AI Paper Atlas

Research map / Point clouds / Point cloud classification

MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes

Yang Jiao, Shaoxiang Chen, Zequn Jie, Jingjing Chen, Lin Ma, Yu-Gang Jiang

ECCV 2022 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D · 40 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 SLGC (semantic first-order edges) (ablation)MORE baseline · ScanRefer val (VoteNet detector, RGB input, ablation)CiDEr@0.5IoU: 33.67 -> 35.46Improved
add OTAG (ablation)MORE baseline · ScanRefer val (VoteNet detector, RGB input, ablation)CiDEr@0.5IoU: 33.67 -> 37.95Improved
add OTAG on top of SLGC (ablation)MORE · ScanRefer val (VoteNet detector, RGB input, ablation)CiDEr@0.5IoU: 35.46 -> 38.98Improved
add SLGC on top of OTAG (ablation)MORE · ScanRefer val (VoteNet detector, RGB input, ablation)CiDEr@0.5IoU: 37.95 -> 38.98Improved
stack 2 SLGC layers instead of 1 (ablation)SLGC · ScanRefer val (VoteNet detector, RGB input, ablation)CiDEr@0.5IoU: 35.46 -> 38.06Improved
stack 4 SLGC layers instead of 3 (ablation)SLGC · ScanRefer val (VoteNet detector, RGB input, ablation)CiDEr@0.5IoU: 38.27 -> 36.58Hurt
stack SLGC layers from 1 to 4 (ablation)SLGC · ScanRefer val (VoteNet detector, RGB input, ablation)MADGap: 17.46 -> 12.28Hurt
use 1 SLGC + OTAG instead of 2 stacked SLGC (ablation)MORE · ScanRefer val (VoteNet detector, RGB input, ablation)CiDEr@0.5IoU: 38.06 -> 38.98Improved
use 1 SLGC + OTAG instead of 1 SLGC alone (ablation)MORE · ScanRefer val (VoteNet detector, RGB input, ablation)MADGap: 17.46 -> 21.70Improved
MORE vs reproduced Scan2Cap, multi-view featuresMORE · ScanRefer val (VoteNet detector, multi-view features)CiDEr@0.25IoU: 53.88 -> 62.91Improved
MORE vs reproduced Scan2Cap, RGB inputMORE · ScanRefer val (VoteNet detector, RGB input)CiDEr@0.5IoU: 35.11 -> 38.98Improved
MORE vs Scan2Cap on BLEU-4@0.5IoU, multi-view featuresMORE · ScanRefer val (VoteNet detector, multi-view features)BLEU-4@0.5IoU: 23.32 -> 22.93Hurt

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