{
  "fetched_at": "2026-10-19T08:26:11Z",
  "source_url": "https://www.kaggle.com/competitions/binary-classifier-for-jugglingballs/data",
  "pages": [
    {
      "name": "data-description",
      "content": "For more details regarding the tasks, including the dataset download, please refer to the information provided in [this Google Colab link](https://colab.research.google.com/drive/19IOk0hmokk726V2WRwNsX9TQDlcRECuU?usp=sharing).",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this competition is **F1 score**. ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "**Programming Language:** All code must be implemented in Python. While you are permitted to use the Scikit Learn toolkit, the use of other toolkits or pretrained models, such as NLTK or transformer network architectures, for your project results is not allowed.\n\n**Project Customization:** We do not accept customized projects. You are expected to adhere to the guidelines and structure provided for the project.\n\n**Model Usage:** You are only allowed to use machine learning models discussed or that will be covered in our course. \n\n**References and Academic Integrity:** Note that you should cite all the references you refer to under each question. Proper referencing is essential for academic integrity, giving credit to original authors, avoiding plagiarism, and providing a traceable path for verification. Please check the course syllabus for more details about academic integrity.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "Your objective is to construct action recognition models on a subset of [the UCF101 dataset](https://www.crcv.ucf.edu/data/UCF101.php). The UCF101 dataset consists of a total of 13,320 videos spanning diverse human action categories. However, for the final project, our focus narrows down to a subset of the dataset, comprising 2,355 training videos and 969 test videos distributed among 30 action categories. You will have to build one binary classifier and one multi-class classifier.\n\nIn this competition, your task is to build a classifier for the class *JugglingBalls*. Your goal is to train a model to classify JugglingBalls videos as *positive* and the remaining videos as *negative*. You are free to choose any machine learning models from the class. \n\nFor more details regarding the tasks, including the dataset download, please refer to the information provided in [this Google Colab link](https://colab.research.google.com/drive/19IOk0hmokk726V2WRwNsX9TQDlcRECuU?usp=sharing).\n\nPlease note that **the deadline for project submission is Tuesday, March 5, 11:59 pm**. ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}