8000 GitHub - xubuvd/EmbodiedQA: Embodied Question Answering (EmbodiedQA)
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

xubuvd/EmbodiedQA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 

Repository files navigation

EmbodiedQA

Embodied Question Answering (EmbodiedQA), in a 3D environment moving beyond a static image context, requires to move into a right location for answering a given question. It is combination of Visual Language Navigation (VLN) task and Visual Question answering (VQA) task. And it poses several challenge problems.

About me

虚步, a Ph.D. student at BUPT. I am very fortunate to be advised by my advisor. My research is in the area of Vision, Language, and Reasoning, with a focus on Visual Dialogue. I am particularly interested in building a visually-grounded conversational AI (social robot) that can see the world and talk with us in natural language. Other interests include Visual/Language Grounding, Visual Reasoning, Visual Question Generation, and Visually-grounded Referring Expression.

Now I've been working on the EmbodiedQA problem. Please feel free to contact me with pangweitf@bupt.edu.cn or pangweitf@163.com if you have any questions or concerns.

In progress...

Performance

Training

References

  1. Abhishek Das, Samyak Datta, Georgia Gkioxari, Stefan Lee, Devi Parikh and Dhruv Batra. Embodied Question Answering. In CVPR 2018.
  2. ...

About

Embodied Question Answering (EmbodiedQA)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published
0