Unconstrained face alignment via cascaded compositional learning
Refereed conference paper presented and published in conference proceedings

Full Text

Times Cited

Other information
AbstractWe present a practical approach to address the problem of unconstrained face alignment for a single image. In our unconstrained problem, we need to deal with large shape and appearance variations under extreme head poses and rich shape deformation. To equip cascaded regressors with the capability to handle global shape variation and irregular appearance-shape relation in the unconstrained scenario, we partition the optimisation space into multiple domains of homogeneous descent, and predict a shape as a composition of estimations from multiple domain-specific regressors. With a specially formulated learning objective and a novel tree splitting function, our approach is capable of estimating a robust and meaningful composition. In addition to achieving state-of-the-art accuracy over existing approaches, our framework is also an efficient solution (350 FPS), thanks to the on-the-fly domain exclusion mechanism and the capability of leveraging the fast pixel feature.
All Author(s) ListZhu S., Li C., Loy C.C., Tang X.
Name of Conference2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
Start Date of Conference26/06/2016
End Date of Conference01/07/2016
Place of ConferenceLas Vegas
Country/Region of ConferenceUnited States of America
Detailed descriptionorganized by IEEE,
Volume Number2016-January
Pages3409 - 3417
LanguagesEnglish-United Kingdom

Last updated on 2021-20-09 at 23:26