Facial Action Unit Detection Using Attention and Relation Learning

TL;DR

This paper introduces a novel end-to-end deep learning framework that uses attention and relation learning to improve facial action unit detection and intensity estimation, outperforming existing methods on multiple benchmarks.

Contribution

The paper proposes a new attention and relation learning framework that adaptively captures AU-related features using only AU labels, without fixed priors or limited attention refinement.

Findings

Outperforms state-of-the-art AU detection methods on BP4D, DISFA, FERA 2015, and BP4D+ datasets.

Effectively captures correlated regions of AUs and handles occlusions and pose variations.

Can be extended to AU intensity estimation without architectural changes.

Abstract

Attention mechanism has recently attracted increasing attentions in the field of facial action unit (AU) detection. By finding the region of interest of each AU with the attention mechanism, AU-related local features can be captured. Most of the existing attention based AU detection works use prior knowledge to predefine fixed attentions or refine the predefined attentions within a small range, which limits their capacity to model various AUs. In this paper, we propose an end-to-end deep learning based attention and relation learning framework for AU detection with only AU labels, which has not been explored before. In particular, multi-scale features shared by each AU are learned firstly, and then both channel-wise and spatial attentions are adaptively learned to select and extract AU-related local features. Moreover, pixel-level relations for AUs are further captured to refine spatial attentions so as to extract more relevant local features. Without changing the network architecture, our framework can be easily extended for AU intensity estimation. Extensive experiments show that our framework (i) soundly outperforms the state-of-the-art methods for both AU detection and AU intensity estimation on the challenging BP4D, DISFA, FERA 2015 and BP4D+ benchmarks, (ii) can adaptively capture the correlated regions of each AU, and (iii) also works well under severe occlusions and large poses.