Dynamic ensembles of exemplar-SVMs for still-to-video face recognition

作者:

Highlights:

• An efficient multi-classifier system is proposed for robust still-to-video FR.

• Multiple diverse representations are generated from the single target still face.

• Individual-specific ensembles of exemplar-SVM are designed based on domain adaptation.

• Different domain adaptation training schemes are proposed to generate the classifiers.

• Dynamic classifier selection and weighting are applied to perform spatio-temporal FR.

摘要

•An efficient multi-classifier system is proposed for robust still-to-video FR.•Multiple diverse representations are generated from the single target still face.•Individual-specific ensembles of exemplar-SVM are designed based on domain adaptation.•Different domain adaptation training schemes are proposed to generate the classifiers.•Dynamic classifier selection and weighting are applied to perform spatio-temporal FR.

论文关键词:Video surveillance,Watch-list screening,Face recognition,Single sample per person,Multi-classifier system,Random subspace methods,Domain adaptation,Dynamic classifier selection

论文评审过程:Received 28 September 2016, Revised 12 February 2017, Accepted 12 April 2017, Available online 13 April 2017, Version of Record 19 April 2017.

论文官网地址:https://doi.org/10.1016/j.patcog.2017.04.014