Submitted by Zhihao Yuan.

Submission data

Full nameX-Trans2Cap
Publication titleX-Trans2Cap: Cross-Modal Knowledge Transfer Using Transformer for 3D Dense Captioning
Publication authorsYuan, Zhihao and Yan, Xu and Liao, Yinghong and Guo, Yao and Li, Guanbin and Cui, Shuguang and Li, Zhen
Publication venueCVPR 2022
Publication URLhttps://arxiv.org/abs/2203.00843
Input Data TypesUses XYZ coordinates,Uses RGB values
Programming language(s)python
Hardware2080ti
Websitehttps://github.com/CurryYuan/X-Trans2Cap
Submission creation date29 Aug, 2022
Last edited29 Aug, 2022

Captioning

Captioning F1-Score Dense Captioning Object Detection
CIDEr@0.5IoUBLEU-4@0.5IoURouge-L@0.5IoUMETEOR@0.5IoUDCmAPmAP@0.5
0.12740.08080.13920.06530.12440.2795