面向中文视频中的居高临下与屈尊俯就语言：一个多模态数据集与检测器
Towards Patronizing and Condescending Language in Chinese Videos: A Multimodal Dataset and Detector
AI总结：
针对中文视频中 PCL 微冒犯缺乏多模态研究的问题，本文构建含 715 个 Bilibili 视频的 PCLMM 数据集，并提出带面部表情检测模块的 MultiPCL 检测器。
摘要：
居高临下与屈尊俯就语言（PCL）是一种针对弱势群体的歧视性有毒言论，威胁着线上与线下安全。尽管有毒言论研究主要关注仇恨言论等显性毒性，但以 PCL 形式出现的微冒犯仍未得到充分研究。此外，主导群体对弱势社群的歧视性面部表情和态度可能比言语线索更具影响力，然而这些画面特征往往被忽视。本文提出 PCLMM 数据集，这是首个用于 PCL 的中文多模态数据集，包含来自 Bilibili 的 715 个带标注视频，并具有高质量的 PCL 面部帧片段。我们还提出了 MultiPCL 检测器，其特点是配备用于 PCL 识别的面部表情检测模块，证明了在这一具有挑战性的任务中模态互补性的有效性。我们的工作为推进有毒言论领域内的微冒犯检测作出了重要贡献。
英文摘要：
Patronizing and Condescending Language (PCL) is a form of discriminatory toxic speech targeting vulnerable groups, threatening both online and offline safety. While toxic speech research has mainly focused on overt toxicity, such as hate speech, microaggressions in the form of PCL remain underexplored. Additionally, dominant groups' discriminatory facial expressions and attitudes toward vulnerable communities can be more impactful than verbal cues, yet these frame features are often overlooked. In this paper, we introduce the PCLMM dataset, the first Chinese multimodal dataset for PCL, consisting of 715 annotated videos from Bilibili, with high-quality PCL facial frame spans. We also propose the MultiPCL detector, featuring a facial expression detection module for PCL recognition, demonstrating the effectiveness of modality complementarity in this challenging task. Our work makes an important contribution to advancing microaggression detection within the domain of toxic speech.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
