{
 "id": "OpenFace-CQUPT/FaceCaption-15M",
 "owner": "OpenFace-CQUPT",
 "name": "FaceCaption-15M",
 "downloads": 245,
 "likes": 107,
 "last_modified": "2026-07-26T13:19:17.000Z",
 "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": "```tex\n@misc{dai202415mmultimodalfacialimagetext,\n      title={15M Multimodal Facial Image-Text Dataset}, \n      author={Dawei Dai and YuTang Li and YingGe Liu and Mingming Jia and Zhang YuanHui and Guoyin Wang},\n      year={2024},\n      eprint={2407.08515},\n      archivePrefix={arXiv},\n      primaryClass={cs.CV},\n      url={https://arxiv.org/abs/2407.08515}, \n}\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}\n```",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "7d0dc054d37493396072016410fa0588a40e3b1d",
 "stated_evidence": "https://huggingface.co/datasets/OpenFace-CQUPT/FaceCaption-15M/blob/7d0dc054d37493396072016410fa0588a40e3b1d/README.md",
 "file_evidence": "https://huggingface.co/datasets/OpenFace-CQUPT/FaceCaption-15M/tree/7d0dc054d37493396072016410fa0588a40e3b1d",
 "card_nc": false
}