Abstract
Micro-facial expressions are brief and involuntary facial movements that reflect genuine emotional states. While most prior work focuses on classifying discrete micro-expression categories, far fewer studies address the continuous evolution of intensity over time. Progress in this direction is limited by the lack of frame-level intensity labels, which makes fully supervised regression impractical. We propose a unified framework for continuous micro-expression intensity estimation using only weak temporal labels (onset, apex, offset). A simple triangular prior converts sparse temporal landmarks into dense pseudo-intensity trajectories, and a lightweight temporal regression model that combines a ResNet18 encoder with a bidirectional GRU predicts frame-wise intensity directly from image sequences. The method requires no frame-level annotation effort and is applied consistently across datasets through a single preprocessing and temporal alignment pipeline. Experiments on SAMM and CASME II show strong temporal agreement with the pseudo-intensity trajectories. On SAMM, the model reaches a Spearman correlation of 0.9014 and a Kendall correlation of 0.7999, outperforming a frame-wise baseline. On CASME II, it achieves up to 0.9116 and 0.8168, respectively, when trained without the apex-ranking term. Ablation studies confirm that temporal modeling and structured pseudo labels are central to capturing the rise-apex-fall dynamics of micro-facial movements. To our knowledge, this is the first unified approach for continuous micro-expression intensity estimation using only sparse temporal annotations.
Abstract (translated)
微面部表情是短暂且不由自主的面部运动，反映的是真实的情感状态。以往的研究大多集中在离散的微表情分类上，而关注其随时间变化连续强度演变的研究则较少。由于缺乏帧级别的强度标签，使得完全监督下的回归方法难以实施，限制了这一领域的进展。我们提出了一种统一框架，仅使用稀疏的时间标签（起始点、峰值点和结束点）来进行连续微表情强度估计。 该方法包含两个关键部分：首先，通过简单的三角形先验将稀疏的时间地标转换为密集的伪强度轨迹；其次，结合 ResNet18 编码器与双向 GRU 的轻量级时间回归模型直接从图像序列中预测帧级别的强度。这种方法不需要对每个帧进行标注，并且可以通过统一的数据预处理和时间对齐管道在不同的数据集中一致地应用。 实验结果表明，在 SAMM 和 CASME II 数据集上，伪强度轨迹与真实值的时间一致性得到了显著提升。具体而言，在 SAMM 上，模型达到了 0.9014 的斯皮尔曼相关系数以及 0.7999 的肯德尔相关系数，并且优于帧级别基线模型的表现；在 CASME II 数据集上，当训练过程中不包括峰值排序项时，分别取得了最高为 0.9116 和 0.8168 的表现。消融研究表明时间建模和结构化伪标签对于捕捉微面部运动的上升-顶峰-下降动态至关重要。 据我们所知，这是第一个仅使用稀疏的时间标注来实现连续微表情强度估计的统一方法。
URL
https://arxiv.org/abs/2512.01145
