摘要：我们推出了 HumanCentric-Scenes-AI，一个包含 296 个 AI 生成刺激样本的人工精选数据集，涵盖人们日常接触 AI 生成媒体的四大典型场景。其中，监控（Surveillance）子集包含 85 张 AI 生成的监控摄像头（CCTV）风格图像；职业（Occupations）子集包含 128 张 AI 生成的职业肖像，采用平衡配对设计，覆盖 64 种职业，每种职业均包含一男一女两个版本；AI 编辑（AI-edited）子集包含 27 张真实照片，其中的特定区域被生成式模型修改或替换；视频（Video）子集包含 56 个 AI 生成的短视频。我们对图像和视频进行了多轮人工筛选与整理，确保其尽可能逼真（photorealistic）。针对每个样本，我们公开发布了对应文件、有记录时的生成提示词（Prompt）以及样本级元数据。我们汇报了在初始 134 次未指定性别的生成中体现的性别分布，并将其与美国劳工统计局（U.S. Bureau of Labor Statistics）的职业性别比例进行了对比；在 AI 编辑子集中，我们分析了编辑区域大小与零样本检测（zero-shot detection）难度之间的关联；此外，我们还展示了监控子集的图像质量分布以及视频子集的主题类别覆盖情况。HumanCentric-Scenes-AI 首先面向人类感知研究设计，同时也可用于 AI 检测分类器的校准以及生成式模型的偏见分析。

Abstract:We introduce HumanCentric-Scenes-AI, a human-curated dataset of 296 AI-generated stimuli that depict people across four contexts in which people encounter AI-generated media. The Surveillance subset contains 85 AI-generated CCTV-style images. The Occupations subset contains 128 AI-generated occupational portraits in a balanced paired design covering 64 occupations with one female and one male version of each. The AI-edited subset contains 27 real photographs in which a region was altered or replaced by a generative model. The Video subset contains 56 AI-generated short videos. We curated the images and videos manually over multiple rounds to make them as photorealistic as possible. For each stimulus we release the file, the generation prompt where recorded, and per-stimulus metadata. We report depicted-gender distributions from an initial set of 134 generations without a specified gender and compare them with U.S. Bureau of Labor Statistics occupational gender shares. We report edit-region size and its association with zero-shot detection difficulty for the AI-edited subset. We report image-quality distributions for the Surveillance subset and subject-category coverage for the Video subset. HumanCentric-Scenes-AI is intended first for human-perception research, and also for calibration of AI-detection classifiers and bias analysis of generative models.