Method Detail: 3DJCG

Back to Leaderboard
Benchmark: VLMOD
Short name: 3DJCG
Long name: 3DJCG
Description: @inproceedings{cai20223djcg, title={3djcg: A unified framework for joint dense captioning and visual grounding on 3d point clouds}, author={Cai, Daigang and Zhao, Lichen and Zhang, Jing and Sheng, Lu and Xu, Dong}, booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition}, pages={16464--16473}, year={2022} }
Reference: Cai, Daigang, Zhao, Lichen, Zhang, Jing, Sheng, Lu, Xu, Dong, 3djcg: A unified framework for joint dense captioning and visual grounding on 3d point clouds. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022.
Last submitted: August 31, 2025
Published: August 31, 2025 at 11:24:58
Submissions: 1
Project page / code: N/A
Open source: No

Benchmark performance

Submission Date F1 (↑) Precision (↑) Recall (↑) TP (↑) FP (↓) FN (↓)
2025-08-31 11:25 63.4100 49.7700 87.3600 55657 56172 8051