基于多层次一致性的弱监督微表情和宏表情识别（英文版）

英文标题：Weakly-supervised Micro- and Macro-expression Spotting Based on Multi-level Consistency中文摘要：本文提出了一种使用多一致协作机制的微弱监督表情识别框架，称为 MC-WES 框架，用于实现精细的帧级别识别。试验结果表明，MC-WES 与当前最先进的全监督方法相当。英文摘要：Most micro- and macro-expression spotting methods in untrimmed videos sufferfrom the burden of video-wise collection and frame-wise annotation.Weakly-supervised expression spotting (WES) based on video-level labels canpotentially mitigate the complexity of frame-level annotation while achievingfine-grained frame-