{
  "fetched_at": "2026-10-19T07:16:26Z",
  "source_url": "https://www.kaggle.com/competitions/ai2022-competition/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## About Files:\nFor this competition, we are providing you with:\n\n*  **train.csv** - The training set. This file has two columns with image ID and yoga pose label (a categorical tuple value separated by '_').\n*  **test.csv** - The test set. This file has just one column with image IDs. \n*  **sample_submission.csv** - A sample submission file in the correct format.\n*  **ReadMe.pdf** - Comprehensive details about the dataset.\n\nThe dataset (train and test image JPEG files) has been provided for your convenience also by means of the below GitHub link:\n\n[https://github.com/stefanomarrone/yogaposes-aii22-challenge](https://github.com/stefanomarrone/yogaposes-aii22-challenge)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "## About The Problem and the Competition\nHuman pose classification is one of the challenging computer vision problems which has potential applications in various fields such as visual surveillance, behavioral analysis, assisted living, and intelligent driver assistance system [1, 2]. \n\nTo handle more variety in human poses, we are using a fine-grained hierarchical pose classification dataset named Yoga-82 for this competition proposed by [1, 2]. This dataset formulates the pose estimation as a classification task. The Yoga-82 database has samples belonging to 82 different classes (yoga poses). The dataset provides hierarchical labels for yoga poses based on the body configuration of the pose. The dataset contains a three-level hierarchy including body positions, variations in body positions, and the actual pose names. There are 6, 20, and 82 classes in the first, second, and third levels, respectively.\n\nMore details about the competition and dataset is provided in the **ReadMe.pdf** file.\n\n## Important Dates:\n*  **Submission deadline** : 1st May 2022 (No extension).\n*  **Winners Announcement**: 2nd May 2022.\n*  **AII2022 in Reggio Calabria, Italy** : 1st – 3rd September 2022\n\n## Prize: The top three winners of the competition will have the below benefits:\n* Free registration to the conference. \n* 14 days extra to submit their paper.\n* A certificate with the indication of the position in the ranking list (1st, 2nd, 3rd)\n\n**Reference:**\n1) Verma, Manisha, Sudhakar Kumawat, Yuta Nakashima, and Shanmuganathan Raman. \"Yoga-82: a new dataset for fine-grained classification of human poses.\" In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 1038-1039. 2020.\n\n2) The Yoga82 database homepage, [https://sites.google.com/view/yoga-82/home](https://sites.google.com/view/yoga-82/home).",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this competition is [Categorization Accuracy](https://towardsdatascience.com/keras-accuracy-metrics-8572eb479ec7#:~:text=Categorical%20Accuracy%20calculates%20the%20percentage,yTrue%2C%20it%20is%20considered%20accurate.). Categorical Accuracy calculates the percentage of predicted values that match with actual values.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "The winning team will have to push their notebooks that reproduce their score. This is mainly because the conference's main theme is: fostering reproducibility of research results. \n\nThe winning team will have an option to publish a paper that succinctly presents the solution to the given problem. ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "AII2022",
      "content": "## About the AII2022 Conference:\n\nThis competition is held as part of the 2nd International Conference on Applied Intelligence and Informatics – AII2022 ([www.aii2022.org](www.aii2022.org)).  The conference provides a premier international forum to bring together researchers and practitioners from diverse domains for the sharing of cutting-edge research results obtained through the application of intelligence and/or informatics to solve problems that otherwise would not have been possible to solve. AII2022 also fosters the exchange and dissemination of innovative and practical development of methodologies and technologies with real-life applications. AII2022 asks all authors to make their dataset and methodology open access for community usage. This is to: **Foster the Reproducibility of Scientific Results**, hence is the theme of the conference. The conference will be held in Reggio Calabria, a beautiful seaside city located in the southernmost tip of Italy.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}