169 comments

[ 2.8 ms ] story [ 234 ms ] thread
This is no fun to talk about without permalinks to uploaded images/results.
I gave this image - https://i.imwx.com/images/maps/truvu/map_specnewsdct-109_lts...

and I got this result "I am not really confident, but I think it's a couple of glass vases with flowers on top of a surfboard."

It suggested that two of the images I uploaded also had something to do with surfing. Maybe it was trained on a lot of surfing images.
(comment deleted)
I gave it this one [1], it claims "I think it's a blurry picture of a boat." which is not entirely bad description but obviously misses the point.

[1] http://vignette3.wikia.nocookie.net/lovecraft/images/9/95/5b...

Of all things to try to make a brand new AI describe, you give it an indescribable god/priest of R'lyeh???

:)

It is important to unit test the boundary conditions.
It loves things being on top of surf boards

http://imgur.com/WWHQu5i

MS has been providing the net with fun activities for a few months now. The other night the celebrity look alike site blew up on twitter and instagram

An interesting project, but it fared pretty poorly on all of the images I gave it - the suggestions were wildly outlandish.
Ha, got eerily accurate results. Some funny ones as well, but interesting tech.
(comment deleted)
It says "any image" but I think they really mean "any photograph", based on the samples as well as the stuff I uploaded to it.
I had to share this one, I sent a screenshot of the Yahoo homepage from a while ago (yeah, I had that hanging around...) with the main image being of Donald Trump.

The caption guess was "I am not really confident, but I think it's a television screen and he seems ."

Did you know that television screens are not only alive, but male?
I tried a bunch of different images and I got 'two giraffes near a tree' a bunch of times. They were drawn images though.
"I seem to be under the weather right now. Try again later :(" i.e. we killed it.
Did you post a picture of rain?
That's disapointing. But it worked once and did very well. I sent this picture http://www.sofoot.com/IMG/img-le-regard-perdu-1460478703_580... and it said "I think it is a football player on the field and he looks :(".

He didn't mistake the football player with a rugby player, a cricket player or else. And +1 for the emoji

>rugby or cricket

Wonder if it was the ball logo on the player's shirt, the greater popularity of football , or something else that helped it distinguish.

Or if it assumed it was actually an American football player and would have answered the same for all the sports on green fields...
I guess Occam's Razor says we should check the EXIF data.
I uploaded a photograph of a bunch of snow piled on top of a round table[0], which looks a lot like a marshmallow to the human eye. But it came back with "I am not really confident, but I think it looks like a polar bear lying in the snow." Not terrible :)

[0] http://imgur.com/nKRK5hc

I came here to say that along with the message: Classic Microsoft... they need to restart the machine.
I got that for a pic of a teddy bear.

I uploaded a photo of the planet Saturn and it guessed that it was dish. It got the shape right.

It can't recognise B. Gates photo. Ok.
Shows how far MS has come since the 90s!
Service appears to be down or "under the weather" whatever that means.
It's only a matter of time before a repeat of Microsoft's last AI experiment (Tay), when the Internet teaches CaptionBot all of the positions in the Kama Sutra.
Potential future quote:

"In a development that surprised even us, after an influx of /b/ and Something Awful Goons, the AI decided to shut itself off."

(comment deleted)
For science: it only states "I think this may be inappropriate content so I won't show it" which is a shame :)
I chose goatse and it says "I am not really confident, but I think it's a man holding a cat."
It was spot on for 30% of the images, but wildly inaccurate on the rest.

In fact, I assume this is a crowd sourced training for the tech..

Kind of disappointing, but at the same time I understand that this task is not trivial at all.

I fed it the "Wat" meme and it thinks it's Pope Benedict.

>I am not really confident, but I think it's a man is smiling for the camera and they seem . I am 99% sure that's Pope Benedict XVI

Source Image: http://memesvault.com/wp-content/uploads/Wat-Meme-Old-Lady-0...

Needless to say, my errant habits of trying to break stuff shine through once again.

Truth to be told it wasn't off too far.
Hah, yeah but when I got it working again, this time with a screenshot of Jules from Pulp Fiction, it thinks his gun is a camera.

>I am not really confident, but I think it's a man holding a camera.

Source Image: http://www.cinemablend.com/images/news_img/79237/pulp_fictio...

Imagine this tech matures and it can be incorporated with bodycams for police, when confronting a subject with objects in their hands it may be able to confidently estimate the probability of being a firearm or not, with better predictability than the police/people.
...and better proveability. Most people are actually unarmed. http://www.theguardian.com/us-news/2015/jun/01/black-america...

While we're here, let's go the full way and set up a proveable and public way to train a robocop, and I'd trust that more than a human cop. The awkward moment when AIs have more brains than cops (at least under the US system).

Likely before we get to robocops the "robocops" will be integrated into people who have proven risky by either previously known behavior in addition to social signals.

So Jane truant with convictions of petty theft or battery gets off with probation if she agrees to embed her own personal "robocop". Yes invasion of privacy, etc. But the alternative for her would be time in the pen, for example. So in this case people can become their own robocops who turn the host in to authorities if certain conditions are met (engages in previously restricted activities).

I think this is more likely than a roving robotic cop which looks out for misdeeds.

You are doing the lord's work. Carry on.
Hmm.

A couple of days ago I think there was a post about Google doing a lot of development and research around creating systems that understand / categorize / comment / recognize images.

One thing I took away from reading about it is that Google has billions of images to train it with from all their different ventures.

Does Microsoft have access to anywhere near the same numbers of pictures?

Microsoft owns Corbis, doesn't it? http://www.corbisimages.com
It is my understanding that it was owned by Bill Gates not Microsoft.

Bill Gates sold it earlier this year to a Chinese Company http://www.ft.com/intl/cms/s/0/d6fbcb88-c126-11e5-846f-79b0e... (paywall),

The Chinese company has structured a deal with Getty to take over licensing outside of China.

However, having access to world class photography is great, but the images that (probably) will be the most interesting for Microsoft to recognize will be selfies, and other "crowd" created amateur photography and possibly memes.

I personally would think it to be cool to see if the bot could traverse the Getty collection and see if it could recognize the photographer of an image it had not seen before. Why yes, this is Leibovitz.

It is almost as smart as a child. I uploaded a picture of my Notre-Dame vacation photo, and the caption was "A person standing in front of a church"... which is close to my sons "mommy standing in front of that church we went to"
Yep, on the stuff it recognizes. It recognized a picture I tested taken from the Grand Tetons as "a lake with a mountain in the background", which was quite correct, but also kind of generic.

On the other hand, it described a picture of Grand Prismatic Springs in Yellowstone as "a train with smoke coming out of the water." Which also is kind of like the crazy things kids sometimes say when they see something new.

http://imgur.com/JBlpJvQ

http://imgur.com/JwidrUy

I get the same "about as smart as a very young child" vibe from CaptionBot; the intersection of pleasantly silly and rather impressive.

(Photo: Rover P6 on the start line with a Nissan R35 GTR, guessed as "I think it's a police car parked in front of a truck.")

I tried a Magic Eye photo. It didn't see the sailboat at all.
I tried the same thing and it saw a monkey.
"I never felt at home here. This is an awful place to be dropped down halfway”
Microsoft has great tech team - no doubt, but seems it lacks in product and market strategies.
CaptionBot team here. Thanks for the images and captions! Please keep sharing them and give us feedback.
First of all congratulations on a) the science (built on the shoulder of giants...) b) the accessibility / interface and service

Wondering if you plan to open up a caption API of any sort? Can definitely use something like this. If you desire the training feedback, then that could be added as well as part of the API. I'd be willing to do that for some images. So if you do add a training feedback API, please make it optional.

It would be great if you added a text box under the stars so I can (optionally) tell you why I didn't give you five stars.

For example, I uploaded a picture of my daughter as an infant, and it said, "This is a baby on a bed and he's :D" which I gave four stars to because it said he instead of she. But honestly you really have no way of knowing that. :)

Thank you jedberg! That's a great idea. We love it and will look into adding it soon.
Do you know why it puts a lot of things on surfboards?

It seems from the comments that that is one of the most represented misclassifications.

Thank you very much for putting your work out there for people to have fun with (and criticise!).

CaptionBot seems to have a bit of trouble with simple two-colour outline drawings. In one case I saw it even get the colour wrong ("red and white" for a black and red image).

Is that something you would have expected?

Also- I notice it doesn't do very well with character recognition either. Is that surprising?

Have you considered an 'abstract' type of version? As in, rather than simply describing the image as the caption, take the information that would be used, fill it in a MAD-LIBS[1] style setup, and see how that turns out? Maybe it's just me but a surrealist CaptionBot could be pretty fun.

[1] https://en.wikipedia.org/wiki/Mad_Libs

It's not at all working. Every time, the same thing pops up - "I am under the weather now. Try again later. :("
Silly Microsoft, should have at least had some caching layer instead of analyzing every image. RIP CaptionBot.
Wow! I gave it a photo of a kitesurfer and it got it (man flying a kite in a body of water). Amazing!!