{
 "id": "OpenFace-CQUPT/HumanCaption-10M",
 "owner": "OpenFace-CQUPT",
 "name": "HumanCaption-10M",
 "downloads": 172,
 "likes": 48,
 "last_modified": "2026-07-26T13:21:27.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "image-to-text",
  "text-to-image"
 ],
 "citation": "@misc{dai2024humanvlmfoundationhumanscenevisionlanguage,\n      title={HumanVLM: Foundation for Human-Scene Vision-Language Model}, \n      author={Dawei Dai and Xu Long and Li Yutang and Zhang Yuanhui and Shuyin Xia},\n      year={2024},\n      eprint={2411.03034},\n      archivePrefix={arXiv},\n      primaryClass={cs.AI},\n      url={https://arxiv.org/abs/2411.03034}, \n}\n@article{dai2026facecaption15m,\n    title={FaceCaption-15M: Benchmarking and Enhancing Facial Vision-Language Models},\n    author={Dawei Dai and YuTang Li and YingGe Liu and Mingming Jia and Zhang YuanHui and Guoyin Wang},\n    journal={IEEE Transactions on Circuits and Systems for Video Technology},\n    year={2026},\n    doi={10.1109/TCSVT.2026.3713342},\n    keywords={Modeling;Faces;Training;Conferences;Computers;Computer vision;Learning (artificial intelligence);Pattern recognition;Educational institutions;Machine learning;Image-Text Dataset;Face Task},\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "6cad21f899d9d282731194be80cad371bda33037",
 "stated_evidence": "https://huggingface.co/datasets/OpenFace-CQUPT/HumanCaption-10M/blob/6cad21f899d9d282731194be80cad371bda33037/README.md",
 "file_evidence": "https://huggingface.co/datasets/OpenFace-CQUPT/HumanCaption-10M/tree/6cad21f899d9d282731194be80cad371bda33037",
 "card_nc": false
}