Submitted by Sijin Chen.

Submission data

Full namevote2cap-detr
DescriptionEnd to End Transformer with parallel decoding
Publication titleEnd-to-End 3D Dense Captioning with Vote2Cap-DETR
Publication authorsSijin Chen, Hongyuan Zhu, Xin Chen, Yinjie Lei, Tao Chen, Gang YU, Taihao Li
Publication venueCVPR 2023
Publication URLhttps://arxiv.org/abs/2301.02508
Input Data TypesUses XYZ coordinates,Uses RGB values,Uses Normal Vectors
Programming language(s)python, pytorch
HardwareRTX 3090
Websitehttps://github.com/ch3cook-fdu/Vote2Cap-DETR
Submission creation date17 Nov, 2022
Last edited27 Dec, 2023

Captioning

Captioning F1-Score Dense Captioning Object Detection
CIDEr@0.5IoUBLEU-4@0.5IoURouge-L@0.5IoUMETEOR@0.5IoUDCmAPmAP@0.5
0.31280.17780.28420.13160.18250.4454