From face images and attributes to attributes
OPEN ACCESS
Author / Producer
Date
2017
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
OPEN ACCESS
Data
Rights / License
Abstract
The face is an important part of the identity of a person. Numerous applications benefit from the recent advances in prediction of face attributes, including biometrics (like age, gender, ethnicity) and accessories (eyeglasses, hat). We study the attributes’ relations to other attributes and to face images and propose prediction models for them. We show that handcrafted features can be as good as deep features, that the attributes themselves are powerful enough to predict other attributes and that clustering the samples according to their attributes can mitigate the training complexity for deep learning. We set new state-of-the-art results on two of the largest datasets to date, CelebA and Facebook BIG5, by predicting attributes either from face images, from other attributes, or from both face and other attributes. Particularly, on Facebook dataset, we show that we can accurately predict personality traits (BIG5) from tens of ‘likes’ or from only a profile picture and a couple of ‘likes’ comparing positively to human reference.
Permanent link
Publication status
published
External links
Book title
Computer Vision – ACCV 2016
Journal / series
Volume
10113
Pages / Article No.
313 - 329
Publisher
Springer
Event
13th Asian Conference on Computer Vision (ACCV 2016)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
FACE (ANATOMY AND PHYSIOLOGY); COMPUTER VISION + SCENE UNDERSTANDING (ARTIFICIAL INTELLIGENCE); GESICHT (ANATOMIE UND PHYSIOLOGIE); COMPUTERVISION (KÜNSTLICHE INTELLIGENZ); PERSONENIDENTIFIZIERUNG (INFORMATIONSTHEORIE); PERSONAL IDENTITY VERIFICATION (INFORMATION THEORY)
Organisational unit
03514 - Van Gool, Luc (emeritus) / Van Gool, Luc (emeritus)
02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.