Statements (29)
Predicate | Object |
---|---|
gptkbp:instanceOf |
facial recognition system
|
gptkbp:accuracy |
97.35%
|
gptkbp:application |
face identification
face verification |
gptkbp:architecture |
nine-layer deep neural network
|
gptkbp:author |
gptkb:Marc'Aurelio_Ranzato
gptkb:Ming_Yang Lior Wolf Yaniv Taigman |
gptkbp:comparesTo |
human-level performance
|
gptkbp:developedBy |
gptkb:Facebook
|
https://www.w3.org/2000/01/rdf-schema#label |
DeepFace
|
gptkbp:input |
face images
|
gptkbp:introducedIn |
2014
|
gptkbp:language |
gptkb:Python
|
gptkbp:notableFor |
closing the gap to human-level face verification accuracy
|
gptkbp:notablePublication |
DeepFace: Closing the Gap to Human-Level Performance in Face Verification
|
gptkbp:output |
face representations
|
gptkbp:publicationDate |
2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
|
gptkbp:relatedTo |
gptkb:artificial_intelligence
computer vision face recognition |
gptkbp:trainer |
4 million facial images
4,000 identities |
gptkbp:uses |
convolutional neural networks
deep learning 3D face alignment |
gptkbp:bfsParent |
gptkb:Kalman_Taigman
|
gptkbp:bfsLayer |
7
|