Skip to content Skip to navigation
Qualifying Exam
12/22/2016 02:00 pm

A Recurrent Encoder-Decoder Network for Sequential Face Alignment

Xi Peng, Dept. of Computer Science

Examination Committee: Prof. Dimitris Metaxas (Chair), Prof. Apostolos Gerasoulis, Prof. Konstantinos Michmizos and Prof. Amelie Marian


We propose a novel recurrent encoder-decoder network model for real-time video-based face alignment. Our proposed model predicts 2D facial point maps regularized by a regression loss, while uniquely exploiting recurrent learning at both spatial and temporal dimensions. At the spatial level, we add a feedback loop connection between the combined output response map and the input, in order to enable iterative coarse-to-fine face alignment using a single network model. At the temporal level, we first decouple the features in the bottleneck of the network into temporal-variant factors, such as pose and expression, and temporal- invariant factors, such as identity information. Temporal recurrent learning is then applied to the decoupled temporal-variant features, yielding better generalization and significantly more accurate results at test time. We perform a comprehensive experimental analysis, showing the importance of each component of our proposed model, as well as superior results over the state-of-the-art in standard datasets.