from Hacker News

Visual question answering using CNN+RNN

by abhshkdz on 11/30/15, 1:39 AM with 9 comments

  • by n0us on 11/30/15, 3:29 AM

    Amazing. I only had a chance to read the README.md but my question is this. What happens if you ask it questions that it could not possibly answer, as in if it were given a picture of the man playing tennis and you asked it what the score was? Is it capable of discerning between questions that cannot be answered (given a particular input) and those that can?
  • by KnightHawk3 on 11/30/15, 3:23 AM

    Is there a catch to the effectiveness of this?

    I haven't seen it before and it seems pretty magical.

  • by arocks on 11/30/15, 2:50 PM

    I have seen sites using captchas which ask such visual questions thinking that only a human can answer them. This project really makes me doubt the effectiveness of such techniques.
  • by mrdrozdov on 11/30/15, 4:51 AM

    How do you measure accuracy? Is this a new baseline?