Submitted by Lichen Zhao.

Submission data

Full name3DJCG (Captioning) (VoteNet + Feature-Enhancement + Transformer-Based-Head)
DescriptionJoint Training
We use the VoteNet backbone for detection.
Publication title3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds
Publication authorsDaigang Cai, Lichen Zhao, Jing Zhang†, Lu Sheng, Dong Xu
Publication venueCVPR2022 Oral
Publication URL
Input Data TypesUses XYZ coordinates,Uses Multiview Image Features,Uses Normal Vectors
Programming language(s)Python With Cuda
HardwareGeForce RTX 2080 Ti, 11GB RAM
Source code or download URL
Submission creation date12 Sep, 2022
Last edited13 Sep, 2022


Captioning F1-Score Dense Captioning Object Detection