Neural Networks That Describe Images • Hacker News Board

Re: Neural Networks That Describe Images

#21

Post by makmanalp » Thu, Nov 20, 2014, 2:03 AM UTC

DavidSJ wrote: post #20

arjie wrote: post #5

Fascinating. Also interesting to see the failure modes. Any human would quickly realize that the "boy doing backflip on wakeboard" is actually playing on a trampoline. Or the "two young girls playing with legos toy". Great stuff!

I think I'm a human, but I did not realize that boy was on a trampoline instead of a wakeboard until you pointed it out. I think the water in the background confused me. I was also probably biased by reading the network's label before reaching my own judgment.

> I think I'm a human

You sure? :) I definitely think the text does bias your interpretation though, I did the exact same.

Re: Neural Networks That Describe Images

#22

Post by ed » Thu, Nov 20, 2014, 2:09 AM UTC

This isn't really a breakthrough in object identification, as much as it is a clever pairing of identification with (mostly existing) language systems, is that right?

Wondering whether there's any merit to sibling comments speculating this is the future of e.g. surveillance

Re: Neural Networks That Describe Images

#23

Post by e12e » Thu, Nov 20, 2014, 2:59 AM UTC

kolbe wrote: post #16

Presentations like these make me realize how close we are to developing law enforcement (/police state) technology that will be very effective. I figure when the kinks are smoothed out, that we could run this on a video feed, and have crimes prevented right as they're about to happen. It's almost scary. Imagine 20 years from now, some guy pulls a gun on you, and a video feeds identifies his action, and immediately sh…

> some guy pulls a gun on you, and a video feeds identifies his action, and immediately shoots a tranquilizer straight into his jugular with perfect aim.

Eh, no. Safe preventive action against a gun (or other lethal weapon, really) needs to happen before the weapon is ready for use. What if the assumed offender was wearing protection? Perfect aim wouldn't help. Lethal force might be possible to deploy - but probably not in a safe manner.

Re: Neural Networks That Describe Images

#24

Post by jameshart » Thu, Nov 20, 2014, 4:09 AM UTC

arjie wrote: post #5

Fascinating. Also interesting to see the failure modes. Any human would quickly realize that the "boy doing backflip on wakeboard" is actually playing on a trampoline. Or the "two young girls playing with legos toy". Great stuff!

Right - impressive though this is, also the cat isn't black, the woman with the bananas might well not be a woman, the girl isn't swinging on a swing, the construction worker is probably not in the road, and the guitarist is tuning the guitar, not playing it. It's pretty much wrong -in detail- on every count.

The weird thing is how at a glance, it seems pretty much correct. And how some people here are willing to look at that and think 'automated law enforcement is clearly imminently possible'.

Re: Neural Networks That Describe Images

#25

Post by sigterm » Thu, Nov 20, 2014, 4:44 AM UTC

tiler wrote: post #14

I really appreciate that the Stanford group is always willing to post mistakes/mislabels. Kudos.

The face detection on her research group's front page has one glaring mislabel (http://vision.stanford.edu/).

I always find that quite amusing.

Re: Neural Networks That Describe Images

#26

Post by visarga » Thu, Nov 20, 2014, 5:04 AM UTC

thomasahle wrote: post #3

It would be great to have this for image search!

It will revolutionize porn search, for sure.

Re: Neural Networks That Describe Images

#27

Post by visarga » Thu, Nov 20, 2014, 5:06 AM UTC

bprater wrote: post #17

kolbe wrote: post #16

Presentations like these make me realize how close we are to developing law enforcement (/police state) technology that will be very effective. I figure when the kinks are smoothed out, that we could run this on a video feed, and have crimes prevented right as they're about to happen. It's almost scary. Imagine 20 years from now, some guy pulls a gun on you, and a video feeds identifies his action, and immediately sh…

Effective and also scary. That same video feed could be archiving (for eternity) every single citizen's movement, action, or even words: "Citizen #5135: In 2015, spit on sidewalks 28x this year, jaywalked 49x, etc..."

Even if this is not working now, it can still be applied later on video shot today. So we are already en route to being judged by such an automated guardian.

Re: Neural Networks That Describe Images

#28

Post by ibrahima » Thu, Nov 20, 2014, 6:12 AM UTC

kolbe wrote: post #16

Presentations like these make me realize how close we are to developing law enforcement (/police state) technology that will be very effective. I figure when the kinks are smoothed out, that we could run this on a video feed, and have crimes prevented right as they're about to happen. It's almost scary. Imagine 20 years from now, some guy pulls a gun on you, and a video feeds identifies his action, and immediately sh…

That's basically the plot of Person of Interest, right? (I've watched a few episodes but never paid much attention).

Re: Neural Networks That Describe Images

#29

Post by negamax » Thu, Nov 20, 2014, 7:22 AM UTC

jameshart wrote: post #24

arjie wrote: post #5

Fascinating. Also interesting to see the failure modes. Any human would quickly realize that the "boy doing backflip on wakeboard" is actually playing on a trampoline. Or the "two young girls playing with legos toy". Great stuff!

Right - impressive though this is, also the cat isn't black, the woman with the bananas might well not be a woman, the girl isn't swinging on a swing, the construction worker is probably not in the road, and the guitarist is tuning the guitar, not playing it. It's pretty much wrong -in detail- on every count. The weird thing is how at a glance, it seems pretty much correct. And how some people here are willing to loo…

Wow.. talk about high expectations. This is really well done. Identifying multiple concepts in an image and describe it to a good degree of accuracy. And this will get better further.

Re: Neural Networks That Describe Images

#30

Post by dustintran » Thu, Nov 20, 2014, 7:45 AM UTC

kolbe wrote: post #16

Presentations like these make me realize how close we are to developing law enforcement (/police state) technology that will be very effective. I figure when the kinks are smoothed out, that we could run this on a video feed, and have crimes prevented right as they're about to happen. It's almost scary. Imagine 20 years from now, some guy pulls a gun on you, and a video feeds identifies his action, and immediately sh…

I imagine more preventative solutions to develop earlier which are more effective, e.g., "treat" citizens who are predicted highly likely to be cause a dangerous outcome in the future.

Or in the simple context of computer vision and the camera, raise warnings as individuals on screen act increasingly more suspicious. I imagine future technology will at least have intelligent security cameras that signal alarms based on the current video feed, not just when it's suddenly shut off for example.