{
  "id": 306069,
  "title": "Sharing - Session-based Recommendation with Multi-Modal Features ",
  "url": "/competitions/h-and-m-personalized-fashion-recommendations/discussion/306069",
  "author_name": "AbaoJiang",
  "post_date": "2022-02-08T03:25:10.365000",
  "votes": 14,
  "comment_count": 0,
  "views": 0,
  "content": "<p><a href=\"https://arxiv.org/pdf/2107.05124.pdf\" target=\"_blank\">Transformers with multi-modal features and post-fusion context\nfor e-commerce session-based recommendation</a> <br>\nThe paper presents one of the winning solutions for the Recommendation task of the <em>SIGIR</em> 2021 Workshop on E-commerce Data Challenge. The problem is formulated as <strong>session-based recommendation</strong>. As for solution, they take <strong>multi-modal features</strong> into consideration, including tabular events, textual and image vectors. Though the data and scenario aren't exactly the same as this competition, I think the proposal can still provide valuable inspiration.</p>\n<p>Hope this helps.</p>",
  "messages": [
    {
      "id": 1680810,
      "postDate": "2022-02-08T03:25:10.367Z",
      "content": "<p><a href=\"https://arxiv.org/pdf/2107.05124.pdf\" target=\"_blank\">Transformers with multi-modal features and post-fusion context\nfor e-commerce session-based recommendation</a> <br>\nThe paper presents one of the winning solutions for the Recommendation task of the <em>SIGIR</em> 2021 Workshop on E-commerce Data Challenge. The problem is formulated as <strong>session-based recommendation</strong>. As for solution, they take <strong>multi-modal features</strong> into consideration, including tabular events, textual and image vectors. Though the data and scenario aren't exactly the same as this competition, I think the proposal can still provide valuable inspiration.</p>\n<p>Hope this helps.</p>",
      "rawMarkdown": "[Transformers with multi-modal features and post-fusion context\nfor e-commerce session-based recommendation](https://arxiv.org/pdf/2107.05124.pdf) \nThe paper presents one of the winning solutions for the Recommendation task of the *SIGIR* 2021 Workshop on E-commerce Data Challenge. The problem is formulated as **session-based recommendation**. As for solution, they take **multi-modal features** into consideration, including tabular events, textual and image vectors. Though the data and scenario aren't exactly the same as this competition, I think the proposal can still provide valuable inspiration.\n\nHope this helps.",
      "votes": 14
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "1680810": "[Transformers with multi-modal features and post-fusion context\nfor e-commerce session-based recommendation](https://arxiv.org/pdf/2107.05124.pdf) \nThe paper presents one of the winning solutions for the Recommendation task of the *SIGIR* 2021 Workshop on E-commerce Data Challenge. The problem is formulated as **session-based recommendation**. As for solution, they take **multi-modal features** into consideration, including tabular events, textual and image vectors. Though the data and scenario aren't exactly the same as this competition, I think the proposal can still provide valuable inspiration.\n\nHope this helps."
  }
}