AI Paper Atlas

Research map / Point clouds / Point cloud classification

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

Daigang Cai, Lichen Zhao, Jing Zhang, Lu Sheng, Dong Xu

CVPR 2022 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D · 91 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Jointly train captioning and grounding instead of removing the grounding head (ablation)3DJCG · Scan2CapB-4@0.5: 26.24 -> 31.03Improved
Add attribute and relation-aware feature enhancement (ablation)3DJCG · Scan2CapB-4@0.5: 29.08 -> 31.03Improved
Add ScanRefer grounding data to the training data (ablation)3DJCG · Scan2CapB-4@0.5: 30.40 -> 31.03Improved
Jointly train captioning and grounding instead of removing the captioning head (ablation)3DJCG · ScanReferOverall Acc@0.5: 36.72 -> 37.33Improved
Add attribute and relation-aware feature enhancement (ablation)3DJCG · ScanReferOverall Acc@0.5: 35.12 -> 37.33Improved
Add Scan2Cap captioning data to the training data (ablation)3DJCG · ScanReferOverall Acc@0.5: 36.93 -> 37.33Improved
Fine-tune the pretrained captioning model on Nr3D (ablation)3DJCG-C · Nr3DB-4@0.5: 20.45 -> 22.82Improved
Use 3DJCG-C from scratch rather than Scan2Cap3D captioning · Nr3DB-4@0.5: 17.24 -> 20.45Improved
Use 3DJCG instead of 3DVG-Transformer3D visual grounding · ScanRefer validation, 2D + 3DOverall Acc@0.5: 34.67 -> 37.33Improved
Use 3DJCG instead of Scan2Cap3D dense captioning · Scan2Cap validation, 2D + 3DC@0.5: 39.08 -> 49.48Improved

Later papers that compared with this method

1 later accepted paper reports 3DJCG as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy