Unpublished conference/Abstract (Scientific congresses, symposiums and conference proceedings)
Space-Time Triplet Loss Network for Dynamic 3D Face Verification
Kacem, Anis; Ben Abdessalem, Hamza; Cherenkova, Kseniya et al.
2020Workshop on 3D Human Understanding, ICPR 2020
 

Files


Full Text
ICPRW-5.pdf
Publisher postprint (919.83 kB)
Request a copy

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
Dynamic 3D Face Recognition; ConvolutionalNeural Networks; Triplet Loss
Abstract :
[en] In this paper, we propose a new approach for 3D dynamic face verification exploiting 3D facial deformations. First, 3D faces are encoded into low-dimensional representations describing the local deformations of the faces with respect to a mean face. Second, the encoded versions of the 3D faces along a sequence are stacked into 2D arrays for temporal modeling. The resulting 2D arrays are then fed to a triplet loss network for dynamic sequence embedding. Finally, the outputs of the triplet loss network are compared using cosine similarity measure for face verification. By projecting the feature maps of the triplet loss network into attention maps on the 3D face sequences, we are able to detect the space-time patterns that contribute most to the pairwise similarity between differ-ent 3D facial expressions of the same person. The evaluation is conducted on the publicly available BU4D dataset which contains dynamic 3D face sequences. Obtained results are promising with respect to baseline methods.
Research center :
Interdisciplinary Centre for Security, Reliability and Trust (SnT) > Computer Vision Imaging & Machine Intelligence (CVI²)
Disciplines :
Computer science
Author, co-author :
Kacem, Anis ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2
Ben Abdessalem, Hamza ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Cherenkova, Kseniya ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Aouada, Djamila  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2
External co-authors :
no
Language :
English
Title :
Space-Time Triplet Loss Network for Dynamic 3D Face Verification
Publication date :
2020
Event name :
Workshop on 3D Human Understanding, ICPR 2020
Event date :
15-01-2020
Available on ORBilu :
since 11 November 2020

Statistics


Number of views
204 (45 by Unilu)
Number of downloads
4 (4 by Unilu)

Bibliography


Similar publications



Contact ORBilu