用因果图消除表情识别中的数据偏见，提升心理状态检测准确率。
Causal-Ex: Causal Graph-based Micro and Macro Expression Spotting
- 构建面部动作单元的因果图，剔除虚假关联
- 在CAS(ME)^2和SAMM数据集上F1分别达0.388和0.3701
- 适合关注情绪识别公平性与可解释性的研究者
识别表面正常表情下的隐藏情绪对发现潜在心理问题并及时干预至关重要。该任务需预测视频中情感的时间线，即确定情绪的起始、峰值和结束帧。利用面部动作单元（Action Units）作为基础肌肉运动线索可提升准确性。然而，以往研究忽视了数据集引入的模型偏见，这些偏见会错误地将特定动作单元与特定情绪类别关联。本文提出Causal-Ex模型，以动作单元因果图替代传统邻接信息，旨在识别并消除虚假关联，仅保留无偏信息用于分类。通过快速因果推断算法构建面部动作单元的因果图，从而筛选出具有因果相关性的动作单元。实验表明，本方法在CAS(ME)^2数据集上达到0.388的F1分数，在SAMM-Long Video数据集上达0.3701，优于现有先进方法。
原文摘要 · Abstract (English)
Detecting concealed emotions within apparently normal expressions is crucial for identifying potential mental health issues and facilitating timely support and intervention. The task of spotting macro and micro-expressions involves predicting the emotional timeline within a video, accomplished by identifying the onset, apex, and offset frames of the displayed emotions. Utilizing foundational facial muscle movement cues, known as facial action units, boosts the accuracy. However, an overlooked challenge from previous research lies in the inadvertent integration of biases into the training model. These biases arising from datasets can spuriously link certain action unit movements to particular emotion classes. We tackle this issue by novel replacement of action unit adjacency information with the action unit causal graphs. This approach aims to identify and eliminate undesired spurious connections, retaining only unbiased information for classification. Our model, named Causal-Ex (Causal-based Expression spotting), employs a rapid causal inference algorithm to construct a causal graph of facial action units. This enables us to select causally relevant facial action units. Our work demonstrates improvement in overall F1-scores compared to state-of-the-art approaches with 0.388 on CAS(ME)^2 and 0.3701 on SAMM-Long Video datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。