Learning Expressionlets via Universal Manifold Model for Dynamic Facial Expression Recognition

TL;DR

This paper introduces a novel manifold-based approach for dynamic facial expression recognition, using expressionlets and a universal model to improve temporal alignment and representation, achieving superior results on multiple datasets.

Contribution

The paper proposes a new expressionlet-based representation and a universal manifold model for better temporal alignment and dynamic feature modeling in facial expression recognition.

Findings

Outperforms state-of-the-art on four public databases.

Effectively aligns facial expressions both spatially and temporally.

Enhances discriminative power with embedding techniques.

Abstract

Facial expression is temporally dynamic event which can be decomposed into a set of muscle motions occurring in different facial regions over various time intervals. For dynamic expression recognition, two key issues, temporal alignment and semantics-aware dynamic representation, must be taken into account. In this paper, we attempt to solve both problems via manifold modeling of videos based on a novel mid-level representation, i.e. \textbf{expressionlet}. Specifically, our method contains three key stages: 1) each expression video clip is characterized as a spatial-temporal manifold (STM) formed by dense low-level features; 2) a Universal Manifold Model (UMM) is learned over all low-level features and represented as a set of local modes to statistically unify all the STMs. 3) the local modes on each STM can be instantiated by fitting to UMM, and the corresponding expressionlet is constructed by modeling the variations in each local mode. With above strategy, expression videos are naturally aligned both spatially and temporally. To enhance the discriminative power, the expressionlet-based STM representation is further processed with discriminant embedding. Our method is evaluated on four public expression databases, CK+, MMI, Oulu-CASIA, and FERA. In all cases, our method outperforms the known state-of-the-art by a large margin.