Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
6939511 | Pattern Recognition | 2018 | 31 Pages |
Abstract
In this paper we present architectures based on deep neural nets for expression recognition in videos, which are invariant to local scaling. We amalgamate autoencoder and predictor architectures using an adaptive weighting scheme coping with a reduced size labeled dataset, while enriching our models from enormous unlabeled sets. We further improve robustness to lighting conditions by introducing a new adaptive filter based on temporal local scale normalization. We provide superior results over known methods, including recent reported approaches based on neural nets.
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Vision and Pattern Recognition
Authors
Otkrist Gupta, Dan Raviv, Ramesh Raskar,