README.md

VisualAidForTheBlind

Visual Aid For The Blind Based On Image Caption And VQA

/NativeApp is Android code of the client
/CoreModel is Flask + Pytorch code of the server
/Else is consist of ppt for defense and demo

References

• Image Captioning
• Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
• Deep Modular Co-Attention Networks for Visual Question Answering