{
 "id": "omni-research/Tarsier2-Recap-585K",
 "owner": "omni-research",
 "name": "Tarsier2-Recap-585K",
 "downloads": 2957,
 "likes": 22,
 "last_modified": "2025-01-24T08:15:30.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": "auto",
 "tasks": [
  "video-text-to-text"
 ],
 "citation": "@misc{yuan2025tarsier2advancinglargevisionlanguage,\r\n      title={Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding}, \r\n      author={Liping Yuan and Jiawei Wang and Haomiao Sun and Yuchen Zhang and Yuan Lin},\r\n      year={2025},\r\n      eprint={2501.07888},\r\n      archivePrefix={arXiv},\r\n      primaryClass={cs.CV},\r\n      url={https://arxiv.org/abs/2501.07888}, \r\n}",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "5cffa8342bbd9900fb50fdb7fd1b5f2cd1778ac4",
 "stated_evidence": "https://huggingface.co/datasets/omni-research/Tarsier2-Recap-585K/blob/5cffa8342bbd9900fb50fdb7fd1b5f2cd1778ac4/README.md",
 "file_evidence": "https://huggingface.co/datasets/omni-research/Tarsier2-Recap-585K/tree/5cffa8342bbd9900fb50fdb7fd1b5f2cd1778ac4",
 "card_nc": false
}