期刊
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
卷 43, 期 3, 页码 1022-1040出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2019.2944808
关键词
Databases; Tools; Computational modeling; Biological system modeling; Sensors; Affective computing; Emotion recognition; SEWA; affect analysis; in-the-wild; emotion recognition; database; valence; arousal; facial action units
资金
- European Community Horizon 2020 [H2020/2014-2020] [645094]
- NVIDIA Corporation
Natural human-computer interaction and audio-visual human behaviour sensing systems are more important than ever, as digital devices become increasingly integral to our lives. The SEWA database provides a valuable resource with over 2000 minutes of audio-visual data from 398 individuals representing six cultures, aiding research in affective computing and automatic human sensing.
Natural human-computer interaction and audio-visual human behaviour sensing systems, which would achieve robust performance in-the-wild are more needed than ever as digital devices are increasingly becoming an indispensable part of our life. Accurately annotated real-world data are the crux in devising such systems. However, existing databases usually consider controlled settings, low demographic variability, and a single task. In this paper, we introduce the SEWA database of more than 2,000 minutes of audio-visual data of 398 people coming from six cultures, 50 percent female, and uniformly spanning the age range of 18 to 65 years old. Subjects were recorded in two different contexts: while watching adverts and while discussing adverts in a video chat. The database includes rich annotations of the recordings in terms of facial landmarks, facial action units (FAU), various vocalisations, mirroring, and continuously valued valence, arousal, liking, agreement, and prototypic examples of (dis)liking. This database aims to be an extremely valuable resource for researchers in affective computing and automatic human sensing and is expected to push forward the research in human behaviour analysis, including cultural studies. Along with the database, we provide extensive baseline experiments for automatic FAU detection and automatic valence, arousal, and (dis)liking intensity estimation.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据