论文标题
用于动作单元检测的多标签变压器
Multi-label Transformer for Action Unit Detection
论文作者
论文摘要
动作单元（AU）检测是情感计算的分支，旨在识别统一的面部肌肉运动。这是解锁公正的计算面表示的关键，因此在过去几年中引起了极大的兴趣。建立有效的基于深度学习的AU检测系统的主要障碍之一是缺乏由AU专家注释的广泛面部图像数据库。在这样的程度上，ABAW挑战为更好的AU检测铺平了道路，因为它涉及2M帧AU注释的数据集。在本文中，我们提出了对ABAW3挑战的提交。简而言之，我们应用了一个多标签检测变压器，该变压器利用多头注意力来了解面部图像的哪一部分与预测每个AU最相关。
Action Unit (AU) Detection is the branch of affective computing that aims at recognizing unitary facial muscular movements. It is key to unlock unbiased computational face representations and has therefore aroused great interest in the past few years. One of the main obstacles toward building efficient deep learning based AU detection system is the lack of wide facial image databases annotated by AU experts. In that extent the ABAW challenge paves the way toward better AU detection as it involves a 2M frames AU annotated dataset. In this paper, we present our submission to the ABAW3 challenge. In a nutshell, we applied a multi-label detection transformer that leverage multi-head attention to learn which part of the face image is the most relevant to predict each AU.
