Git Product home page Git Product logo

mgcn's People

Contributors

demonph10 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar

Forkers

fqldom

mgcn's Issues

原始数据获取

作者您好,您的工作做的十分出色,我想请问一下这三个原始数据集的图片和文字应该如何获取呢?能否提供一下处理的代码呢?

Question about Modal Embedding Calculation in "mgcn.py" line 200

Hello researchers of MGCN,
I am deeply impressed by the excellent performance of your work and am currently studying your MGCN project. I find it very insightful. However, I have a question regarding the Behavior-Aware Fuser implementation in the file mgcn.py.
In line 200, the modal embedding is calculated as follows:
side_embeds = (sep_image_embeds + sep_text_embeds + common_embeds) / 3
From my understanding, based on the original formula 15 in the paper, the modal embedding should be the sum of the shared embedding and the specific modal embeddings, without dividing by 3. Maybe like this:
side_embeds = common_embeds + (sep_image_embeds + sep_text_embeds) / 2

Could you please clarify the reasoning behind this implementation? Is this an experimental adjustment, or is there another rationale behind averaging these embeddings?
I am trying to understand the impact of this specific implementation choice on the model's performance and would greatly appreciate your insight on this matter. Thank you for your time and for sharing such an interesting project with the community. :))))))))

Best regards,
xiaodunshou

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.