Research map / 3D vision / 3D generation
View N-Gram Network for 3D Object Retrieval
Xinwei He, Tengteng Huang, Song Bai, Xiang Bai
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 |
|---|---|---|---|
| increase n-gram size from 1 to 3 (attention aggregation) (ablation) | VNN · ModelNet40 ablation | mAP: 80.7 -> 84.9 | Improved |
| use n-gram size 5 instead of 3 (ablation) | VNN · ModelNet40 ablation | mAP: 84.9 -> 87.3 | Improved |
| use n-gram size 7 instead of 5 (ablation) | VNN · ModelNet40 ablation | mAP: 87.3 -> 85.9 | Hurt |
| fuse n-gram sizes 3+5+7 instead of single size 5 (ablation) | VNN · ModelNet40 ablation | mAP: 87.3 -> 88.9 | Improved |
| fuse n-gram sizes 3+5 instead of single size 3 (ablation) | VNN · ModelNet40 ablation | mAP: 84.9 -> 88.0 | Improved |
| use attentional aggregation instead of max-pooling (n-gram 5) (ablation) | VNN · ModelNet40 ablation | mAP: 84.7 -> 87.3 | Improved |
| use attentional aggregation instead of max-pooling (3+5+7) (ablation) | VNN · ModelNet40 ablation | mAP: 88.2 -> 88.9 | Improved |
| add triplet-center loss to softmax (ablation) | VNN · ModelNet40 ablation | mAP: 88.9 -> 89.5 | Improved |
| add view n-gram network over max-pool MVCNN baseline | MVCNN · ModelNet40 retrieval | mAP: 72.9 -> 88.9 | Improved |
| add view n-gram network over max-pool MVCNN baseline | MVCNN · ModelNet10 retrieval | mAP: 80.1 -> 92.8 | Improved |
| use VGG-19 backbone instead of VGG-A | VNN · ModelNet40 retrieval | mAP: 88.9 -> 89.3 | Improved |
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.
- GIFT — GIFT: A Real-Time and Scalable 3D Shape Search Engine (CVPR 2016) · better on 4 of 4 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
- MLVCNN: Multi-Loop-View Convolutional Neural Network for 3D Shape Retrieval (AAAI 2019 · similarity 0.89)
- View-GCN: View-Based Graph Convolutional Network for 3D Shape Analysis (CVPR 2020 · similarity 0.89)
- Learning Relationships for Multi-View 3D Object Recognition (ICCV 2019 · similarity 0.89)
- Group-Pair Convolutional Neural Networks for Multi-View Based 3D Object Retrieval (AAAI 2018 · similarity 0.88)
- Learning View-Based Graph Convolutional Network for Multi-View 3D Shape Analysis (TPAMI 2022 · similarity 0.88)
- ImageNet3D: Towards General-Purpose Object-Level 3D Understanding (NeurIPS 2024 · 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.
