{
  "fetched_at": "2026-10-22T09:25:49Z",
  "source_url": "https://www.kaggle.com/competitions/computervisioncompetitionsc2020/data",
  "pages": [
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<h1> Dataset description </h1>\n<p>\nUCF is an action recognition data set of realistic action videos, collected from YouTube. The dataset contains 5 categories (Basketball, Diving, Jumping, Tennis, and Walking). The training set contains 5 folders, around 100 video for each vategory. The testing set contains 126 vidoos. The goal is to build a model than can recognize the cateogry of each video in the testing set.\n<h2>Files description</h2>\n<ul>\n<li> train.rar</strong> - https://drive.google.com/file/d/1fu93ErsAOzDf9kK2ws4I2ILcMYr2SZbF/view?usp=sharing</li>\n<li><strong>test.rar</strong> - https://drive.google.com/file/d/1tfcRgZrMp8cVJeH-YY2YO0RJEe9dKMVy/view?usp=sharing</li>\n<li><strong>submit.csv</strong> - a sample submission file in the correct format</li>\n<li><strong>names.csv</strong> this file contains the IDs of the five categories</li>\n</ul>\n<h2>Data fields</h2>\n<ul>\n<li><strong>Video</strong> - the name of video </li>\n<li><strong>Label</strong> - the predicted label</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<h1> Introduction </h1>\nWelcome to the competition. This competition is for SC Students in Computer Vision course at FCIS. The goal of the competition is to build deep learning models that can recognize the action of the video.\n<p>\nAction recognition task involves the identification of different actions from video clips (a\nsequence of 2D frames) where the action may or may not be performed throughout the\nentire duration of the video. This seems like a natural extension of image classification\ntasks to multiple frames and then aggregating the predictions from each frame.\n</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>You have to submit a file in CSV format named as 'submit.csv'.</p>\n<hr>\n<p>The evaluation metric for this competition is the overall accuracy </p><p> \n\n</p><h2>Submission Format</h2>\n<p><strong> The file contains 2 column, the first column is Video, which is the name of the test video. The second column is label, which is your predicted label for the video </strong> </p>\n<p>The file should contain a header and have the following format:</p>\n<pre>video,label<br>test_image (1).mpg,1<br></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}