arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2109.08409cs.CV
收藏

基于表情嗅探器Transformer的鲁棒视频人脸表情识别

Expression Snippet Transformer for Robust Video-based Facial Expression Recognition

China University of Geosciences (Wuhan)(中国地质大学(武汉));The University of Sydney(悉尼大学);Jingdong(京东)

Yuanyuan Liu, Wenbin Wang, Chuanxu Feng, Haoyu Zhang, Zhe Chen, Yibing Zhan

摘要:

最近Transformer的成功为各种视觉理解任务提供了新的方向,包括基于视频的面部表情识别(FER)。通过有效地建模视觉关系,Transformer已经显示出其描述复杂模式的能力。然而,Transformer在注意细微面部表情运动方面的表现仍然不令人满意,因为许多视频的表情运动可能太小,无法提取有意义的时空关系并实现鲁棒性能。为此,我们建议将每个视频分解成一系列的表情片段,其中每一个包含少量的面部运动,并试图增加Transformer的能力,分别为建模片段内和片段间的视觉关系,获得表达式片段Transformer(EST)。特别是,对于片段内建模,我们设计了一个注意力增强片段特征提取器(AA-SFE),通过逐渐关注更突出的信息来增强每个片段的细微面部运动的编码。此外,对于片段间建模,我们引入了混洗片段顺序预测(SSOP)头部和相应的损失,以通过训练Transformer来识别混洗片段顺序,从而改善对后续片段中细微运动变化的建模。在四个具有挑战性的数据集上进行了广泛的实验(即,BU-3DFE,MMI,AFEW和DFEW)表明,我们的EST优于其他基于CNN的方法,获得最先进的性能。

英文摘要:

The recent success of Transformer has provided a new direction to various visual understanding tasks, including video-based facial expression recognition (FER). By modeling visual relations effectively, Transformer has shown its power for describing complicated patterns. However, Transformer still performs unsatisfactorily to notice subtle facial expression movements, because the expression movements of many videos can be too small to extract meaningful spatial-temporal relations and achieve robust performance. To this end, we propose to decompose each video into a series of expression snippets, each of which contains a small number of facial movements, and attempt to augment the Transformer's ability for modeling intra-snippet and inter-snippet visual relations, respectively, obtaining the Expression snippet Transformer (EST). In particular, for intra-snippet modeling, we devise an attention-augmented snippet feature extractor (AA-SFE) to enhance the encoding of subtle facial movements of each snippet by gradually attending to more salient information. In addition, for inter-snippet modeling, we introduce a shuffled snippet order prediction (SSOP) head and a corresponding loss to improve the modeling of subtle motion changes across subsequent snippets by training the Transformer to identify shuffled snippet orders. Extensive experiments on four challenging datasets (i.e., BU-3DFE, MMI, AFEW, and DFEW) demonstrate that our EST is superior to other CNN-based methods, obtaining state-of-the-art performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑