{
  "fetched_at": "2026-10-19T07:19:13Z",
  "source_url": "https://www.kaggle.com/competitions/2018-ml-final-video-caption/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>Team mergers are not allowed in this competition.</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 2 final submissions for judging.</p>\r\n    <h3>Competition Timeline</h3>\r\n    <p>Start Date: <strong>TBA</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>2/1/2014 12:00 AM UTC</strong></p>\r\n\t<!-- End Base Rules -->\r\n<p>The rules page is a bit special: it will auto-update the text based on the parameters of the competition. The rules you need to add here are any additional rules relating to dataset usage. You may also put grading information here.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<h2>File descriptions</h2>\n<ul>\n<li><strong>training_data.zip</strong> - the training set</li>\n<li><strong>testing_data.zip</strong> - the test set</li>\n<li><strong>training_label.json</strong> - captions of the training set</li>\n<li><strong>testing_options.csv</strong> - options of the testing set</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<h2>Useful Links</h2>\n\n - PPT link: https://goo.gl/fBuw25\n - Raw Dataset: https://www.microsoft.com/en-us/download/details.aspx?id=52422 \n - Vgg16 feature extraction network: https://goo.gl/oUPeQ7 \n\n<h2>Additional Resources</h2>\n - Attention Layer:  https://goo.gl/BcnnLB ,  https://goo.gl/smkpku \n - Scheduled Sampling:  https://goo.gl/UFM4gv ,  https://goo.gl/QPa8w9 \n - Word Embeddings:  https://goo.gl/4Ur7oH ,  https://goo.gl/7rfcCn ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation pages describes how submissions will be scored and how students should format their submissions. You don't need a sub-title at the top (the page title appears above). For an example of a high quality evaluation page, see the 2013 KDD Cup page, which we have copied here:</p>\r\n<hr />\r\n<p>The evaluation metric for this competition is <a href=\"https://www.kaggle.com/wiki/MeanFScore\"> Mean F1-Score</a>. The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision p and recall r. Precision is the ratio of true positives (tp) to all predicted positives (tp + fp). Recall is the ratio of true positives to all actual positives (tp + fn). The F1 score is given by:</p>\r\n<p>\\[ F1 = 2\\frac{p \\cdot r}{p+r}\\ \\ \\mathrm{where}\\ \\ p = \\frac{tp}{tp+fp},\\ \\ r = \\frac{tp}{tp+fn} \\]</p>\r\n<p>The F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.</p>\r\n<h2>Submission Format</h2>\r\n<p><strong>For every author in the dataset</strong>, submission files should contain two columns: AuthorId and DuplicateAuthorIds. DuplicateAuthorIds should be a space-delimited list. Every AuthorId counts as his/her own duplicate, and every duplicate should be listed under each of its respective ids. For example, if you suspect author A, B, and C are the same, you should list (A,A B C), (B,B A C), (C,C A B).</p>\r\n<p>The file should contain a header and have the following format:</p>\r\n<pre>AuthorId,DuplicateAuthorIds<br />1,1<br /><span style=\"font-size: 14px; line-height: 1.4em;\">8,8<br />9,9 10<br /></span><span style=\"font-size: 14px; line-height: 1.4em;\">10,10 9<br /></span><span style=\"font-size: 14px; line-height: 1.4em;\">etc.</span></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}