{
    "scope": "published-public-metadata",
    "resource": {
        "id": "AISLI-R-55E951F568F0152E5099",
        "kind": "dataset",
        "title": "YouTube 8 Million - Data Lakehouse Ready",
        "summary": "This both the original .tfrecords and a Parquet representation of the [YouTube 8 Million dataset](https://research.google.com/youtube8m/). YouTube-8M is a large-scale labeled video dataset that consists of millions of YouTube video IDs, with high-quality machine-generated annotations from a diverse vocabulary of 3,800+ visual entities. It comes with precomputed audio-visual features from billions of frames and audio segments, designed to fit on a single hard disk. This dataset also includes the YouTube-8M Segments data from June 2019. This dataset is 'Lakehouse Ready'. Meaning, you can query this data in-place straight out of the Registry of ",
        "provider": "[Amazon Web Services](https://aws.amazon.com/)",
        "source": "registry.opendata.aws",
        "url": "https://registry.opendata.aws/yt8m/",
        "topics": "科技与开放工具",
        "languages": "",
        "date": "",
        "rights": "https://github.com/aws-samples/data-lake-as-code/blob/roda-ml/docs/roda_attributions.txt",
        "access": "metadata_public",
        "state": "metadata",
        "summary_status": "source_metadata",
        "link_status": "source_link",
        "classification_basis": "原目录资源类型"
    },
    "record_url": "https://aiedchair.bnu.edu.cn/resources/?lang=fr&record=AISLI-R-55E951F568F0152E5099"
}
