Relational Scene Graphs for Object Grounding of Natural Language Commands
基于关系场景图的对象接地自然语言指令
机构 * School of Electrical Engineering, Aalto University(艾尔沃大学电气工程学院) ; School of Science, Aalto University(艾尔沃大学科学学院)
专题命中 视觉定位与Grounding :grounding(title,abstract);VLM(summary_cn,abstract_cn);vision language model(abstract)
AI总结 本文提出基于关系场景图的方法,通过结合LLM和VLM增强自然语言指令中对象接地的准确性。
Comments Accepted to the 35th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN 2026)