研究人员开发了 SkelHCC，一个用于基于骨骼数据的单次动作识别的新框架。该方法利用超bolic 几何来更好地模拟人类运动的层次结构并将其与语言语义对齐。该框架还包含一个由 LLM 引导的缓存，用于高效推理，并在基准数据集上展示了卓越的性能。 AI
影响 该框架可以提高解释骨骼数据的 AI 系统的准确性和效率，尤其是在训练样本有限的情况下。
排序理由 该集群包含一篇详细介绍用于基于骨骼的动作识别的新框架的研究论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2606.03610v1 Announce Type: new Abstract: Skeleton-based action recognition aims to understand human behaviors from body joint sequences and is especially challenging in the one-shot setting, where only a single labeled exemplar is available for each novel action. A key cha…
Skeleton-based action recognition aims to understand human behaviors from body joint sequences and is especially challenging in the one-shot setting, where only a single labeled exemplar is available for each novel action. A key challenge is learning representations that capture …