sharifza / schemata Goto Github PK
View Code? Open in Web Editor NEWThis repository contains code and dataset splits for the paper "Classification by Attention: Scene Graph Classification with Prior Knowledge"
License: MIT License
This repository contains code and dataset splits for the paper "Classification by Attention: Scene Graph Classification with Prior Knowledge"
License: MIT License
Great work!
Buy the way, I don’t know wether I missed some important information in this paper, it seems that there are no details about the Prior Knowledge (a prior knowledge base (ICP))?
Becides, "Later we will show that our model can accurately generate the PKG
, i.e., the commonsense that is captured from perceptions during training."
I don’t seem to find the corresponding part.
thanks again :)
Under what license is the code distributed? It would be important to add a LICENSE file otherwise it's difficult for others to reuse/modify it
Thanks for your nice work in sgg :)
I notice that the edge feature has two initialization methods in RelModel. One is initialized by union feature and another is initialized by the spatial of subject and object. I am wondering their difference and why Schemata applies the latter method.
By the way, It seems that a learnable ScaleLayer is applied to scale the gradient of location_hlayer. Is a trick to make the training process stable? I don't know if there's anything wrong with what I understand.
Looking forward to your reply. Thanks again :)
Great work!
But I have an important question. How to get the embedding vector of the schema Sc in Section "Schemata"?
So, I wonder if you would consider sending me the details about the Schema Representations.
Thank you very much! :)
Good morning,
thanks for your work in scene graph generation, very well done! I would like to ask when you plan to release the code of the project.
Thanks in advance and have a nice day!
Silvia
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.