{
  "id": 5088,
  "title": "Does the final evaluation data include frame separations? ",
  "url": "/competitions/multi-modal-gesture-recognition/discussion/5088",
  "author_name": "",
  "post_date": "2013-07-13T14:33:32.727Z",
  "votes": null,
  "comment_count": 4,
  "views": 1231,
  "content": "<p>I'm a bit unclear on this point. &nbsp;Do we have to take a given set of frames known to contain a single gesture, and then label it.. or do we have to take a video known to contain 20 gestures, and then figure out where the individual gestures are, and then\r\n label those?</p>",
  "messages": [
    {
      "id": "27132",
      "postDate": "07/13/2013 14:33:32",
      "content": "<p>I'm a bit unclear on this point. &nbsp;Do we have to take a given set of frames known to contain a single gesture, and then label it.. or do we have to take a video known to contain 20 gestures, and then figure out where the individual gestures are, and then\r\n label those?</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "27173",
      "postDate": "07/14/2013 06:05:12",
      "content": "<p>Ok, looks like it's the latter. &nbsp;Hmm, that complicates things..</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "27174",
      "postDate": "07/14/2013 06:05:14",
      "content": "<p>Edit: &nbsp;oops double post.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "27180",
      "postDate": "07/14/2013 12:39:11",
      "content": "<p>Dear Brian,</p>\r\n<p></p>\r\n<p>The test dataset will be composed by sequences of one minute, which will be contained 10 gestures from the vocabulary (without replications). People who perform the gestures are the same as training and evaluation dataset. It is not necessary to segment\r\n the gesture in frames, only label 10 gestures in each sequence. Feel free to ask any question.&nbsp;</p>\r\n<p>Greetings,</p>\r\n<p></p>\r\n<p>Miguel Reyes Estany</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "27410",
      "postDate": "07/18/2013 14:16:29",
      "content": "<p>Hi Miguel,</p>\r\n<p>&nbsp;&nbsp;&nbsp;You mentioned &quot;The test dataset will be composed by sequences of one minute, which will be contained 10 gestures from the vocabulary (without replications).&quot;&nbsp;Does that mean for testing dataset, the label number is fixed at 10 unique numbers (out of 20).\r\n That's quite different from validation dataset ( I assume there will be more than 10 gestures in one sequence and there might be several same gestures in a video sequence). Can you give us some further instructions concerning with the validation dataset since\r\n validation set and test set have different structure and it will cause the design of our system to be quite different for validation set and testing set.</p>\r\n<p>Thank you</p>",
      "rawMarkdown": "",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 27173,
      "author_name": "brianfeldstein",
      "author_url": "",
      "post_date": "07/14/2013 06:05:12",
      "content": "<p>Ok, looks like it's the latter. &nbsp;Hmm, that complicates things..</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 27174,
      "author_name": "brianfeldstein",
      "author_url": "",
      "post_date": "07/14/2013 06:05:14",
      "content": "<p>Edit: &nbsp;oops double post.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 27180,
      "author_name": "miguelreyesestany",
      "author_url": "",
      "post_date": "07/14/2013 12:39:11",
      "content": "<p>Dear Brian,</p>\r\n<p></p>\r\n<p>The test dataset will be composed by sequences of one minute, which will be contained 10 gestures from the vocabulary (without replications). People who perform the gestures are the same as training and evaluation dataset. It is not necessary to segment\r\n the gesture in frames, only label 10 gestures in each sequence. Feel free to ask any question.&nbsp;</p>\r\n<p>Greetings,</p>\r\n<p></p>\r\n<p>Miguel Reyes Estany</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 27410,
      "author_name": "stevenwudi",
      "author_url": "",
      "post_date": "07/18/2013 14:16:29",
      "content": "<p>Hi Miguel,</p>\r\n<p>&nbsp;&nbsp;&nbsp;You mentioned &quot;The test dataset will be composed by sequences of one minute, which will be contained 10 gestures from the vocabulary (without replications).&quot;&nbsp;Does that mean for testing dataset, the label number is fixed at 10 unique numbers (out of 20).\r\n That's quite different from validation dataset ( I assume there will be more than 10 gestures in one sequence and there might be several same gestures in a video sequence). Can you give us some further instructions concerning with the validation dataset since\r\n validation set and test set have different structure and it will cause the design of our system to be quite different for validation set and testing set.</p>\r\n<p>Thank you</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "27132": "",
    "27173": "",
    "27174": "",
    "27180": "",
    "27410": ""
  },
  "source": "meta"
}