Buckets:

redmingwei's picture
|
download
raw
18.6 kB

📜 署名与许可归属声明 / Attribution & Licensing Notice

本桶(illusion-brain/training-data)收录的 10 组数据集与 7 个小模型检查点来自不同来源,各受其原始许可证约束。 本文档提供各资源的署名信息、许可证声明、来源链接与修改说明。

再分发 (Redistribution) 说明: 本桶以原样方式(as-is)从各上游 Hugging Face 仓库复制文件, 未对数据内容做任何转换或修改(除文件组织路径外)。


目录

数据集

模型


📦 数据集

1. THINGS-EEG — CC-BY 4.0

项目 详情
作者 (Creator) Gifford, Alessandro T.; Dwivedi, Kshitij; Roig, Gemma; Cichy, Radoslaw M.
版权声明 © 2022 Gifford, Dwivedi, Roig & Cichy
许可证 Creative Commons Attribution 4.0 International (CC-BY 4.0)
许可证链接 https://creativecommons.org/licenses/by/4.0/
原始来源 (URI) https://osf.io/3jk45/ (OSF, CC-BY 4.0)
本桶副本来源 https://huggingface.co/datasets/Haitao999/things-eeg
修改说明 上游镜像将 EEG 数据重压缩为 float16(减半存储);本桶再分发时未做进一步修改
免责声明 本数据按"原样"提供,不附带任何明示或默示担保(详见 CC-BY 4.0 第 5 节)

引用要求:

@article{gifford2022large,
  title={A large and rich EEG dataset for modeling human visual object recognition},
  author={Gifford, Alessandro T and Dwivedi, Kshitij and Roig, Gemma and Cichy, Radoslaw M},
  journal={NeuroImage}, volume={264}, pages={119754}, year={2022},
  publisher={Elsevier}
}

另请引用上游处理版本论文:

@inproceedings{wu2025ubp,
  title={Bridging the Vision-Brain Gap with an Uncertainty-Aware Blur Prior},
  author={Wu, Haitao and Li, Qing and Zhang, Changqing and He, Zhen and Ying, Xiaomin},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2025}
}

2. EEG-Image-Decode — CC-BY 4.0

项目 详情
作者 (Creator) Li, Dongyang; Wei, Chen; et al. (Zhejiang University 等)
版权声明 © 2024 The Authors
许可证 Creative Commons Attribution 4.0 International (CC-BY 4.0)
许可证链接 https://creativecommons.org/licenses/by/4.0/
来源 (URI) https://huggingface.co/datasets/LidongYang/EEG_Image_decode
修改说明 本桶再分发时未做修改
免责声明 本数据按"原样"提供,不附带任何担保(详见 CC-BY 4.0 第 5 节)

引用要求 (NeurIPS 2024, arXiv:2403.07721):

@inproceedings{li2024visual,
  title={Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusion},
  author={Li, Dongyang and Wei, Chen and others},
  booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
  year={2024}
}

3. Algonauts 2025 特征 — CC0 1.0

项目 详情
作者 (Creator) MedARC 团队;底层脑数据: Courtois Neuromod (CNeuroMod) 项目参与者
许可证 Creative Commons CC0 1.0 Universal (公共领域贡献)
许可证链接 https://creativecommons.org/publicdomain/zero/1.0/
来源 (URI) https://huggingface.co/datasets/medarc/algonauts_2025.features
修改说明 本桶再分发时未做修改
权利说明 CC0 下作者已放弃全部著作权,无署名法律义务;以下引用出于学术规范

来源声明: The CNeuroMod data used in the Algonauts 2025 Challenge has been openly shared under a Creative Commons CC0 license by a subset of CNeuroMod participants.

引用建议 (学术规范):

@article{algonauts2025,
  title={The Algonauts Project 2025 Challenge: How the Human Brain Makes Sense of Multimodal Movies},
  author={The Algonauts Project},
  year={2025}
}

4. CineBrain — Apache-2.0

项目 详情
作者 (Creator) 复旦大学 (Fudan University) — Jianxiong Gao, Yanwei Fu 等
版权声明 Copyright 2026 Fudan University
许可证 Apache License 2.0
许可证链接 https://www.apache.org/licenses/LICENSE-2.0
来源 (URI) https://huggingface.co/datasets/Fudan-fMRI/CineBrain
修改说明 本桶再分发时未做修改
免责声明 依 Apache-2.0 第 7 节,本数据按"原样"提供,不附带任何担保

引用要求 (CVPR 2026, arXiv:2503.06940):

@article{gao2025cinebrain,
  title={CineBrain: A Large-Scale Multi-Modal Brain Dataset During Naturalistic Audiovisual Narrative Processing},
  author={Gao, Jianxiong and Fu, Yanwei and others},
  journal={arXiv preprint arXiv:2503.06940},
  year={2025}
}

5. fMRI-Shape — Apache-2.0

项目 详情
作者 (Creator) 复旦大学 (Fudan University) — Jianxiong Gao 等
版权声明 Copyright 2024-2025 Fudan University
许可证 Apache License 2.0
许可证链接 https://www.apache.org/licenses/LICENSE-2.0
来源 (URI) https://huggingface.co/datasets/Fudan-fMRI/fMRI-Shape
修改说明 本桶再分发时未做修改
免责声明 依 Apache-2.0 第 7 节,本数据按"原样"提供,不附带任何担保

引用要求 (MinD-3D++, arXiv:2409.11315):

@article{gao2024mind3dpp,
  title={MinD-3D++: Advancing fMRI-Based 3D Reconstruction with High-Quality Textured Mesh Generation and a Comprehensive Dataset},
  author={Gao, Jianxiong and Fu, Yuqian and Wang, Yun and Qian, Xuelin and Feng, Jianfeng and Fu, Yanwei},
  journal={arXiv preprint arXiv:2409.11315},
  year={2024}
}

6. Steinmetz Spike 数据 — CC-BY 4.0

项目 详情
原始作者 (Creator) Steinmetz, Nicholas A.; Zatka-Haas, Peter; Carandini, Matteo; Harris, Kenneth D.
版权声明 © 2019 The Authors (Nature)
许可证 Creative Commons Attribution 4.0 International (CC-BY 4.0)
许可证链接 https://creativecommons.org/licenses/by/4.0/
原始来源 Steinmetz et al. 2019, Nature 576:266-273
本桶副本来源 https://huggingface.co/datasets/mysteriousauthor/spikeprophecy-steinmetz
修改说明 上游做了预处理(50ms 分箱尖峰计数张量);本桶再分发时未做进一步修改
免责声明 本数据按"原样"提供,不附带任何担保(详见 CC-BY 4.0 第 5 节)

引用要求:

@article{steinmetz2019distributed,
  title={Distributed coding of choice, action and engagement across the mouse brain},
  author={Steinmetz, Nicholas A and Zatka-Haas, Peter and Carandini, Matteo and Harris, Kenneth D},
  journal={Nature}, volume={576}, number={7786}, pages={266--273}, year={2019}
}

7. FlyWire 连接组 — CC-BY 4.0

项目 详情
原始作者 (Creator) FlyWire Consortium — Dorkenwald, Sven; Matsliah, Arie; et al.
版权声明 © 2024 The Authors (Nature)
许可证 Creative Commons Attribution 4.0 International (CC-BY 4.0)
许可证链接 https://creativecommons.org/licenses/by/4.0/
原始来源 Dorkenwald et al. 2024, Nature — FlyWire FAFB v783
本桶副本来源 https://huggingface.co/datasets/SLOP011/flywire-fafb-connectome
修改说明 上游做了打包(GNN 就绪的 parquet 格式);本桶再分发时未做进一步修改
免责声明 本数据按"原样"提供,不附带任何担保(详见 CC-BY 4.0 第 5 节)

引用要求:

@article{dorkenwald2024neuronal,
  title={Neuronal wiring diagram of an adult brain},
  author={Dorkenwald, Sven and Matsliah, Arie and others},
  journal={Nature}, volume={634}, pages={124--138}, year={2024}
}

8. Sleep Staging Sequences(Sleep-EDF 派生)— ODC-BY 1.0

项目 详情
上传者 wbxlala(Hugging Face)
许可证 ODC-BY 1.0 (Open Data Commons Attribution License)
许可证链接 https://opendatacommons.org/licenses/by/1-0/
来源 (URI) https://huggingface.co/datasets/wbxlala/sleep_edf_str
衍生自 Sleep-EDF Expanded, PhysioNet
修改说明 序列被抽取并格式化为 CSV(每序列 40 采样,label=睡眠阶段);本桶再分发时未做进一步修改

引用要求:

@article{kemp2000analysis,
  title={Analysis of a sleep-dependent neuronal feedback loop...},
  author={Kemp, Bob and Zwinderman, Aeilko H and others},
  journal={IEEE Transactions on Biomedical Engineering}, year={2000}
}
@article{goldberger2000physiobank,
  title={{PhysioBank, PhysioToolkit, and PhysioNet}},
  author={Goldberger, Ary L and others},
  journal={Circulation}, volume={101}, number={23}, year={2000}
}

9. CHB-MIT Preprocessed Features(癫痫预测)— ODC-BY 1.0

项目 详情
上传者 JayF14(Hugging Face)/ Neuro_Pulse 项目
许可证 ODC-BY 1.0 (Open Data Commons Attribution License)
许可证链接 https://opendatacommons.org/licenses/by/1-0/
来源 (URI) https://huggingface.co/datasets/JayF14/chb-mit-preprocessed-eeg
衍生自 CHB-MIT Scalp EEG Database v1.0.0, PhysioNet (DOI: 10.13026/C2K01R)
修改说明 特征工程化 epochs(347,075 个标注 epoch,每个 590 特征);本桶再分发时未做进一步修改
使用限制 仅限研究用途,不得用于临床决策

引用要求 (按 PhysioNet 官方规定):

@article{guttag2010chbmit,
  author = {Guttag, John},
  title = {{CHB-MIT Scalp EEG Database}},
  journal = {{PhysioNet}}, year = {2010}, note = {Version 1.0.0},
  doi = {10.13026/C2K01R}
}
@phdthesis{shoeb2009application,
  title = {Application of Machine Learning to Epileptic Seizure Onset Detection and Treatment},
  author = {Shoeb, Ali Hossam}, year = {2009}, school = {Massachusetts Institute of Technology}
}

10. BCI Competition IV 2a Tensors(运动想象)— MIT

项目 详情
上传者 graycatHCO3(Hugging Face)
许可证 MIT License
许可证链接 https://opensource.org/licenses/MIT
来源 (URI) https://huggingface.co/datasets/graycatHCO3/BCICIV_2A_tensor
衍生自 BCI Competition IV Dataset 2a (Graz), https://www.bbci.de/competition/iv/
修改说明 转换为 PyTorch 张量格式(.pt);本桶再分发时未做进一步修改

引用要求:

@inproceedings{brunner2008bci,
  title={BCI Competition 2008 -- Graz data set A},
  author={Brunner, Clemens and Leeb, Robert and M{\"u}ller-Putz, Gernot and Schl{\"o}gl, Alois and Pfurtscheller, Gert},
  year={2008}
}

🐣 模型

11. MIRepNet — MIT

项目 详情
作者 Liu, Dingkun et al.
许可证 MIT License
来源 (URI) https://huggingface.co/braindecode/mirepnet-pretrained
原始发布 https://github.com/staraink/MIRepNet
修改说明 braindecode 团队转换格式;本桶再分发时未做进一步修改
备注 数据集许可与检查点许可相互独立

引用要求:

@article{liu2026mirepnet,
  title = {MIRepNet: A pipeline and pre-trained model for EEG-based motor imagery classification},
  journal = {Knowledge-Based Systems},
  volume = {343}, pages = {115966}, year = {2026},
  doi = {10.1016/j.knosys.2026.115966},
  author = {Liu, Dingkun and others}
}

12. CBraMod — BSD-3-Clause

项目 详情
作者 Wang, Jiquan et al.(浙江大学 + 阿里巴巴)
许可证 BSD-3-Clause
来源 (URI) https://huggingface.co/braindecode/cbramod-pretrained
原始发布 https://github.com/wjq-learning/cbramod
修改说明 braindecode 团队转换格式;本桶再分发时未做进一步修改

引用要求 (ICLR 2025):

@inproceedings{wang2025cbramod,
  title={CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding},
  author={Wang, Jiquan and others},
  booktitle={International Conference on Learning Representations (ICLR)},
  year={2025}
}

13. LaBraM — BSD-3-Clause

项目 详情
作者 Jiang, Wei-Bang; Zhao, Li-Ming; Lu, Bao-Liang(清华大学)
许可证 BSD-3-Clause
来源 (URI) https://huggingface.co/braindecode/labram-pretrained
原始发布 https://github.com/935963004/LaBraM
修改说明 braindecode 团队转换格式;本桶再分发时未做进一步修改

引用要求 (ICLR 2024):

@inproceedings{jiang2024labram,
  title={Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI},
  author={Jiang, Wei-Bang and Zhao, Li-Ming and Lu, Bao-Liang},
  booktitle={International Conference on Learning Representations (ICLR)},
  year={2024}
}

14. BIOT — BSD-3-Clause

项目 详情
作者 Yang, Chaoqi; Westover, M. Brandon; Sun, Jimeng(UIUC)
许可证 BSD-3-Clause
来源 (URI) https://huggingface.co/braindecode/biot-pretrained-six-datasets-18chs
原始发布 https://github.com/ycq091044/BIOT
修改说明 braindecode 团队转换格式;本桶再分发时未做进一步修改

引用要求 (NeurIPS 2023):

@inproceedings{yang2023biot,
  title={BIOT: Biosignal Transformer for Cross-data Learning in the Wild},
  author={Yang, Chaoqi and Westover, M. Brandon and Sun, Jimeng},
  booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
  year={2023}
}

15. EEG-DINO Small — BSD-3-Clause

项目 详情
作者 Wang, Xujia; Liu, Xuhui; Liu, Xi; Si, Qian; Xu, Zhaoliang; Li, Yang; Zhen, Xiantong
许可证 BSD-3-Clause
来源 (URI) https://huggingface.co/braindecode/eegdino-small-pretrained
修改说明 braindecode 团队打包(OpenEEG-Bench 计划);本桶再分发时未做进一步修改
预训练数据 Temple University Hospital EEG Corpus (TUEG),19 通道 @200Hz

引用要求 (需同时引用架构论文和 braindecode,MICCAI 2025):

@inproceedings{wang2025eegdino,
  title     = {{EEG-DINO}: Learning {EEG} Foundation Models via Hierarchical Self-Distillation},
  author    = {Wang, Xujia and Liu, Xuhui and Liu, Xi and Si, Qian and Xu, Zhaoliang and Li, Yang and Zhen, Xiantong},
  booktitle = {Medical Image Computing and Computer Assisted Intervention (MICCAI)},
  year      = {2025}
}

16. Signal-JEPA — MIT

项目 详情
作者 Guetschel, Pierre; Moreau, Thomas; Tangermann, Michael
许可证 MIT License
来源 (URI) https://huggingface.co/braindecode/signal-jepa
修改说明 braindecode 团队打包;本桶再分发时未做进一步修改
预训练数据 Lee2019(62 通道,10-10 布局,128Hz)

引用要求:

@article{guetschel2024sjepa,
  title   = {S-JEPA: towards seamless cross-dataset transfer through dynamic spatial attention},
  author  = {Guetschel, Pierre and Moreau, Thomas and Tangermann, Michael},
  journal = {arXiv preprint arXiv:2403.11772},
  year    = {2024}
}

17. BrainTokenizer — MIT

项目 详情
作者 Xiao, Q.; Cui, Z.; Zhang, C.; Chen, S.; Wu, W.; Thwaites, A.; Woolgar, A.; Zhou, B.; Zhang, C.
许可证 MIT License
来源 (URI) https://huggingface.co/braindecode/braintokenizer-pretrained
原始发布 https://huggingface.co/OpenTSLab/BrainOmni(MIT)
修改说明 braindecode 团队转换键名格式并去除预训练掩码预测器;本桶再分发时未做进一步修改

引用要求 (NeurIPS 2025):

@inproceedings{xiao2025brainomni,
  title     = {BrainOmni: A Brain Foundation Model for Unified EEG and MEG Signals},
  author    = {Xiao, Q. and Cui, Z. and Zhang, C. and Chen, S. and Wu, W. and Thwaites, A. and Woolgar, A. and Zhou, B. and Zhang, C.},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2025}
}

许可证全文位置


许可证义务速查

许可证 署名 许可证声明 修改标注 担保免责
CC-BY 4.0 必须 必须 必须 必须
CC0 1.0 无义务 无义务 无义务 无义务
Apache-2.0 保留声明 附许可证 变更说明 必须
ODC-BY 1.0 必须 必须 建议 必须
MIT 保留声明 附许可证 无要求 必须
BSD-3-Clause 保留声明 附许可证 无要求 必须

如有疑问请以 LICENSES/ 中的许可证全文为准。


最后更新: 2026-10-16 · 由幻脑组织维护

Xet Storage Details

Size:
18.6 kB
·
Xet hash:
cbac3477f6aefe6af22bcf0e0d711ff4d8ef1c3f447c0788f4ce7f0cb605b348

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.