InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring

Zhihao Yuan, Xu Yan 0014, Yinghong Liao, Ruimao Zhang, Sheng Wang 0001, Zhen Li 0026, Shuguang Cui. InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring. In 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10-17, 2021. pages 1771-1780, IEEE, 2021. [doi]

Abstract

Abstract is missing.