• Innovation through disruptive and scalable technology .
  • Cutting-edge AI research .
  • Accelerating innovations in research and service .
  • We strive for (and achieve) excellence! .
  • “SotA” (State-of-the-Art) .
  • Visual demo of research and service innovation
  • Human. Machine. Experience Together .

Korean Localization of Visual Question Answering for Blind People

2019

NeurIPS 2019

Abstract

The advancement of computer vision and natural language processing increases the possibility of assisting people with visual impairment upon their verbal commands. At 2018 ECCV, VizWiz Grand Challenge: Answering Visual Questions from Blind People initiated this effort by questioning how advanced technology can contribute to a higher standard of human rights by providing an inclusive platform. Here, we extend its effort by inviting Korean blind people to create a Korean version of the VizWiz dataset. We collect the images taken by Korean blind people and the corresponding questions reflecting the local context. In contrast to the 7 years collection of 31K VizWiz, we expect to collect 100K dataset within 6 months and benchmark the dataset using one of state-of-the-art visual question answering models. We hope that this project will contribute to social welfare by providing an appropriate solution to make our society more equitable and sustainable for all.

More Detail: Click Here