{
  "id": 183527,
  "title": "Deep Conditional Generative Models (AKA Conditional Variational Auto-encoders)",
  "url": "/competitions/lyft-motion-prediction-autonomous-vehicles/discussion/183527",
  "author_name": "",
  "post_date": "2020-09-17T02:16:02.482214800Z",
  "votes": 5,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Hey all! <br>\nAfter reading some papers with innovative solutions to the trajectory prediction problem, I found several approaches using Deep Conditional Generative Models (AKA Conditional Variational Auto-encoders). This innovation was introduced in 2015, in the paper <strong>Learning Structured Output Representation using Deep Conditional Generative Models</strong>. The code below implements the paper, and can be used as base to apply CVAEs to trajectory prediction:</p>\n<p><a href=\"https://www.kaggle.com/carlossouza/conditional-variational-auto-encoder\" target=\"_blank\">https://www.kaggle.com/carlossouza/conditional-variational-auto-encoder</a></p>\n<p>Cheers!</p>",
  "messages": [
    {
      "id": "1013819",
      "postDate": "09/17/2020 02:16:02",
      "content": "<p>Hey all! <br>\nAfter reading some papers with innovative solutions to the trajectory prediction problem, I found several approaches using Deep Conditional Generative Models (AKA Conditional Variational Auto-encoders). This innovation was introduced in 2015, in the paper <strong>Learning Structured Output Representation using Deep Conditional Generative Models</strong>. The code below implements the paper, and can be used as base to apply CVAEs to trajectory prediction:</p>\n<p><a href=\"https://www.kaggle.com/carlossouza/conditional-variational-auto-encoder\" target=\"_blank\">https://www.kaggle.com/carlossouza/conditional-variational-auto-encoder</a></p>\n<p>Cheers!</p>",
      "rawMarkdown": "Hey all! \nAfter reading some papers with innovative solutions to the trajectory prediction problem, I found several approaches using Deep Conditional Generative Models (AKA Conditional Variational Auto-encoders). This innovation was introduced in 2015, in the paper **Learning Structured Output Representation using Deep Conditional Generative Models**. The code below implements the paper, and can be used as base to apply CVAEs to trajectory prediction:\n\nhttps://www.kaggle.com/carlossouza/conditional-variational-auto-encoder\n\nCheers!",
      "votes": null
    },
    {
      "id": "1014157",
      "postDate": "09/17/2020 08:39:14",
      "content": "<p>Interesting topic</p>",
      "rawMarkdown": "Interesting topic",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1014157,
      "author_name": "bharathreddy3468",
      "author_url": "",
      "post_date": "09/17/2020 08:39:14",
      "content": "<p>Interesting topic</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1013819": "Hey all! \nAfter reading some papers with innovative solutions to the trajectory prediction problem, I found several approaches using Deep Conditional Generative Models (AKA Conditional Variational Auto-encoders). This innovation was introduced in 2015, in the paper **Learning Structured Output Representation using Deep Conditional Generative Models**. The code below implements the paper, and can be used as base to apply CVAEs to trajectory prediction:\n\nhttps://www.kaggle.com/carlossouza/conditional-variational-auto-encoder\n\nCheers!",
    "1014157": "Interesting topic"
  },
  "source": "meta"
}