Illumination invariants in deep video expression recognition

Otkrist Gupta, Dan Raviv, Ramesh Raskar

Research output: Contribution to journalArticlepeer-review


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.

Original languageEnglish
Pages (from-to)25-35
Number of pages11
JournalPattern Recognition
StatePublished - Apr 2018


  • Deep learning
  • Expression recognition
  • Machine learning
  • Neural nets
  • Video classification

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence


Dive into the research topics of 'Illumination invariants in deep video expression recognition'. Together they form a unique fingerprint.

Cite this