AI Paper Atlas

Research map / 3D vision / 3D generation

View N-Gram Network for 3D Object Retrieval

Xinwei He, Tengteng Huang, Song Bai, Xiang Bai

ICCV 2019 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 68 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
increase n-gram size from 1 to 3 (attention aggregation) (ablation)VNN · ModelNet40 ablationmAP: 80.7 -> 84.9Improved
use n-gram size 5 instead of 3 (ablation)VNN · ModelNet40 ablationmAP: 84.9 -> 87.3Improved
use n-gram size 7 instead of 5 (ablation)VNN · ModelNet40 ablationmAP: 87.3 -> 85.9Hurt
fuse n-gram sizes 3+5+7 instead of single size 5 (ablation)VNN · ModelNet40 ablationmAP: 87.3 -> 88.9Improved
fuse n-gram sizes 3+5 instead of single size 3 (ablation)VNN · ModelNet40 ablationmAP: 84.9 -> 88.0Improved
use attentional aggregation instead of max-pooling (n-gram 5) (ablation)VNN · ModelNet40 ablationmAP: 84.7 -> 87.3Improved
use attentional aggregation instead of max-pooling (3+5+7) (ablation)VNN · ModelNet40 ablationmAP: 88.2 -> 88.9Improved
add triplet-center loss to softmax (ablation)VNN · ModelNet40 ablationmAP: 88.9 -> 89.5Improved
add view n-gram network over max-pool MVCNN baselineMVCNN · ModelNet40 retrievalmAP: 72.9 -> 88.9Improved
add view n-gram network over max-pool MVCNN baselineMVCNN · ModelNet10 retrievalmAP: 80.1 -> 92.8Improved
use VGG-19 backbone instead of VGG-AVNN · ModelNet40 retrievalmAP: 88.9 -> 89.3Improved

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