Content moderation in online multiplayer 3D virtual environments has recently been relegated to automated, AI-based pipelines. However, the field has mainly been involved in detection of illicit content in images, video, and audio, leaving blind spots in detection techniques for suggestive motion. We present a motion-only classification pipeline that detects suggestive and explicit movement from SMPL skeleton trajectories using Laban Movement Analysis (LMA) descriptors. On 20,514 motion fragments (17+ hours) spanning four ordinal tiers -- everyday, artistic, suggestive, explicit -- logistic regression over 110 LMA features achieves 57.3% four-way accuracy (2.3x chance), 72.1% three-way, and 78.7% binary SFW/NSFW. Confusion concentrates on adjacent tiers, confirming that classification errors are concentrated between adjacent tiers over non-adjacent ones. Moreover, different movement qualities dominate at each level of the taxonomy -- no single feature drives the classification, suggesting that the four-tier structure reflects genuinely distinct motion regimes.

翻译：在线多玩家3D虚拟环境中的内容审核近期已交由基于AI的自动化流程处理。然而，该领域主要专注于图像、视频和音频中的不良内容检测，导致对暗示性动作的检测技术存在盲区。我们提出了一种纯运动分类流程，该流程使用拉班运动分析（LMA）描述符从SMPL骨骼轨迹中检测暗示性和露骨性动作。在涵盖四个有序层级（日常、艺术、暗示、露骨）的20,514个动作片段（超过17小时）上，基于110个LMA特征的逻辑回归实现了57.3%的四分类准确率（随机概率的2.3倍）、72.1%的三分类准确率以及78.7%的二分类（安全/不安全）准确率。分类混淆集中在相邻层级，证实误分类更多发生在相邻层级而非非相邻层级之间。此外，不同运动特质在各分类层级中占据主导地位——没有任何单一特征驱动分类结果，这表明四层级结构确实反映了截然不同的运动模式。