3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds

Benchmark Model Rank Results
3d-dense-captioning-on-nr3d3DJCG–CIDEr: 38.06BLEU-4: 22.82METEOR: 23.77ROUGE-L: 52.99
3d-dense-captioning-on-scanrefer-dataset3DJCG–CIDEr: 60.86BLEU-4: 39.67METEOR: 27.45ROUGE-L: 59.02