适应性阈值和负类引导嘈杂标注的鲁棒性面部表情识别（英文版）

英文标题：Class adaptive threshold and negative class guided noisy annotation robust Facial Expression Recognition中文摘要：本研究提出了一种动态自适应阈值的方法来解决面部表情识别中存在的不准确注释的问题，该方法通过样本选择和负类一致性引导模型学习，以获得比现有基线方法更好的性能。英文摘要：The hindering problem in facial expression recognition (FER) is the presenceof inaccurate annotations referred to as noisy annotations in the datasets.These noisy annotations are present in the datasets inherently because thelabeling is subjective to the annotator, clarity of the image, etc. Recentwor