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 2203.09463cs.CV
收藏

FERV39k:一个用于视频人脸表情识别的大规模多场景数据集

FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos

Fudan University(复旦大学)

Yan Wang, Yixuan Sun, Yiwen Huang, Zhongying Liu, Shuyong Gao, Wei Zhang, Weifeng Ge, Wenqiang Zhang

摘要:

目前人脸表情识别(FER)的基准测试主要集中在静态图像上,而视频中的FER数据集有限。它仍然是模糊的,以评估现有的方法的性能是否仍然令人满意的现实世界中面向应用的场景。例如,在谈话-表演中,高强度的“快乐”表情比在纪念-事件中低强度的相同表情更有区分力。为了填补这一空白,我们构建了一个大规模的多场景数据集,称为FERV 39 k。我们从三个方面分析了构建这种新数据集的重要组成部分:(1)多场景层次和表达类,(2)候选视频片段的生成,(3)可信的人工标记过程。基于这些准则,我们选择了细分为22个场景的4个场景,基于精心设计的工作流程对从4k视频中自动获得的86 k样本进行注释,最终构建了38,935个带有7个经典表达式的视频片段。最后给出了四种基本框架的实验基准,并对它们在不同场景下的性能进行了分析,指出了未来研究的一些挑战。此外,我们通过消融研究系统地研究了DFER的关键组成部分。基线框架和我们的项目将可用。

英文摘要:

Current benchmarks for facial expression recognition (FER) mainly focus on static images, while there are limited datasets for FER in videos. It is still ambiguous to evaluate whether performances of existing methods remain satisfactory in real-world application-oriented scenes. For example, the "Happy" expression with high intensity in Talk-Show is more discriminating than the same expression with low intensity in Official-Event. To fill this gap, we build a large-scale multi-scene dataset, coined as FERV39k. We analyze the important ingredients of constructing such a novel dataset in three aspects: (1) multi-scene hierarchy and expression class, (2) generation of candidate video clips, (3) trusted manual labelling process. Based on these guidelines, we select 4 scenarios subdivided into 22 scenes, annotate 86k samples automatically obtained from 4k videos based on the well-designed workflow, and finally build 38,935 video clips labeled with 7 classic expressions. Experiment benchmarks on four kinds of baseline frameworks were also provided and further analysis on their performance across different scenes and some challenges for future research were given. Besides, we systematically investigate key components of DFER by ablation studies. The baseline framework and our project will be available.

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。

↑