AI Paper Atlas

Research map / Point clouds / Point cloud classification

3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds

Lichen Zhao, Daigang Cai, Lu Sheng, Dong Xu

ICCV 2021 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D · 161 citations (OpenAlex)

Read the paperCheck 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
add multiplex-attention cross-modal fusion to ScanRefer-like baseline (ablation)3DVG-Transformer · ScanRefer val (2D+3D)Acc@0.5: 26.66 -> 31.15Improved
add multiplex-attention cross-modal fusion (ablation)3DVG-Transformer · ScanRefer val (2D+3D)Acc@0.25: 41.45 -> 43.65Improved
add feature augmentation (proposal copy&paste, word erase) (ablation)3DVG-Transformer · ScanRefer val (2D+3D)Acc@0.5: 31.15 -> 32.25Improved
add feature augmentation (ablation)3DVG-Transformer · ScanRefer val (2D+3D)Acc@0.25: 43.65 -> 45.76Improved
add coordinate-guided contextual aggregation (CCA) (ablation)3DVG-Transformer · ScanRefer val (2D+3D)Acc@0.5: 32.25 -> 34.67Improved
add coordinate-guided contextual aggregation (CCA) (ablation)3DVG-Transformer · ScanRefer val (2D+3D)Acc@0.25: 45.76 -> 47.57Improved
add spatial proximity matrix to the attention matrix (Add-SPM) vs no SPM (ablation)3DVG-Transformer · Nr3D valoverall accuracy: 36.6% -> 40.8%Improved
fuse SPM by addition instead of multiplication (ablation)3DVG-Transformer · Nr3D valoverall accuracy: 38.7% -> 40.8%Improved
multiply SPM with attention versus no SPM (ablation)3DVG-Transformer · Nr3D valoverall accuracy: 36.6% -> 38.7%Improved
add SPM (addition) on view-dependent subset (ablation)3DVG-Transformer · Nr3D val (view-dep)accuracy: 32.6% -> 34.8%Improved
Mul SPM vs Add SPM on view-dependent subset (ablation)3DVG-Transformer · Nr3D val (view-dep)accuracy: 34.8% -> 34.8%No clear effect
use full 3DVG-Transformer instead of ScanRefer baseline (multiple-object subset, 2D+3D)3DVG-Transformer · ScanRefer val (multiple)Acc@0.25: 32.73 -> 39.30Improved

Later papers that compared with this method

2 later accepted papers report 3DVG-Transformer as a baseline in their results tables; 2 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