Video Joint-Embedding Predictive Architectures for Facial Expression Recognition
视频联合嵌入预测架构用于面部表情识别
机构 * Chair for Human-Centered Artificial Intelligence(人中心人工智能教研室) ; University of Augsburg(奥斯特拉赫大学) ; Faculty of Computer Science(计算机科学学院) ; Technical University of Applied Sciences Augsburg(应用科学大学奥斯特拉赫)
专题命中 视频理解 :video understanding(abstract);分类 cs.CV
AI总结 本文提出了一种基于嵌入的预训练方法,用于提升面部表情识别的性能,在RAVDESS和CREMA-D数据集上取得了显著成果。
Comments To appear in 2025 Proceedings of the 13th International Conference on Affective Computing and Intelligent Interaction (ACII), submitted to IEEE. \c{opyright} 2025 IEEE