Illumination invariants in deep video expression recognition

作者：

Highlights：

• highlights

• We develop a scale invariant architecture for generating illumination invariant deep motion features.

• We report state of the art results for video gesture recognition using spatio-temporal convolutional neural networks.

• We introduce an improved topology and protocol for semi-supervised learning, where the number of labeled data points is only a fraction of the entire dataset.

摘要

highlights•We develop a scale invariant architecture for generating illumination invariant deep motion features.•We report state of the art results for video gesture recognition using spatio-temporal convolutional neural networks.•We introduce an improved topology and protocol for semi-supervised learning, where the number of labeled data points is only a fraction of the entire dataset.

论文关键词：Deep learning,Expression recognition,Video classification,Neural nets,Machine learning

论文评审过程：Received 23 May 2017, Revised 19 September 2017, Accepted 15 October 2017, Available online 20 October 2017, Version of Record 21 December 2017.

论文官网地址：https://doi.org/10.1016/j.patcog.2017.10.017