{
  "id": 405782,
  "title": "some ideas about this competition",
  "url": "/competitions/asl-signs/discussion/405782",
  "author_name": "",
  "post_date": "2023-04-29T08:39:13.067049100Z",
  "votes": 1,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Recently, I have read some papers on the direction of sign language recognition, and I have two ideas for this competition: 1. Can we use 3D convolution to extract the correlation between different frames. 2. By slicing, shifting, and concatenating the sequence, the attention relationship between the current frame and other frames is obtained, so that the extracted features can include the features of the previous and subsequent frames.</p>",
  "messages": [
    {
      "id": "2239188",
      "postDate": "04/29/2023 08:39:13",
      "content": "<p>Recently, I have read some papers on the direction of sign language recognition, and I have two ideas for this competition: 1. Can we use 3D convolution to extract the correlation between different frames. 2. By slicing, shifting, and concatenating the sequence, the attention relationship between the current frame and other frames is obtained, so that the extracted features can include the features of the previous and subsequent frames.</p>",
      "rawMarkdown": "Recently, I have read some papers on the direction of sign language recognition, and I have two ideas for this competition: 1. Can we use 3D convolution to extract the correlation between different frames. 2. By slicing, shifting, and concatenating the sequence, the attention relationship between the current frame and other frames is obtained, so that the extracted features can include the features of the previous and subsequent frames.",
      "votes": null
    },
    {
      "id": "2239402",
      "postDate": "04/29/2023 13:01:05",
      "content": "<p>thank you </p>",
      "rawMarkdown": "thank you",
      "votes": null
    },
    {
      "id": "2240922",
      "postDate": "05/01/2023 02:17:35",
      "content": "<p>What is the following  means? <br>\n\"Can we use 3D convolution to extract the correlation between different frames.\"</p>",
      "rawMarkdown": "What is the following  means? \n\"Can we use 3D convolution to extract the correlation between different frames.\"",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2239402,
      "author_name": "shahidulugvcse",
      "author_url": "",
      "post_date": "04/29/2023 13:01:05",
      "content": "<p>thank you </p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 2240922,
      "author_name": "jacksonyou",
      "author_url": "",
      "post_date": "05/01/2023 02:17:35",
      "content": "<p>What is the following  means? <br>\n\"Can we use 3D convolution to extract the correlation between different frames.\"</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "2239188": "Recently, I have read some papers on the direction of sign language recognition, and I have two ideas for this competition: 1. Can we use 3D convolution to extract the correlation between different frames. 2. By slicing, shifting, and concatenating the sequence, the attention relationship between the current frame and other frames is obtained, so that the extracted features can include the features of the previous and subsequent frames.",
    "2239402": "thank you",
    "2240922": "What is the following  means? \n\"Can we use 3D convolution to extract the correlation between different frames.\""
  },
  "source": "meta"
}