期刊
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
卷 -, 期 -, 页码 9070-9080出版社
IEEE COMPUTER SOC
DOI: 10.1109/CVPR46437.2021.00896
关键词
-
资金
- National Institute for Health Research
Temporal context is crucial for the recognition of expressions of emotion. A method based on Neural Processes framework is proposed, with key new components of probabilistic contextual representation, temporal context modeling, and smart temporal context selection, achieving consistent improvement over strong baselines and state-of-the-art methods on four databases for emotion recognition.
Temporal context is key to the recognition of expressions of emotion. Existing methods, that rely on recurrent or self-attention models to enforce temporal consistency, work on the feature level, ignoring the task-specific temporal dependencies, and fail to model context uncertainty. To alleviate these issues, we build upon the framework of Neural Processes to propose a method for apparent emotion recognition with three key novel components: (a) probabilistic contextual representation with a global latent variable model; (b) temporal context modelling using task-specific predictions in addition to features; and (c) smart temporal context selection. We validate our approach on four databases, two for Valence and Arousal estimation (SEWA and AffWild2), and two for Action Unit intensity estimation (DISFA and BP4D). Results show a consistent improvement over a series of strong baselines as well as over state-of-the-art methods.
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