{
  "fetched_at": "2026-10-19T11:13:28Z",
  "source_url": "https://www.kaggle.com/competitions/facial-keypoint-detection/data",
  "pages": [
    {
      "name": "rules",
      "content": "\r\n\t<!-- Begin Base Rules -->\r\n    <h3>One account per participant</h3>\r\n    <p>You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.</p>\r\n    <h3>No private sharing outside teams</h3>\r\n    <p>\r\n        Privately sharing code or data outside of teams is not permitted.\r\n        It's okay to share code if made available to all participants on the forums.\r\n    </p>\r\n    <h3>Team Mergers</h3>\r\n    <p>\r\n        Team mergers are allowed and can be performed by the team leader. In order to merge, the combined team must have a total submission count less than or equal to the maximum allowed as of the merge date. The maximum allowed is the number of submissions per day multiplied by the number of days the competition has been running.<br/>\r\n    </p>\r\n\r\n    <h3>Team Limits</h3>\r\n    <p>There is no maximum team size.</p>\r\n    <h3>Submission Limits</h3>\r\n    <p>You may submit a maximum of 2 entries per day.</p>\r\n    <p>You may select up to 5 final submissions for judging.</p>\r\n    <h3>Competition Timeline</h3>\r\n    <p>Start Date: <strong>3/20/2013 5:11 PM UTC</strong></p>\r\n    <p>Merger Deadline: <strong>None</strong></p>\r\n    <p>Entry Deadline: <strong>None</strong></p>\r\n    <p>End Date: <strong>5/20/2013 12:00 AM UTC</strong></p>\r\n\t<!-- End Base Rules -->\r\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>The objective is to predict keypoint positions on face images.This is useful to track faces in images and video, or as a preprocessing for analysis of expression, for example.</p>\r\n<p>&nbsp;</p>\r\n<p>The input is a 96x96 image and the output is a 30-long vector of predictions for 15 keypoints on the face. Error is measured by the root mean squared error of predictions on non-missing target values. Not all keypoints are available on all examples.</p>\r\n<p>&nbsp;</p>\r\n<p>&nbsp;</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Prizes",
      "content": "<p>Glory and Fame!</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>Predictors are evaluated based on a standard regression task, i.e., root mean square error.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<p>&nbsp;</p>\r\n<p>Each keypoint to be predicted is specified by an (x,y) real-valued pair in the space of pixel indices. There are 15 keypoints, which represent the following elements of the face:</p>\r\n<p>left_eye_center,&nbsp;<span>right_eye_center, left_eye_inner_corner, left_eye_outer_corner, right_eye_inner_corner, right_eye_outer_corner, left_eyebrow_inner_end, left_eyebrow_outer_end, right_eyebrow_inner_end, right_eyebrow_outer_end, nose_tip, mouth_left_corner,\r\n mouth_right_corner, mouth_center_top_lip, mouth_center_bottom_lip</span></p>\r\n<p>Left and right here refers to the point of view of the subject, i.e, our right in the images.</p>\r\n<p>In some examples, some of the target keypoint positions are misssing (encoded as missing entries in the csv, i.e., with nothing betwen two commas).</p>\r\n<p>The input image is given in the last field of the data files, and consists of a list of pixels (ordered by row), as integers in (0,255). The images are 96x96 pixels.</p>\r\n<p><strong>Data files</strong></p>\r\n<ul>\r\n<li><strong>training.csv:</strong>&nbsp;list of training 7049 images. Each row contains the (x,y) coordinates for 15 keypoints, and image data as row-ordered list of pixels.\r\n</li><li><strong>test.csv:</strong>&nbsp;list of 1783 test images. Each row contains ImageId and image data as row-ordered list of pixels\r\n</li><li><strong>submissionFileFormat.csv:</strong>&nbsp;list of 27124 keypoints to predict. Each row contains a RowId, ImageId, FeatureName, Location. FeatureName are &quot;left_eye_center_x,&quot; &quot;right_eyebrow_outer_end_y,&quot; etc. Location is what you need to predict.&nbsp;\r\n</li></ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Submission Instructions",
      "content": "<p>Please download the file submissionFileFormat.csv from the data page. This file lists the points whose locations need to be detected.</p>\r\n<p>Submission File Columns</p>\r\n<ul>\r\n<li><strong>Row Id:</strong>&nbsp;integer id for the row </li><li><strong>Image Id:</strong>&nbsp;integer id for the image. There are 1783 images in the test set.\r\n</li><li><strong>Feature Name:</strong>&nbsp;string identifying the facial keypoint, e.g., left_eye_center_x, left_eye_center_y, mouth_bottom_center_lip_x, nose_tip_y\r\n</li><li><strong>Location:</strong>&nbsp;x- or y-coordinate of the specified feature.&nbsp;<strong>This is the value to be predicted.</strong>\r\n</li></ul>\r\n<div>Note that you will not be detecting all 30 features (x and y coordinates for 15 facial keypoints) for each image. Some images require fewer keypoints to be detected. Please see submissionFileFormat.csv for the details.</div>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}