Zhengyuan Yang, Songyang Zhang, Liwei Wang 0009, Jiebo Luo. SAT: 2D Semantics Assisted Training for 3D Visual Grounding. In 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10-17, 2021. pages 1836-1846, IEEE, 2021. [doi]
Abstract is missing.