论文标题
海报：用于面部表达识别的金字塔交叉融合变压器网络
POSTER: A Pyramid Cross-Fusion Transformer Network for Facial Expression Recognition
论文作者
论文摘要
面部表情识别（FER）是计算机视觉中的重要任务，在人类计算机互动，教育，医疗保健和在线监控等领域具有实际应用。在这项具有挑战性的FER任务中，有三个关键问题，尤其是普遍存在：类间相似性，类内部差异和规模敏感性。尽管现有作品通常解决了其中一些问题，但没有一个在统一框架中完全解决了所有三个挑战。在本文中，我们提出了一个两流金字塔交叉融合变压器网络（海报），该网络旨在整体解决这三个问题。具体而言，我们设计了一种基于变压器的交叉融合方法，该方法可以有效地协作面部地标特征和图像功能，以最大程度地关注显着面部区域。此外，海报采用金字塔结构来促进规模不变性。广泛的实验结果表明，我们的海报在RAF-DB（92.05％），Ferplus（91.62％）以及AffectNet 7类（67.31％）和8类（63.34％）上获得了新的最先进结果。该代码可在https://github.com/zczcwh/poster上找到。
Facial expression recognition (FER) is an important task in computer vision, having practical applications in areas such as human-computer interaction, education, healthcare, and online monitoring. In this challenging FER task, there are three key issues especially prevalent: inter-class similarity, intra-class discrepancy, and scale sensitivity. While existing works typically address some of these issues, none have fully addressed all three challenges in a unified framework. In this paper, we propose a two-stream Pyramid crOss-fuSion TransformER network (POSTER), that aims to holistically solve all three issues. Specifically, we design a transformer-based cross-fusion method that enables effective collaboration of facial landmark features and image features to maximize proper attention to salient facial regions. Furthermore, POSTER employs a pyramid structure to promote scale invariance. Extensive experimental results demonstrate that our POSTER achieves new state-of-the-art results on RAF-DB (92.05%), FERPlus (91.62%), as well as AffectNet 7 class (67.31%) and 8 class (63.34%). The code is available at https://github.com/zczcwh/POSTER.
