ModelNet40
Description
The Princeton ModelNet40 dataset is a benchmark dataset from the area of computer graphics first introduced by Wu et al. (Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, and Jianxiong Xiao. 3d shapenets: A deep representation for volumetric shapes. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1912–1920, 2015.) The ModelNet40 dataset consists of 12,311 objects from 40 popular categories and the graph structure is constructed using a probability graph based on node distance. See 'Hypergraph Neural Networks' (https://arxiv.org/pdf/1809.09401) for details on construction.
Basic statistics
- Nodes: 12311
- Hyperedges: 11638
- Unique hyperedges: 11638
- Max size hyperedge: 30
Hypergraph metadata
| Property | Description |
|---|---|
| type | (STRING) Hypergraph type (e.g., Hypergraph). |
| weighted | (BOOL) Whether the hypergraph is weighted (e.g., false). |
Node metadata
| Property | Description |
|---|---|
| label | (INT) 3D object category label (0-39 for 40 categories) (e.g., 1). |
Hyperedge size distribution
Hyperdegree distribution
Download
- Version 1.0.0 Binary (350.2 KB) JSON (166.3 KB)
Provenance
Source: https://github.com/jianhao2016/AllSet?tab=readme-ov-file
License: MIT
Reproducibility: Instructions and scripts
Citation
When this data is used in published research or for visualization purposes, please cite the following:
Copied!
@inproceedings{chien2022you,
title={You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks},
author={Eli Chien and Chao Pan and Jianhao Peng and Olgica Milenkovic},
booktitle={International Conference on Learning Representations},
year={2022},
url={https://openreview.net/forum?id=hpBTIv2uy_E}
}
@INPROCEEDINGS{wu2015shapenets,
author={Zhirong Wu and Song, Shuran and Khosla, Aditya and Fisher Yu and Linguang Zhang and Xiaoou Tang and Xiao, Jianxiong},
booktitle={2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
title={3D ShapeNets: A deep representation for volumetric shapes},
year={2015},
volume={},
number={},
pages={1912-1920},
keywords={Three-dimensional displays;Shape;Solid modeling;Object recognition;Planning;Computational modeling;Convolution},
doi={10.1109/CVPR.2015.7298801}
}