{
 "id": "TornadoLabs/vatex",
 "owner": "TornadoLabs",
 "name": "vatex",
 "downloads": 89,
 "likes": 0,
 "last_modified": "2026-09-29T16:43:09.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "academic-source-terms",
 "licence_link": "https://eric-xw.github.io/vatex-website/",
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "video-classification",
  "text-to-video",
  "video-text-to-text"
 ],
 "citation": "- Original dataset: https://eric-xw.github.io/vatex-website/\n- Paper: Wang et al., ICCV 2019 — VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research\n- 41k clips, captions EN+ZH.\n\nThe video files remain the property of their respective YouTube uploaders. The\nannotations belong to the original dataset authors — cite their paper if you use\nthem. This re-hosting is provided for reproducible research; if you are a rights\nholder and want content removed, open a discussion on this repo.",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "dc7f30ff9887e1f65a2dd34e1f1bf5deb6583a13",
 "stated_evidence": "https://huggingface.co/datasets/TornadoLabs/vatex/blob/dc7f30ff9887e1f65a2dd34e1f1bf5deb6583a13/README.md",
 "file_evidence": "https://huggingface.co/datasets/TornadoLabs/vatex/tree/dc7f30ff9887e1f65a2dd34e1f1bf5deb6583a13",
 "card_nc": false
}