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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add SLGC (semantic first-order edges) (ablation) | MORE baseline · ScanRefer val (VoteNet detector, RGB input, ablation) | CiDEr@0.5IoU: 33.67 -> 35.46 | Improved |
| add OTAG (ablation) | MORE baseline · ScanRefer val (VoteNet detector, RGB input, ablation) | CiDEr@0.5IoU: 33.67 -> 37.95 | Improved |
| add OTAG on top of SLGC (ablation) | MORE · ScanRefer val (VoteNet detector, RGB input, ablation) | CiDEr@0.5IoU: 35.46 -> 38.98 | Improved |
| add SLGC on top of OTAG (ablation) | MORE · ScanRefer val (VoteNet detector, RGB input, ablation) | CiDEr@0.5IoU: 37.95 -> 38.98 | Improved |
| stack 2 SLGC layers instead of 1 (ablation) | SLGC · ScanRefer val (VoteNet detector, RGB input, ablation) | CiDEr@0.5IoU: 35.46 -> 38.06 | Improved |
| stack 4 SLGC layers instead of 3 (ablation) | SLGC · ScanRefer val (VoteNet detector, RGB input, ablation) | CiDEr@0.5IoU: 38.27 -> 36.58 | Hurt |
| stack SLGC layers from 1 to 4 (ablation) | SLGC · ScanRefer val (VoteNet detector, RGB input, ablation) | MADGap: 17.46 -> 12.28 | Hurt |
| use 1 SLGC + OTAG instead of 2 stacked SLGC (ablation) | MORE · ScanRefer val (VoteNet detector, RGB input, ablation) | CiDEr@0.5IoU: 38.06 -> 38.98 | Improved |
| use 1 SLGC + OTAG instead of 1 SLGC alone (ablation) | MORE · ScanRefer val (VoteNet detector, RGB input, ablation) | MADGap: 17.46 -> 21.70 | Improved |
| MORE vs reproduced Scan2Cap, multi-view features | MORE · ScanRefer val (VoteNet detector, multi-view features) | CiDEr@0.25IoU: 53.88 -> 62.91 | Improved |
| MORE vs reproduced Scan2Cap, RGB input | MORE · ScanRefer val (VoteNet detector, RGB input) | CiDEr@0.5IoU: 35.11 -> 38.98 | Improved |
| MORE vs Scan2Cap on BLEU-4@0.5IoU, multi-view features | MORE · ScanRefer val (VoteNet detector, multi-view features) | BLEU-4@0.5IoU: 23.32 -> 22.93 | Hurt |
Closest papers by meaning
- Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning (CVPR 2019 · similarity 0.89)
- Object-Centric Representation Learning for Enhanced 3D Semantic Scene Graph Prediction (NeurIPS 2025 · similarity 0.87)
- DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generation (CVPR 2024 · similarity 0.86)
- Leveraging Predicate and Triplet Learning for Scene Graph Generation (CVPR 2024 · similarity 0.86)
- Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships (CVPR 2024 · similarity 0.86)
- Relation-aware Hierarchical Prompt for Open-vocabulary Scene Graph Generation (AAAI 2025 · similarity 0.86)
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.
