How do Foundation Models Compare to Skeleton-Based Approaches for Gesture Recognition in Human-Robot Interaction?

作者：Stephanie Käs, Anton Burenko, Louis Markert, Onur Alp Çulha, Dennis Mack, Timm Linder, Bastian Leibe · 单位：Chair for Computer Vision, RWTH Aachen University, Germany. Mail, Robert Bosch GmbH, Corporate Research & Bosch Center for AI, Renningen and Hildesheim, Germany. Mail · 会议/期刊：arXiv preprint · 方向：6D位姿 · 发布日期：2025-06-25