{
  "id": 406557,
  "title": "Recap of Competition - Congratulations to the Winners!",
  "url": "/competitions/asl-signs/discussion/406557",
  "author_name": "",
  "post_date": "2023-05-02T19:03:57.688700900Z",
  "votes": 6,
  "comment_count": 5,
  "views": 0,
  "content": "<p>Hi Kagglers,</p>\n<p>We’re happy to announce the conclusion of the Google - Isolated Sign Language Recognition competition. Thank you everyone for your participation!</p>\n<p>This competition ended with 10,266 registrations and 1,340 participants on 1,165 teams. We had 20,210 submissions from 85 countries. For 264 users (including 19 in the top 100!), this was their first competition. Thank you all for your hard work in this competition and congratulations to our winners and to those who gained a new ranking!  </p>\n<p>The top potential winning teams will be contacted via email for the next steps. We look forward to learning more about their winning solutions.</p>\n<p>We've cleaned the leaderboard and disqualified some teams that have violated the rules. If you think you were removed by mistake, or believe you have evidence that suggests another team cheated, please contact <a href=\"https://www.kaggle.com/compliance\" target=\"_blank\">compliance</a>. Please fill in all the fields honestly.</p>\n<p>You’re encouraged to post a write-up about your approach and solution in the forums, and link it to your position on the leaderboard through the ‘Your Team’ tab. Details can be found <a href=\"https://www.kaggle.com/product-feedback/373153\" target=\"_blank\">here</a>.</p>\n<p>Thanks for continuing to make Kaggle a great place to learn, practice, and test data science techniques!</p>\n<p>Happy Modeling!<br>\nKaggle Team</p>",
  "messages": [
    {
      "id": "2243262",
      "postDate": "05/02/2023 19:03:57",
      "content": "<p>Hi Kagglers,</p>\n<p>We’re happy to announce the conclusion of the Google - Isolated Sign Language Recognition competition. Thank you everyone for your participation!</p>\n<p>This competition ended with 10,266 registrations and 1,340 participants on 1,165 teams. We had 20,210 submissions from 85 countries. For 264 users (including 19 in the top 100!), this was their first competition. Thank you all for your hard work in this competition and congratulations to our winners and to those who gained a new ranking!  </p>\n<p>The top potential winning teams will be contacted via email for the next steps. We look forward to learning more about their winning solutions.</p>\n<p>We've cleaned the leaderboard and disqualified some teams that have violated the rules. If you think you were removed by mistake, or believe you have evidence that suggests another team cheated, please contact <a href=\"https://www.kaggle.com/compliance\" target=\"_blank\">compliance</a>. Please fill in all the fields honestly.</p>\n<p>You’re encouraged to post a write-up about your approach and solution in the forums, and link it to your position on the leaderboard through the ‘Your Team’ tab. Details can be found <a href=\"https://www.kaggle.com/product-feedback/373153\" target=\"_blank\">here</a>.</p>\n<p>Thanks for continuing to make Kaggle a great place to learn, practice, and test data science techniques!</p>\n<p>Happy Modeling!<br>\nKaggle Team</p>",
      "rawMarkdown": "Hi Kagglers,\n\nWe’re happy to announce the conclusion of the Google - Isolated Sign Language Recognition competition. Thank you everyone for your participation!\n\nThis competition ended with 10,266 registrations and 1,340 participants on 1,165 teams. We had 20,210 submissions from 85 countries. For 264 users (including 19 in the top 100!), this was their first competition. Thank you all for your hard work in this competition and congratulations to our winners and to those who gained a new ranking!  \n\nThe top potential winning teams will be contacted via email for the next steps. We look forward to learning more about their winning solutions.\n\nWe've cleaned the leaderboard and disqualified some teams that have violated the rules. If you think you were removed by mistake, or believe you have evidence that suggests another team cheated, please contact [compliance](https://www.kaggle.com/compliance). Please fill in all the fields honestly.\n\nYou’re encouraged to post a write-up about your approach and solution in the forums, and link it to your position on the leaderboard through the ‘Your Team’ tab. Details can be found [here](https://www.kaggle.com/product-feedback/373153).\n\nThanks for continuing to make Kaggle a great place to learn, practice, and test data science techniques!\n\nHappy Modeling!\nKaggle Team",
      "votes": null
    },
    {
      "id": "2243306",
      "postDate": "05/02/2023 19:48:51",
      "content": "<p>Thanks for providing a high quality dataset, interesting modeling task, and fun competition!</p>",
      "rawMarkdown": "Thanks for providing a high quality dataset, interesting modeling task, and fun competition!",
      "votes": null
    },
    {
      "id": "2243310",
      "postDate": "05/02/2023 19:57:28",
      "content": "<p>Thanks for this competition. It's a great pleasure to participate in one with stable metric and very good correlated datasets.<br>\nIt was a very interesting point to limit the inference time and model size, although it cost our nerves 😅</p>",
      "rawMarkdown": "Thanks for this competition. It's a great pleasure to participate in one with stable metric and very good correlated datasets.\nIt was a very interesting point to limit the inference time and model size, although it cost our nerves 😅",
      "votes": null
    },
    {
      "id": "2243825",
      "postDate": "05/03/2023 07:40:33",
      "content": "<p>Thanks for organizing this competition (I'm one of those 19 😃). As a researcher in the Sign Language Recognition field, it was interesting to work with a large dataset and a real-life use-case.</p>",
      "rawMarkdown": "Thanks for organizing this competition (I'm one of those 19 😃). As a researcher in the Sign Language Recognition field, it was interesting to work with a large dataset and a real-life use-case.",
      "votes": null
    },
    {
      "id": "2246513",
      "postDate": "05/05/2023 07:53:21",
      "content": "<p>Dear organizers,</p>\n<p>Thanks a lot for this very interesting competition.<br>\nAs an active researcher in Sign Language Recognition/Translation, I especially value the dataset that has been created and released for the community here.</p>\n<p>For research purposes, we are currently evaluating some models that weren't submitted before. However, we have the impression that model types that passed scoring before are now failing. Has something changed to the settings? Maybe the scoring resources have been tuned down, making runtimes longer? It would be good to communicate on this. Also, as researchers, we are mainly interested in achievable model results, so dropping the timeout would be very useful.</p>\n<p>As an alternative, and in order to make the data even more valuable for future research, we were wondering whether the test set will be released for research purposes in the future?</p>\n<p>Kindly,</p>\n<p>Joni Dambre</p>",
      "rawMarkdown": "Dear organizers,\n\nThanks a lot for this very interesting competition.\nAs an active researcher in Sign Language Recognition/Translation, I especially value the dataset that has been created and released for the community here.\n\nFor research purposes, we are currently evaluating some models that weren't submitted before. However, we have the impression that model types that passed scoring before are now failing. Has something changed to the settings? Maybe the scoring resources have been tuned down, making runtimes longer? It would be good to communicate on this. Also, as researchers, we are mainly interested in achievable model results, so dropping the timeout would be very useful.\n\nAs an alternative, and in order to make the data even more valuable for future research, we were wondering whether the test set will be released for research purposes in the future?\n\nKindly,\n\nJoni Dambre",
      "votes": null
    },
    {
      "id": "2247183",
      "postDate": "05/05/2023 19:32:01",
      "content": "<p>We haven't updated the metric or evaluation in about two months.</p>\n<p>I don't have any news at the moment on if or when the test set might be released.</p>",
      "rawMarkdown": "We haven't updated the metric or evaluation in about two months.\n\nI don't have any news at the moment on if or when the test set might be released.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2243306,
      "author_name": "cdeotte",
      "author_url": "",
      "post_date": "05/02/2023 19:48:51",
      "content": "<p>Thanks for providing a high quality dataset, interesting modeling task, and fun competition!</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 2243310,
      "author_name": "kolyaforrat",
      "author_url": "",
      "post_date": "05/02/2023 19:57:28",
      "content": "<p>Thanks for this competition. It's a great pleasure to participate in one with stable metric and very good correlated datasets.<br>\nIt was a very interesting point to limit the inference time and model size, although it cost our nerves 😅</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 2243825,
      "author_name": "mdecoster",
      "author_url": "",
      "post_date": "05/03/2023 07:40:33",
      "content": "<p>Thanks for organizing this competition (I'm one of those 19 😃). As a researcher in the Sign Language Recognition field, it was interesting to work with a large dataset and a real-life use-case.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 2246513,
      "author_name": "wonderingalice",
      "author_url": "",
      "post_date": "05/05/2023 07:53:21",
      "content": "<p>Dear organizers,</p>\n<p>Thanks a lot for this very interesting competition.<br>\nAs an active researcher in Sign Language Recognition/Translation, I especially value the dataset that has been created and released for the community here.</p>\n<p>For research purposes, we are currently evaluating some models that weren't submitted before. However, we have the impression that model types that passed scoring before are now failing. Has something changed to the settings? Maybe the scoring resources have been tuned down, making runtimes longer? It would be good to communicate on this. Also, as researchers, we are mainly interested in achievable model results, so dropping the timeout would be very useful.</p>\n<p>As an alternative, and in order to make the data even more valuable for future research, we were wondering whether the test set will be released for research purposes in the future?</p>\n<p>Kindly,</p>\n<p>Joni Dambre</p>",
      "votes": null,
      "replies": [
        {
          "id": 2247183,
          "author_name": "sohier",
          "author_url": "",
          "post_date": "05/05/2023 19:32:01",
          "content": "<p>We haven't updated the metric or evaluation in about two months.</p>\n<p>I don't have any news at the moment on if or when the test set might be released.</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "2243262": "Hi Kagglers,\n\nWe’re happy to announce the conclusion of the Google - Isolated Sign Language Recognition competition. Thank you everyone for your participation!\n\nThis competition ended with 10,266 registrations and 1,340 participants on 1,165 teams. We had 20,210 submissions from 85 countries. For 264 users (including 19 in the top 100!), this was their first competition. Thank you all for your hard work in this competition and congratulations to our winners and to those who gained a new ranking!  \n\nThe top potential winning teams will be contacted via email for the next steps. We look forward to learning more about their winning solutions.\n\nWe've cleaned the leaderboard and disqualified some teams that have violated the rules. If you think you were removed by mistake, or believe you have evidence that suggests another team cheated, please contact [compliance](https://www.kaggle.com/compliance). Please fill in all the fields honestly.\n\nYou’re encouraged to post a write-up about your approach and solution in the forums, and link it to your position on the leaderboard through the ‘Your Team’ tab. Details can be found [here](https://www.kaggle.com/product-feedback/373153).\n\nThanks for continuing to make Kaggle a great place to learn, practice, and test data science techniques!\n\nHappy Modeling!\nKaggle Team",
    "2243306": "Thanks for providing a high quality dataset, interesting modeling task, and fun competition!",
    "2243310": "Thanks for this competition. It's a great pleasure to participate in one with stable metric and very good correlated datasets.\nIt was a very interesting point to limit the inference time and model size, although it cost our nerves 😅",
    "2243825": "Thanks for organizing this competition (I'm one of those 19 😃). As a researcher in the Sign Language Recognition field, it was interesting to work with a large dataset and a real-life use-case.",
    "2246513": "Dear organizers,\n\nThanks a lot for this very interesting competition.\nAs an active researcher in Sign Language Recognition/Translation, I especially value the dataset that has been created and released for the community here.\n\nFor research purposes, we are currently evaluating some models that weren't submitted before. However, we have the impression that model types that passed scoring before are now failing. Has something changed to the settings? Maybe the scoring resources have been tuned down, making runtimes longer? It would be good to communicate on this. Also, as researchers, we are mainly interested in achievable model results, so dropping the timeout would be very useful.\n\nAs an alternative, and in order to make the data even more valuable for future research, we were wondering whether the test set will be released for research purposes in the future?\n\nKindly,\n\nJoni Dambre",
    "2247183": "We haven't updated the metric or evaluation in about two months.\n\nI don't have any news at the moment on if or when the test set might be released."
  },
  "source": "meta"
}