{
  "id": 243114,
  "title": "On continuing research in this area",
  "url": "/competitions/bms-molecular-translation/discussion/243114",
  "author_name": "",
  "post_date": "2021-06-01T07:46:32.527710500Z",
  "votes": 6,
  "comment_count": 5,
  "views": 0,
  "content": "<p>The competition is almost over but the topic is still interesting to me. Due to lack of resources (both computational and engineering) I couldn't deliver the result that I was aiming to.</p>\n<p>In such time-limited contests, all the approaches that deliver the highest results are good (usage of the existing methods, by involving more computational resources and so on). I'm thinking on building a model (without using existing pre-trained CNNs) that better \"understands\" the chemical formula and deliver decent results.</p>\n<p>If you want to be a part of this research and ready to deliver research paper(s) in reputable journals, please respond.</p>\n<p>Regards,<br>\nJH</p>",
  "messages": [
    {
      "id": "1330977",
      "postDate": "06/01/2021 07:46:32",
      "content": "<p>The competition is almost over but the topic is still interesting to me. Due to lack of resources (both computational and engineering) I couldn't deliver the result that I was aiming to.</p>\n<p>In such time-limited contests, all the approaches that deliver the highest results are good (usage of the existing methods, by involving more computational resources and so on). I'm thinking on building a model (without using existing pre-trained CNNs) that better \"understands\" the chemical formula and deliver decent results.</p>\n<p>If you want to be a part of this research and ready to deliver research paper(s) in reputable journals, please respond.</p>\n<p>Regards,<br>\nJH</p>",
      "rawMarkdown": "The competition is almost over but the topic is still interesting to me. Due to lack of resources (both computational and engineering) I couldn't deliver the result that I was aiming to.\n\nIn such time-limited contests, all the approaches that deliver the highest results are good (usage of the existing methods, by involving more computational resources and so on). I'm thinking on building a model (without using existing pre-trained CNNs) that better \"understands\" the chemical formula and deliver decent results.\n\nIf you want to be a part of this research and ready to deliver research paper(s) in reputable journals, please respond.\n\nRegards,\nJH",
      "votes": null
    },
    {
      "id": "1333449",
      "postDate": "06/02/2021 18:13:42",
      "content": "<p>This paper might be of interest for an alternative to transfer learning CNN: <a href=\"https://arxiv.org/pdf/2101.11986.pdf\" target=\"_blank\">https://arxiv.org/pdf/2101.11986.pdf</a>.</p>",
      "rawMarkdown": "This paper might be of interest for an alternative to transfer learning CNN: https://arxiv.org/pdf/2101.11986.pdf.",
      "votes": null
    },
    {
      "id": "1333820",
      "postDate": "06/03/2021 04:45:23",
      "content": "<p>Thanks for the paper! To be honest, in the beginning I wasn't sure if transformer is a good match for this problem… Now I will give a try when there is enough time)</p>",
      "rawMarkdown": "Thanks for the paper! To be honest, in the beginning I wasn't sure if transformer is a good match for this problem... Now I will give a try when there is enough time)",
      "votes": null
    },
    {
      "id": "1355697",
      "postDate": "06/18/2021 13:49:22",
      "content": "<p>Hi Jamal, I was curious if have you had good progress towards your research?</p>",
      "rawMarkdown": "Hi Jamal, I was curious if have you had good progress towards your research?",
      "votes": null
    },
    {
      "id": "1355850",
      "postDate": "06/18/2021 15:11:49",
      "content": "<p>Hi Mo. Not yet - working on some experiments with autoencoders, which should be a part of that project.</p>",
      "rawMarkdown": "Hi Mo. Not yet - working on some experiments with autoencoders, which should be a part of that project.",
      "votes": null
    },
    {
      "id": "2019088",
      "postDate": "11/06/2022 10:38:44",
      "content": "<p><a href=\"https://link.springer.com/article/10.1186/s13321-022-00642-3\" target=\"_blank\">Review of techniques and models used in optical chemical structure recognition in images and scanned documents</a></p>",
      "rawMarkdown": "[Review of techniques and models used in optical chemical structure recognition in images and scanned documents](https://link.springer.com/article/10.1186/s13321-022-00642-3)",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1333449,
      "author_name": "mvenou",
      "author_url": "",
      "post_date": "06/02/2021 18:13:42",
      "content": "<p>This paper might be of interest for an alternative to transfer learning CNN: <a href=\"https://arxiv.org/pdf/2101.11986.pdf\" target=\"_blank\">https://arxiv.org/pdf/2101.11986.pdf</a>.</p>",
      "votes": null,
      "replies": [
        {
          "id": 1333820,
          "author_name": "jhasanov",
          "author_url": "",
          "post_date": "06/03/2021 04:45:23",
          "content": "<p>Thanks for the paper! To be honest, in the beginning I wasn't sure if transformer is a good match for this problem… Now I will give a try when there is enough time)</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 1355697,
          "author_name": "mvenou",
          "author_url": "",
          "post_date": "06/18/2021 13:49:22",
          "content": "<p>Hi Jamal, I was curious if have you had good progress towards your research?</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 1355850,
          "author_name": "jhasanov",
          "author_url": "",
          "post_date": "06/18/2021 15:11:49",
          "content": "<p>Hi Mo. Not yet - working on some experiments with autoencoders, which should be a part of that project.</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 2019088,
      "author_name": "jhasanov",
      "author_url": "",
      "post_date": "11/06/2022 10:38:44",
      "content": "<p><a href=\"https://link.springer.com/article/10.1186/s13321-022-00642-3\" target=\"_blank\">Review of techniques and models used in optical chemical structure recognition in images and scanned documents</a></p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1330977": "The competition is almost over but the topic is still interesting to me. Due to lack of resources (both computational and engineering) I couldn't deliver the result that I was aiming to.\n\nIn such time-limited contests, all the approaches that deliver the highest results are good (usage of the existing methods, by involving more computational resources and so on). I'm thinking on building a model (without using existing pre-trained CNNs) that better \"understands\" the chemical formula and deliver decent results.\n\nIf you want to be a part of this research and ready to deliver research paper(s) in reputable journals, please respond.\n\nRegards,\nJH",
    "1333449": "This paper might be of interest for an alternative to transfer learning CNN: https://arxiv.org/pdf/2101.11986.pdf.",
    "1333820": "Thanks for the paper! To be honest, in the beginning I wasn't sure if transformer is a good match for this problem... Now I will give a try when there is enough time)",
    "1355697": "Hi Jamal, I was curious if have you had good progress towards your research?",
    "1355850": "Hi Mo. Not yet - working on some experiments with autoencoders, which should be a part of that project.",
    "2019088": "[Review of techniques and models used in optical chemical structure recognition in images and scanned documents](https://link.springer.com/article/10.1186/s13321-022-00642-3)"
  },
  "source": "meta"
}