[CVPR2022 Oral] 3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds
deep-learning pytorch 3d-vision dense-captioning visual-grounding scanrefer cvpr2022 3d-visual-grounding 3d-vision-and-language 3d-visual-question-answering 3d-vqa
-
Updated
Jan 29, 2023 - Python