Home

Awesome

awesome-Face_Recognition

this collecting the papers (mainly from arxiv.org) about bellow themes:

also, some papers and links collected from:


Face Detection && Face Segmentation

2008

2010

2011

2012

2013

2014

2015

2016

2017

2018

2019

2020

2021

2022

2023


Face Alignment

2012

2013

2014

2015

2016

2017

2018

2019

2020

2021

2022

2023


Face recognition && Face Representations

2008

2009

2010

2011

2012

2013

2014

2015

2016

2017

2018

2019

2020

2021

2022

2023


Face(Facial) Attribute && Face(Facial) Analysis && Face Quality && Face Parsing

2012

2014

2015

2016

2017

2018

2019

2020

2021

2022

2023


Face Reconstruction && Face 3D

2015

2016

2017

2018

2019

2020

2021

2022

2023


Face Tracking


Face Clustering


Face Super-Resolution && Face Deblurring && Face Hallucination


Face Generation && Face Synthesis && Face Completion && Face Restoration && Face De-Occlusion && Face Reenactment

2010

2013

2014

2015

2016

2017

2018

2019

2020

2021

2022

2023


Face Transfer && Face Editing

Face Swapping


Face Anti-Spoofing && Face Attack && Face Privacy

2020

2021

2022

2023


Face Retrieval

2008

2012

2014

2016

2017

2018

2019

2021

Face Application

2019

2020

2021

2022

2023

Model Acceleration && Model Compression

Others


Piplines


DataSets

2D face recognition

DatasetsDescriptionLinksPublish Time
CASIA-WebFace10,575 subjects and 494,414 imagesDownload2014
MegaFace🏅1 million faces, 690K identitiesDownload2016
MS-Celeb-1M🏅about 10M images for 100K celebrities Concrete measurement to evaluate the performance of recognizing one million celebritiesDownload2016
LFW🏅13,000 images of faces collected from the web. Each face has been labeled with the name of the person pictured. 1680 of the people pictured have two or more distinct photos in the data set.Download2007
VGG Face2🏅The dataset contains 3.31 million images of 9131 subjects (identities), with an average of 362.6 images for each subject.Download2017
UMDFaces Dataset-image367,888 face annotations for 8,277 subjects.Download2016
Trillion Pairs🏅Train: MS-Celeb-1M-v1c & Asian-Celeb Test: ELFW&DELFWDownload2018
FaceScrubIt comprises a total of 106,863 face images of male and female 530 celebrities, with about 200 images per person.Download2014
Mut1ny🏅head/face segmentation dataset contains over 17.3k labeled imagesDownload2018
IMDB-FaceThe dataset contains about 1.7 million faces, 59k identities, which is manually cleaned from 2.0 million raw images.Download2018

video face recognition

DatasetsDescriptionLinksPublish Time
YouTube Face🏅The data set contains 3,425 videos of 1,595 different people.Download2011
UMDFaces Dataset-video🏅Over 3.7 million annotated video frames from over 22,000 videos of 3100 subjects.Download2017
PaSCThe challenge includes 9,376 still images and 2,802 videos of 293 people.Download2013
YTCThe data consists of two parts: video clips (1910 sequences of 47 subjects) and initialization data(initial frame face bounding boxes, manually marked).Download2008
iQIYI-VID🏅The iQIYI-VID dataset contains 500,000 videos clips of 5,000 celebrities, adding up to 1000 hours. This dataset supplies multi-modal cues, including face, cloth, voice, gait, and subtitles, for character identification.Download2018

3D face recognition

DatasetsDescriptionLinksPublish Time
Bosphorus🏅105 subjects and 4666 faces 2D & 3D face dataDownload2008
BD-3DFEAnalyzing Facial Expressions in 3D SpaceDownload2006
ND-2006422 subjects and 9443 faces 3D Face RecognitionDownload2006
FRGC V2.0466 subjects and 4007 of 3D Face, Visible Face ImagesDownload2005
B3D(AC)^21000 high quality, dynamic 3D scans of faces, recorded while pronouncing a set of English sentences.Download2010

Anti-spoofing

Datasets# of subj. / # of sess.LinksYearSpoof attacks attacksPublish Time
NUAA15/3Download2010Print2010
CASIA-MFSD50/3Download(link failed)2012Print, Replay2012
Replay-Attack50/1Download2012Print, 2 Replay2012
MSU-MFSD35/1Download2015Print, 2 Replay2015
MSU-USSA1140/1Download20162 Print, 6 Replay2016
Oulu-NPU55/3Download20172 Print, 6 Replay2017
Siw165/4Download20182 Print, 4 Replay2018

cross age and cross pose

DatasetsDescriptionLinksPublish Time
CACD2000The dataset contains more than 160,000 images of 2,000 celebrities with age ranging from 16 to 62.Download2014
FGNetThe dataset contains more than 1002 images of 82 people with age ranging from 0 to 69.Download2000
MPRPHThe MORPH database contains 55,000 images of more than 13,000 people within the age ranges of 16 to 77Download2016
CPLFWwe construct a Cross-Pose LFW (CPLFW) which deliberately searches and selects 3,000 positive face pairs with pose difference to add pose variation to intra-class variance.Download2017
CALFWThereby we construct a Cross-Age LFW (CALFW) which deliberately searches and selects 3,000 positive face pairs with age gaps to add aging process intra-class variance.Download2017

📌Face Detection

DatasetsDescriptionLinksPublish Time
FDDB🏅5171 faces in a set of 2845 imagesDownload2010
Wider-face32,203 images and label 393,703 faces with a high degree of variability in scale, pose and occlusion, organized based on 61 event classesDownload2015
AFWAFW dataset is built using Flickr images. It has 205 images with 473 labeled faces. For each face, annotations include a rectangular bounding box, 6 landmarks and the pose angles.Download2013
MALFMALF is the first face detection dataset that supports fine-gained evaluation. MALF consists of 5,250 images and 11,931 faces.Download2015

📌 Face Attributes

DatasetsDescriptionLinksKey featuresPublish Time
CelebA10,177 number of identities, 202,599 number of face images, and 5 landmark locations, 40 binary attributes annotations per image.Downloadattribute & landmark2015
IMDB-WIKI500k+ face images with age and gender labelsDownloadage & gender2015
AdienceUnfiltered faces for gender and age classificationDownloadage & gender2014
WFLW🏅WFLW contains 10000 faces (7500 for training and 2500 for testing) with 98 fully manual annotated landmarks.Downloadlandmarks2018
Caltech10k Web FacesThe dataset has 10,524 human faces of various resolutions and in different settingsDownloadlandmarks2005
EmotioNetThe EmotioNet database includes950,000 images with annotated AUs. A subset of the images in the EmotioNet database correspond to basic and compound emotions.DownloadAU and Emotion2017
RAF( Real-world Affective Faces)29672 number of real-world images, including 7 classes of basic emotions and 12 classes of compound emotions, 5 accurate landmark locations, 37 automatic landmark locations, race, age range and gender attributes annotations per imageDownloadEmotions、landmark、race、age and gender2017

📌 Others:

DatasetsDescriptionLinksPublish Time
IJB C/B/A🏅IJB C/B/A is currently running three challenges related to face detection, verification, identification, and identity clustering.Download2015
MOBIObi-modal (audio and video) data taken from 152 people.Download2012
BANCAThe BANCA database was captured in four European languages in two modalities (face and voice).Download2014
3D Mask Attack76500 frames of 17 persons using Kinect RGBD with eye positions (Sebastien Marcel).Download2013
WebCaricature6042 caricatures and 5974 photographs from 252 persons collected from the webDownload2018