Submitted by yufeng zhong.

Submission data

Full nameGroupFree 3D+Multi-Transformer
Publication titleContextual Modeling for 3D Dense Captioning on Point Clouds
Publication authorsYufeng Zhong, Long Xu, Jiebo Luo, Lin Ma
Publication URLhttps://arxiv.org/abs/2210.03925
Input Data TypesUses XYZ coordinates,Uses Multiview Image Features,Uses Normal Vectors
Programming language(s)Python
HardwareRTX 3090Ti
Submission creation date27 Sep, 2022
Last edited13 Oct, 2022

Captioning

Captioning F1-Score Dense Captioning Object Detection
CIDEr@0.5IoUBLEU-4@0.5IoURouge-L@0.5IoUMETEOR@0.5IoUDCmAPmAP@0.5
0.23480.13830.22500.10300.13980.2966