论文标题:Do As I Can, Not As I Say: Grounding Language in Robotic Affordances 论文作者:Michael Ahn, Anthony Brohan, Noah Brown, Yevgen Chebotar, Omar Cortes, Byron David, Chelsea Finn, Chuyuan Fu, Keerthana
文章目录 引言方法1. Language Scene Graph Module Paper:《Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud》【ICCV’2021】 Code:https://github.com/PNXD/FFL-3DOG
文章目录 引言方法1. Language Scene Graph Module Paper:《Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud》【ICCV’2021】 Code:https://github.com/PNXD/FFL-3DOG
OV-VG: A Benchmark for Open-Vocabulary Visual Grounding 一、Abstract 写在前面 又是一周周末,光调代码去了,都没时间看论文了,汗。 这是一篇关于开放词汇定位的文章,也是近两年的新坑,但是资源也是需要不少。 论文地址:OV-VG: A Benchmark for Open-Vocabulary Visua