{
  "id": 308113,
  "title": "Important resource in Face Recognition",
  "url": "/competitions/happy-whale-and-dolphin/discussion/308113",
  "author_name": "",
  "post_date": "2022-02-17T06:41:18.228497500Z",
  "votes": 18,
  "comment_count": 2,
  "views": 0,
  "content": "<p>There are lots of topics and code with ArcFace, <br>\nSo I find some past year famous research in Face Recognition field.</p>\n<p><strong>RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition</strong><br>\n<strong>Year: 2021</strong><br>\nPaper: <a href=\"https://arxiv.org/pdf/2105.01883v2.pdf\" target=\"_blank\">https://arxiv.org/pdf/2105.01883v2.pdf</a><br>\nCode: <a href=\"https://github.com/DingXiaoH/RepMLP\" target=\"_blank\">https://github.com/DingXiaoH/RepMLP</a></p>\n<p><strong>ArcFace: Additive Angular Margin Loss for Deep Face Recognition</strong><br>\n<strong>Year: 2019</strong><br>\nPaper: <a href=\"https://arxiv.org/pdf/1801.07698v3.pdf\" target=\"_blank\">https://arxiv.org/pdf/1801.07698v3.pdf</a><br>\nCode: <a href=\"https://github.com/deepinsight/insightface\" target=\"_blank\">https://github.com/deepinsight/insightface</a></p>\n<p><strong>VGGFace2: A dataset for recognising faces across pose and age</strong><br>\n<strong>Year: 2017</strong><br>\nPaper: <a href=\"https://arxiv.org/pdf/1710.08092v2.pdf\" target=\"_blank\">https://arxiv.org/pdf/1710.08092v2.pdf</a><br>\nCode: <a href=\"https://github.com/deepinsight/insightface\" target=\"_blank\">https://github.com/deepinsight/insightface</a></p>\n<p><strong>SphereFace: Deep Hypersphere Embedding for Face Recognition</strong><br>\n<strong>Year: 2017</strong><br>\nPaper: <a href=\"https://arxiv.org/pdf/1704.08063v4.pdf\" target=\"_blank\">https://arxiv.org/pdf/1704.08063v4.pdf</a><br>\nCode: <a href=\"https://github.com/wy1iu/sphereface\" target=\"_blank\">https://github.com/wy1iu/sphereface</a></p>\n<p><strong>FaceNet: A Unified Embedding for Face Recognition and Clustering</strong><br>\n<strong>Year: 2015</strong><br>\nPaper: <a href=\"https://arxiv.org/pdf/1503.03832v3.pdf\" target=\"_blank\">https://arxiv.org/pdf/1503.03832v3.pdf</a><br>\nCode: <a href=\"https://github.com/timesler/facenet-pytorch\" target=\"_blank\">https://github.com/timesler/facenet-pytorch</a></p>\n<blockquote>\n  <p><strong>DeepInsight</strong> is a good lib for achieve the problem<br>\n  <strong>Core Featured Baseline Model</strong> could still be ArcFace</p>\n</blockquote>",
  "messages": [
    {
      "id": "1694105",
      "postDate": "02/17/2022 06:41:18",
      "content": "<p>There are lots of topics and code with ArcFace, <br>\nSo I find some past year famous research in Face Recognition field.</p>\n<p><strong>RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition</strong><br>\n<strong>Year: 2021</strong><br>\nPaper: <a href=\"https://arxiv.org/pdf/2105.01883v2.pdf\" target=\"_blank\">https://arxiv.org/pdf/2105.01883v2.pdf</a><br>\nCode: <a href=\"https://github.com/DingXiaoH/RepMLP\" target=\"_blank\">https://github.com/DingXiaoH/RepMLP</a></p>\n<p><strong>ArcFace: Additive Angular Margin Loss for Deep Face Recognition</strong><br>\n<strong>Year: 2019</strong><br>\nPaper: <a href=\"https://arxiv.org/pdf/1801.07698v3.pdf\" target=\"_blank\">https://arxiv.org/pdf/1801.07698v3.pdf</a><br>\nCode: <a href=\"https://github.com/deepinsight/insightface\" target=\"_blank\">https://github.com/deepinsight/insightface</a></p>\n<p><strong>VGGFace2: A dataset for recognising faces across pose and age</strong><br>\n<strong>Year: 2017</strong><br>\nPaper: <a href=\"https://arxiv.org/pdf/1710.08092v2.pdf\" target=\"_blank\">https://arxiv.org/pdf/1710.08092v2.pdf</a><br>\nCode: <a href=\"https://github.com/deepinsight/insightface\" target=\"_blank\">https://github.com/deepinsight/insightface</a></p>\n<p><strong>SphereFace: Deep Hypersphere Embedding for Face Recognition</strong><br>\n<strong>Year: 2017</strong><br>\nPaper: <a href=\"https://arxiv.org/pdf/1704.08063v4.pdf\" target=\"_blank\">https://arxiv.org/pdf/1704.08063v4.pdf</a><br>\nCode: <a href=\"https://github.com/wy1iu/sphereface\" target=\"_blank\">https://github.com/wy1iu/sphereface</a></p>\n<p><strong>FaceNet: A Unified Embedding for Face Recognition and Clustering</strong><br>\n<strong>Year: 2015</strong><br>\nPaper: <a href=\"https://arxiv.org/pdf/1503.03832v3.pdf\" target=\"_blank\">https://arxiv.org/pdf/1503.03832v3.pdf</a><br>\nCode: <a href=\"https://github.com/timesler/facenet-pytorch\" target=\"_blank\">https://github.com/timesler/facenet-pytorch</a></p>\n<blockquote>\n  <p><strong>DeepInsight</strong> is a good lib for achieve the problem<br>\n  <strong>Core Featured Baseline Model</strong> could still be ArcFace</p>\n</blockquote>",
      "rawMarkdown": "There are lots of topics and code with ArcFace, \nSo I find some past year famous research in Face Recognition field.\n\n**RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition**\n**Year: 2021**\nPaper: https://arxiv.org/pdf/2105.01883v2.pdf\nCode: https://github.com/DingXiaoH/RepMLP\n\n**ArcFace: Additive Angular Margin Loss for Deep Face Recognition**\n**Year: 2019**\nPaper: https://arxiv.org/pdf/1801.07698v3.pdf\nCode: https://github.com/deepinsight/insightface\n\n**VGGFace2: A dataset for recognising faces across pose and age**\n**Year: 2017**\nPaper: https://arxiv.org/pdf/1710.08092v2.pdf\nCode: https://github.com/deepinsight/insightface\n\n**SphereFace: Deep Hypersphere Embedding for Face Recognition**\n**Year: 2017**\nPaper: https://arxiv.org/pdf/1704.08063v4.pdf\nCode: https://github.com/wy1iu/sphereface\n\n**FaceNet: A Unified Embedding for Face Recognition and Clustering**\n**Year: 2015**\nPaper: https://arxiv.org/pdf/1503.03832v3.pdf\nCode: https://github.com/timesler/facenet-pytorch\n\n> **DeepInsight** is a good lib for achieve the problem\n**Core Featured Baseline Model** could still be ArcFace",
      "votes": null
    },
    {
      "id": "1694350",
      "postDate": "02/17/2022 11:06:36",
      "content": "<p>good work ! it is very helpful <br>\ni'm mini project <br>\nthe goal of this project is to make Python script which takes a video as input and returns all texts visible on the video.<br>\nthe videos are titlok videos so texts can appear everywhere on screen, with different background, font size etc..<br>\ncan you give me some source of video can help me <br>\ni try this code but i is weak <br>\n<a href=\"https://www.kaggle.com/ayoubchaoui/code1\" target=\"_blank\">https://www.kaggle.com/ayoubchaoui/code1</a></p>",
      "rawMarkdown": "good work ! it is very helpful \ni'm mini project \nthe goal of this project is to make Python script which takes a video as input and returns all texts visible on the video.\nthe videos are titlok videos so texts can appear everywhere on screen, with different background, font size etc..\ncan you give me some source of video can help me \ni try this code but i is weak \nhttps://www.kaggle.com/ayoubchaoui/code1",
      "votes": null
    },
    {
      "id": "2630051",
      "postDate": "02/01/2024 06:12:10",
      "content": "<p>good work</p>",
      "rawMarkdown": "good work",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1694350,
      "author_name": "ayoubchaoui",
      "author_url": "",
      "post_date": "02/17/2022 11:06:36",
      "content": "<p>good work ! it is very helpful <br>\ni'm mini project <br>\nthe goal of this project is to make Python script which takes a video as input and returns all texts visible on the video.<br>\nthe videos are titlok videos so texts can appear everywhere on screen, with different background, font size etc..<br>\ncan you give me some source of video can help me <br>\ni try this code but i is weak <br>\n<a href=\"https://www.kaggle.com/ayoubchaoui/code1\" target=\"_blank\">https://www.kaggle.com/ayoubchaoui/code1</a></p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 2630051,
      "author_name": "divyachopra140601",
      "author_url": "",
      "post_date": "02/01/2024 06:12:10",
      "content": "<p>good work</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1694105": "There are lots of topics and code with ArcFace, \nSo I find some past year famous research in Face Recognition field.\n\n**RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition**\n**Year: 2021**\nPaper: https://arxiv.org/pdf/2105.01883v2.pdf\nCode: https://github.com/DingXiaoH/RepMLP\n\n**ArcFace: Additive Angular Margin Loss for Deep Face Recognition**\n**Year: 2019**\nPaper: https://arxiv.org/pdf/1801.07698v3.pdf\nCode: https://github.com/deepinsight/insightface\n\n**VGGFace2: A dataset for recognising faces across pose and age**\n**Year: 2017**\nPaper: https://arxiv.org/pdf/1710.08092v2.pdf\nCode: https://github.com/deepinsight/insightface\n\n**SphereFace: Deep Hypersphere Embedding for Face Recognition**\n**Year: 2017**\nPaper: https://arxiv.org/pdf/1704.08063v4.pdf\nCode: https://github.com/wy1iu/sphereface\n\n**FaceNet: A Unified Embedding for Face Recognition and Clustering**\n**Year: 2015**\nPaper: https://arxiv.org/pdf/1503.03832v3.pdf\nCode: https://github.com/timesler/facenet-pytorch\n\n> **DeepInsight** is a good lib for achieve the problem\n**Core Featured Baseline Model** could still be ArcFace",
    "1694350": "good work ! it is very helpful \ni'm mini project \nthe goal of this project is to make Python script which takes a video as input and returns all texts visible on the video.\nthe videos are titlok videos so texts can appear everywhere on screen, with different background, font size etc..\ncan you give me some source of video can help me \ni try this code but i is weak \nhttps://www.kaggle.com/ayoubchaoui/code1",
    "2630051": "good work"
  },
  "source": "meta"
}