{
  "id": 403709,
  "title": "Data Video Resolution",
  "url": "/competitions/asl-signs/discussion/403709",
  "author_name": "",
  "post_date": "2023-04-24T13:15:21.272252800Z",
  "votes": 1,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Hello,</p>\n<p>The data provided is the coordinates. Is all the data captured from videos of the same resolution across both training and test data? Is that 1920x1080 or something else?</p>\n<p>Thanks! </p>",
  "messages": [
    {
      "id": "2232568",
      "postDate": "04/24/2023 13:15:21",
      "content": "<p>Hello,</p>\n<p>The data provided is the coordinates. Is all the data captured from videos of the same resolution across both training and test data? Is that 1920x1080 or something else?</p>\n<p>Thanks! </p>",
      "rawMarkdown": "Hello,\n\nThe data provided is the coordinates. Is all the data captured from videos of the same resolution across both training and test data? Is that 1920x1080 or something else?\n\nThanks!",
      "votes": null
    },
    {
      "id": "2232739",
      "postDate": "04/24/2023 15:16:00",
      "content": "<p>The Data Card says: \"Signers who communicate using American Sign Language as their primary language were recruited from across the United States. They were shipped a Pixel 4a smartphone with an installed collection app.\" I would assume that all videos had the same resolution because of this, but it is not clear what the resolution was. In any case, the coordinates returned by MediaPipe are normalized by image width and height to the range [0,1] (out of frame keypoints will have values outside this range).</p>",
      "rawMarkdown": "The Data Card says: \"Signers who communicate using American Sign Language as their primary language were recruited from across the United States. They were shipped a Pixel 4a smartphone with an installed collection app.\" I would assume that all videos had the same resolution because of this, but it is not clear what the resolution was. In any case, the coordinates returned by MediaPipe are normalized by image width and height to the range [0,1] (out of frame keypoints will have values outside this range).",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2232739,
      "author_name": "mdecoster",
      "author_url": "",
      "post_date": "04/24/2023 15:16:00",
      "content": "<p>The Data Card says: \"Signers who communicate using American Sign Language as their primary language were recruited from across the United States. They were shipped a Pixel 4a smartphone with an installed collection app.\" I would assume that all videos had the same resolution because of this, but it is not clear what the resolution was. In any case, the coordinates returned by MediaPipe are normalized by image width and height to the range [0,1] (out of frame keypoints will have values outside this range).</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "2232568": "Hello,\n\nThe data provided is the coordinates. Is all the data captured from videos of the same resolution across both training and test data? Is that 1920x1080 or something else?\n\nThanks!",
    "2232739": "The Data Card says: \"Signers who communicate using American Sign Language as their primary language were recruited from across the United States. They were shipped a Pixel 4a smartphone with an installed collection app.\" I would assume that all videos had the same resolution because of this, but it is not clear what the resolution was. In any case, the coordinates returned by MediaPipe are normalized by image width and height to the range [0,1] (out of frame keypoints will have values outside this range)."
  },
  "source": "meta"
}