VQA based on image captions

  • 5 Replies
  • 742 Views
*

hainaa

  • Roomba
  • *
  • 4
VQA based on image captions
« on: April 22, 2019, 07:28:47 am »
Hi,

Is there some paper related to the task of answering an image based question given as input an image and its description.
I tried to search online but I didn't find any but I remember some days back I saw such work. If anyone know of some work related to it, please share the link.

Thanks!

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • ******************
  • Hal 4000
  • *
  • 4383
  • First it wiggles, then it is rewarded.
    • Main Project Thread
Re: VQA based on image captions
« Reply #1 on: April 22, 2019, 08:46:11 am »
like google deepmind or somethin? I seen something like white images with circles and patterns of problem solving in a video i seen online, on I think it was Two Minute Papers's youtube channel. They make it generally aswer questions like what is the most likely pattern that comes next in this array of circles...
Emergent

*

ivan.moony

  • Trusty Member
  • ***********
  • Eve
  • *
  • 1468
    • contrast-zone
Re: VQA based on image captions
« Reply #2 on: April 22, 2019, 10:52:11 am »
There exist some rules interwoven within this world. As much as it is a blessing, so much it is a curse.

*

hainaa

  • Roomba
  • *
  • 4
Re: VQA based on image captions
« Reply #3 on: April 23, 2019, 05:59:01 am »
No, It's different. It's great work but I want one where input is (question, image , image description) and output is the answer for the question.

*

WriterOfMinds

  • Trusty Member
  • *******
  • Starship Trooper
  • *
  • 358
    • WriterOfMinds Blog
Re: VQA based on image captions
« Reply #4 on: April 23, 2019, 06:53:11 am »
The closest thing I can think of is Visual Chatbot. It generates the image description rather than taking it as input, but I think it can use dialogue history (including the generated caption?) to help answer followup questions.

https://arxiv.org/abs/1611.08669

*

hainaa

  • Roomba
  • *
  • 4
Re: VQA based on image captions
« Reply #5 on: April 23, 2019, 06:57:59 am »
Actually this is really interesting and maybe I could get ideas from it. Thanks for the link  :)

 


GTP-3 is bigoted!
by frankinstien (AI News )
January 20, 2021, 10:00:31 pm
White House Launches National AI Office
by MikeB (AI News )
January 15, 2021, 03:45:53 am
DALL-E text & image 2 image !!!!!
by LOCKSUIT (AI News )
January 06, 2021, 08:14:52 pm
Creating a VR sense of temperature
by frankinstien (AI News )
January 02, 2021, 09:19:51 am
Robots dancing better than us?
by 8pla.net (Robotics News)
December 31, 2020, 05:54:29 am
Bjarne Stroustrup (the creator of C++) talks about Machine Learning
by MikeB (AI News )
December 19, 2020, 12:26:31 pm
Wheels Are Better Than Feet for Legged Robots
by HS (Robotics News)
December 10, 2020, 07:51:29 pm
Getting a bot to smell!
by frankinstien (AI News )
December 09, 2020, 03:53:00 pm

Users Online

130 Guests, 0 Users

Most Online Today: 160. Most Online Ever: 2369 (November 21, 2020, 04:08:13 pm)

Articles