Spatio-temporal representation for face authentication by using multi-task learning with human attributes

Seong-Tae Kim, Dae Hoe Kim, Yong Man RoICIP 2016 · OpenReview

Abstract

For human identification, facial motion is useful in representing specific dynamic signature. In this paper, we present an effective spatio-temporal representation from facial motion as well as appearance by devising a 3D convolutional neural network (CNN). To maintain the intra-class invariance with limited number of training samples, a multi-task learning approach with human attributes, which are high-level semantic descriptions for identity, has been proposed. Identity-related human attributes can be leveraged to learn the 3D CNN. Comparative experiment has showed that the proposed method improves the performance of the face-based authentication system compared to conventional methods by effectively encoding facial appearance and motions with identity-related human attributes.
BibTeX
@inproceedings{kim2016spatio,
  author = {Seong-Tae Kim and Dae Hoe Kim and Yong Man Ro},
  title = {{Spatio-temporal representation for face authentication by using multi-task learning with human attributes}},
  booktitle = {ICIP},
  year = {2016},
  url = {https://openreview.net/forum?id=sZHC7g7YNEg},
}

Loading related content...

Figure