TY - GEN
T1 - Robust Video Facial Authentication with Unsupervised Mode Disentanglement
AU - Kim, Minsu
AU - Lee, Hong Joo
AU - Lee, Sangmin
AU - Ro, Yong Man
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/10
Y1 - 2020/10
N2 - Deep learning-based video facial authentication has limitations when it comes to real-world applications, due to large mode variations such as illumination, pose, and eyeglasses variations in real-life situations. Many of existing mode-invariant facial authentication methods need labels of each mode. However, the label information could not be always available in practice. To alleviate this problem, we develop an unsupervised mode disentangling method for video facial authentication. By matching both disentangled identity features and dynamic features of two facial videos, our proposed method shows significant face verification and identification performances on three publicly available datasets, KAIST-MPMI, UVA-NEMO, and YTF.
AB - Deep learning-based video facial authentication has limitations when it comes to real-world applications, due to large mode variations such as illumination, pose, and eyeglasses variations in real-life situations. Many of existing mode-invariant facial authentication methods need labels of each mode. However, the label information could not be always available in practice. To alleviate this problem, we develop an unsupervised mode disentangling method for video facial authentication. By matching both disentangled identity features and dynamic features of two facial videos, our proposed method shows significant face verification and identification performances on three publicly available datasets, KAIST-MPMI, UVA-NEMO, and YTF.
KW - Deep learning
KW - disentangled representation
KW - dynamic encoding
KW - facial authentication
UR - https://www.scopus.com/pages/publications/85098671813
U2 - 10.1109/ICIP40778.2020.9191052
DO - 10.1109/ICIP40778.2020.9191052
M3 - Conference contribution
AN - SCOPUS:85098671813
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 1321
EP - 1325
BT - 2020 IEEE International Conference on Image Processing, ICIP 2020 - Proceedings
PB - IEEE Computer Society
T2 - 2020 IEEE International Conference on Image Processing, ICIP 2020
Y2 - 25 September 2020 through 28 September 2020
ER -