AI Paper Atlas

Research map / Point clouds / Point cloud classification

X-Trans2Cap: Cross-Modal Knowledge Transfer Using Transformer for 3D Dense Captioning

Zhihao Yuan, Xu Yan, Yinghong Liao, Yao Guo, Guanbin Li, Shuguang Cui, Zhen Li

CVPR 2022 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D · 80 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
Train with a multimodal teacher, 3D-only student, CMF, and feature alignmentTransCap · ScanRefer Oracle DCCIDEr: 75.75 -> 87.09Improved
Train with a multimodal teacher, 3D-only student, CMF, and feature alignmentTransCap · Nr3D Oracle DCCIDEr: 70.60 -> 80.02Improved
Use cross-modal knowledge transferTransCap · ScanRefer Scan DCCIDEr@0.25: 55.36 -> 58.81Improved
Add CIDEr-D reward lossX-Trans2Cap · ScanRefer Oracle DCCIDEr: 87.09 -> 97.17Improved
Initialize with a separately pre-trained teacher instead of joint teacher-student trainingX-Trans2Cap · ScanRefer Oracle DCCIDEr: 87.09 -> 79.41Hurt
Add feature alignment loss (ablation)X-Trans2Cap · ScanRefer Oracle DCCIDEr: 79.58 -> 87.09Improved
Add cross-modal fusion module (ablation)X-Trans2Cap · ScanRefer Oracle DCCIDEr: 80.54 -> 87.09Improved
Use the standard CMF rather than concatenation (ablation)X-Trans2Cap · ScanRefer Oracle DCCIDEr: 79.87 -> 87.09Improved
Add random masking to CMF (ablation)X-Trans2Cap · ScanRefer Oracle DCCIDEr: 85.36 -> 87.09Improved
Use standard CMF rather than attention-based fusion (ablation)X-Trans2Cap · ScanRefer Oracle DCCIDEr: 80.85 -> 87.09Improved
Add object class to the student input (ablation)X-Trans2Cap · ScanRefer Oracle DCCIDEr: 70.41 -> 87.09Improved
Add 3D bounding box to the student input (ablation)X-Trans2Cap · ScanRefer Oracle DCCIDEr: 82.99 -> 87.09Improved

Later papers that compared with this method

1 later accepted paper reports X-Trans2Cap* 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 1 of 1 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