen, upbrownno(1), yes(2)
7 color of lower-body clothingdownblack, downwhite, downred, downgray, downblue, downgreen, downbrownno(1), yes(2)
-

source: https://github.com/vana77/DukeMTMC-attribute/blob/master/README.md

-

From H3D Dataset

-

The joints and other keypoints (eyes, ears, nose, shoulders, elbows, wrists, hips, knees and ankles) -The 3D pose inferred from the keypoints. -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/

-

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/public/research/index.html b/site/public/research/index.html deleted file mode 100644 index 1be8203f..00000000 --- a/site/public/research/index.html +++ /dev/null @@ -1,49 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
- - -
- Datasets - About -
-
-
- -

Research Blog

-
- -
- - - - - \ No newline at end of file diff --git a/site/public/test/chart/index.html b/site/public/test/chart/index.html deleted file mode 100644 index e882ecc5..00000000 --- a/site/public/test/chart/index.html +++ /dev/null @@ -1,50 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
- - -
- Datasets - About -
-
-
- -

Chart

-

← Back to test index

-
- -
- - - - - \ No newline at end of file diff --git a/site/public/test/citations/index.html b/site/public/test/citations/index.html deleted file mode 100644 index a8af41df..00000000 --- a/site/public/test/citations/index.html +++ /dev/null @@ -1,50 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
- - -
- Datasets - About -
-
-
- -

Citations

-

← Back to test index

-
- -
- - - - - \ No newline at end of file diff --git a/site/public/test/csv/index.html b/site/public/test/csv/index.html deleted file mode 100644 index 2c2242b4..00000000 --- a/site/public/test/csv/index.html +++ /dev/null @@ -1,50 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
- - -
- Datasets - About -
-
-
- -

CSV Test

-

← Back to test index

-
- -
- - - - - \ No newline at end of file diff --git a/site/public/test/datasets/index.html b/site/public/test/datasets/index.html deleted file mode 100644 index bf08418f..00000000 --- a/site/public/test/datasets/index.html +++ /dev/null @@ -1,50 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
- - -
- Datasets - About -
-
-
- -

Index of datasets

-

← Back to test index

-
- -
- - - - - \ No newline at end of file diff --git a/site/public/test/face_search/index.html b/site/public/test/face_search/index.html deleted file mode 100644 index 75bb907b..00000000 --- a/site/public/test/face_search/index.html +++ /dev/null @@ -1,50 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
- - -
- Datasets - About -
-
-
- -

Face search

-

← Back to test index

-
- -
- - - - - \ No newline at end of file diff --git a/site/public/test/gallery/index.html b/site/public/test/gallery/index.html deleted file mode 100644 index 8958f369..00000000 --- a/site/public/test/gallery/index.html +++ /dev/null @@ -1,68 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
- - -
- Datasets - About -
-
-
- -

Gallery test

-

← Back to test index

-
Modal image 1
Modal image 1
-
Modal image 2
Modal image 2
-
Modal image 3
Modal image 3

Test table

- - - - - - - - - - - - - - -
Col1Col2Col3
Content1Content2Content3
-
- -
- - - - - \ No newline at end of file diff --git a/site/public/test/index.html b/site/public/test/index.html deleted file mode 100644 index e660bb2d..00000000 --- a/site/public/test/index.html +++ /dev/null @@ -1,61 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
- - -
- Datasets - About -
-
-
- -

Megapixels UI Tests

- -
- -
- - - - - \ No newline at end of file diff --git a/site/public/test/map/index.html b/site/public/test/map/index.html deleted file mode 100644 index 21229ec1..00000000 --- a/site/public/test/map/index.html +++ /dev/null @@ -1,50 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
- - -
- Datasets - About -
-
-
- -

Map test

-

← Back to test index

-
- -
- - - - - \ No newline at end of file diff --git a/site/public/test/name_search/index.html b/site/public/test/name_search/index.html deleted file mode 100644 index b0bdb86f..00000000 --- a/site/public/test/name_search/index.html +++ /dev/null @@ -1,50 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
- - -
- Datasets - About -
-
-
- -

Name search

-

← Back to test index

-
- -
- - - - - \ No newline at end of file diff --git a/site/public/test/pie_chart/index.html b/site/public/test/pie_chart/index.html deleted file mode 100644 index 98a89ff4..00000000 --- a/site/public/test/pie_chart/index.html +++ /dev/null @@ -1,50 +0,0 @@ - - - - MegaPixels - - - - - - - - - - - -
- - -
MegaPixels
- - -
- Datasets - About -
-
-
- -

Pie Chart

-

← Back to test index

-
- -
- - - - - \ No newline at end of file -- cgit v1.2.3-70-g09d2