{"id":21384666,"url":"https://github.com/imoonlab/hgm2r","last_synced_at":"2025-07-13T14:31:42.241Z","repository":{"id":219724836,"uuid":"747537943","full_name":"iMoonLab/HGM2R","owner":"iMoonLab","description":"Source code for IEEE TPAMI 2024 \"Hypergraph-Based Multi-Modal Representation for Open-Set 3D Object Retrieval\"","archived":false,"fork":false,"pushed_at":"2024-02-02T07:15:54.000Z","size":6997,"stargazers_count":31,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-04-07T12:52:03.646Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://ieeexplore.ieee.org/abstract/document/10319392/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/iMoonLab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-01-24T06:05:18.000Z","updated_at":"2025-02-28T07:56:30.000Z","dependencies_parsed_at":"2024-02-02T08:43:49.733Z","dependency_job_id":null,"html_url":"https://github.com/iMoonLab/HGM2R","commit_stats":null,"previous_names":["imoonlab/hgm2r"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/iMoonLab/HGM2R","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iMoonLab%2FHGM2R","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iMoonLab%2FHGM2R/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iMoonLab%2FHGM2R/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iMoonLab%2FHGM2R/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/iMoonLab","download_url":"https://codeload.github.com/iMoonLab/HGM2R/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iMoonLab%2FHGM2R/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265155716,"owners_count":23719567,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-22T11:42:29.570Z","updated_at":"2025-07-13T14:31:37.202Z","avatar_url":"https://github.com/iMoonLab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Hypergraph-Based Multi-Modal Representation for Open-Set 3D Object Retrieval\nThis repository contains the source code for the paper \"Hypergraph-Based Multi-Modal Representation for Open-Set 3D Object Retrieval\" published in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2024 by [Yifan Feng](https://fengyifan.site/), Shuyi Ji, Yu-Shen Liu, Shaoyi Du, Qionghai Dai, Yue Gao*. This paper is available at [here](https://ieeexplore.ieee.org/abstract/document/10319392/).\n\n![framework](doc/fw.jpg)\n\n## Introduction\nIn this repository, we provide our implementation of Hypergraph-Based Multi-Modal Representation (HGM2R), which is based on the following environments:\n* [python 3.9](https://www.python.org/): basic programming language.\n* [torch 1.12.1](https://pytorch.org/): for computation.\n* [hydra-core 1.3.2](https://hydra.cc/docs/intro/): for configuration and multi-run management.\n\n## Installation\n1. Clone this repository.\n2. Install the required libraries.\n``` bash\npip install -r requirements.txt\n```\n\n## Downloads\nIn this paper, we release four datasets (OS-ESB-core, OS-NTU-core, OS-MN40-core, and OS-ABO-core) for Open-Set Retrieval task, which can be download in [here](https://moon-lab.tech/os3dor). Our dataset splitting files of the four datasets can be download in [here](https://pan.baidu.com/s/1uvrT9xBps6DENndxyu8V_A?pwd=evby). And those pre-extracted features (80 files) of the four datasets can be download in [here](https://pan.baidu.com/s/1gylhaVO9dXmTbfIqV3DMBw?pwd=y774). The pre-extracted features should be placed in the `feature` folder.\n\n## Usage\nFirst, you should compress the voxel features with the following command:\n```bash\npython pre_vox_ft_compress.py\n```\nThen, you can train the HGM2R model with the following command:\n```bash\npython train_hgm2r.py\n```\nTo change the dataset, you can modify the `line 272` of `train_hgm2r.py` with names (esb, ntu, mn40, abo):\n```python\ndataset = \"esb\" # esb, ntu, mn40, abo\n```\n\n## Citation\nIf you find this repository useful in your research, please cite our following papers:\n```\n@article{feng2023hypergraph,\n  title={Hypergraph-Based Multi-Modal Representation for Open-Set 3D Object Retrieval},\n  author={Feng, Yifan and Ji, Shuyi and Liu, Yu-Shen and Du, Shaoyi and Dai, Qionghai and Gao, Yue},\n  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},\n  year={2023},\n  publisher={IEEE}\n}\n\n@inproceedings{feng2019hypergraph,\n  title={Hypergraph neural networks},\n  author={Feng, Yifan and You, Haoxuan and Zhang, Zizhao and Ji, Rongrong and Gao, Yue},\n  booktitle={Proceedings of the AAAI conference on artificial intelligence},\n  volume={33},\n  number={01},\n  pages={3558--3565},\n  year={2019}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fimoonlab%2Fhgm2r","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fimoonlab%2Fhgm2r","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fimoonlab%2Fhgm2r/lists"}