[–] mig39 11y ago ↗ Are these supposed to be funny?http://www.cs.toronto.edu/~nitish/nips2014demo/results/92679..."a man wielding an electric razor is gleefully shaving away another man ' s hair ."Hilarious!I think they've stumbled on computer-generated comedy. Some funny stuff in there. [–] Houshalter 11y ago ↗ That's from the "Nearest Caption in the Training Dataset". Which means it found the most similar image, and that image had that caption. [–] ilija139 11y ago ↗ No. That is not how it works. Read the papers again. [–] Houshalter 11y ago ↗ It very clearly says "Nearest Caption in the Training Dataset". The generated labels are below it. [–] mig39 11y ago ↗ What papers? [–] vlasev 11y ago ↗ This one http://www.cs.toronto.edu/~nitish/nips2014demo/results/82676... has a tag "fingering" [–] bottled_poe 11y ago ↗ http://www.cs.toronto.edu/~nitish/nips2014demo/results/80282...It must be making some very broad generalisations to come up with the tag 'homosexuals'... [–] unwind 11y ago ↗ It weirded me out, too.The only image I tried (http://www.cs.toronto.edu/~nitish/nips2014demo/results/79355...) is tagged "lesbianism".
[–] Houshalter 11y ago ↗ That's from the "Nearest Caption in the Training Dataset". Which means it found the most similar image, and that image had that caption. [–] ilija139 11y ago ↗ No. That is not how it works. Read the papers again. [–] Houshalter 11y ago ↗ It very clearly says "Nearest Caption in the Training Dataset". The generated labels are below it. [–] mig39 11y ago ↗ What papers?
[–] ilija139 11y ago ↗ No. That is not how it works. Read the papers again. [–] Houshalter 11y ago ↗ It very clearly says "Nearest Caption in the Training Dataset". The generated labels are below it. [–] mig39 11y ago ↗ What papers?
[–] Houshalter 11y ago ↗ It very clearly says "Nearest Caption in the Training Dataset". The generated labels are below it.
[–] vlasev 11y ago ↗ This one http://www.cs.toronto.edu/~nitish/nips2014demo/results/82676... has a tag "fingering" [–] bottled_poe 11y ago ↗ http://www.cs.toronto.edu/~nitish/nips2014demo/results/80282...It must be making some very broad generalisations to come up with the tag 'homosexuals'... [–] unwind 11y ago ↗ It weirded me out, too.The only image I tried (http://www.cs.toronto.edu/~nitish/nips2014demo/results/79355...) is tagged "lesbianism".
[–] bottled_poe 11y ago ↗ http://www.cs.toronto.edu/~nitish/nips2014demo/results/80282...It must be making some very broad generalisations to come up with the tag 'homosexuals'... [–] unwind 11y ago ↗ It weirded me out, too.The only image I tried (http://www.cs.toronto.edu/~nitish/nips2014demo/results/79355...) is tagged "lesbianism".
[–] unwind 11y ago ↗ It weirded me out, too.The only image I tried (http://www.cs.toronto.edu/~nitish/nips2014demo/results/79355...) is tagged "lesbianism".
[–] guillegette 11y ago ↗ OP, could you give us more details about this ? [–] thatcat 11y ago ↗ Not OP, but from the site... http://www.cs.toronto.edu/~nitish/Nitish Srivastava, co-instructor for CSC 321 : Intro to Neural Networks ( http://www.cs.toronto.edu/~rgrosse/csc321/ ) pretrains a convolutional neural net using image sets ( https://github.com/torontodeeplearning/convnet/tree/master/e... and https://github.com/torontodeeplearning/convnet/tree/master/e... )also has a demo to upload your own images and get them captioned or classified http://deeplearning.cs.toronto.edu/i2t but seems their servers are getting blasted right now
[–] thatcat 11y ago ↗ Not OP, but from the site... http://www.cs.toronto.edu/~nitish/Nitish Srivastava, co-instructor for CSC 321 : Intro to Neural Networks ( http://www.cs.toronto.edu/~rgrosse/csc321/ ) pretrains a convolutional neural net using image sets ( https://github.com/torontodeeplearning/convnet/tree/master/e... and https://github.com/torontodeeplearning/convnet/tree/master/e... )also has a demo to upload your own images and get them captioned or classified http://deeplearning.cs.toronto.edu/i2t but seems their servers are getting blasted right now
[–] mkoryak 11y ago ↗ I was going to write a negative post about how singularity is still a long while away based on this caption: http://www.cs.toronto.edu/~nitish/nips2014demo/results/84542...but then I realized that I cant come up with a description of what is going there myself.Ill get you next time CPU! [–] ConceptJunkie 11y ago ↗ Looks like they are dyeing cloth to me.I would really like to know how this works because the captions are... interesting. [–] ethana 11y ago ↗ Because you have never experienced what it is happening in the picture?The singularity is not going to be an AI revolution, it's when we decode the human brain's signals. [–] tomjen3 11y ago ↗ Indian textile workers dye cloth in large outside pots?
[–] ConceptJunkie 11y ago ↗ Looks like they are dyeing cloth to me.I would really like to know how this works because the captions are... interesting.
[–] ethana 11y ago ↗ Because you have never experienced what it is happening in the picture?The singularity is not going to be an AI revolution, it's when we decode the human brain's signals.
[–] nixy 11y ago ↗ Some results are pretty funny.http://www.cs.toronto.edu/~nitish/nips2014demo/results/84824...Generated caption: "a man appears to be a banana on a tree"
[–] starshadowx2 11y ago ↗ I like how two of the options to this one (http://www.cs.toronto.edu/~nitish/nips2014demo/results/84291...), of a guy at the gym, are"a woman in a kitchen, leaps in the air while attempting to balance a glass cup in one hand."and"a young man playing wii in front of a large knife."
16 comments
[ 2.7 ms ] story [ 57.1 ms ] threadhttp://www.cs.toronto.edu/~nitish/nips2014demo/results/92679...
"a man wielding an electric razor is gleefully shaving away another man ' s hair ."
Hilarious!
I think they've stumbled on computer-generated comedy. Some funny stuff in there.
It must be making some very broad generalisations to come up with the tag 'homosexuals'...
The only image I tried (http://www.cs.toronto.edu/~nitish/nips2014demo/results/79355...) is tagged "lesbianism".
Nitish Srivastava, co-instructor for CSC 321 : Intro to Neural Networks ( http://www.cs.toronto.edu/~rgrosse/csc321/ ) pretrains a convolutional neural net using image sets ( https://github.com/torontodeeplearning/convnet/tree/master/e... and https://github.com/torontodeeplearning/convnet/tree/master/e... )
also has a demo to upload your own images and get them captioned or classified http://deeplearning.cs.toronto.edu/i2t but seems their servers are getting blasted right now
but then I realized that I cant come up with a description of what is going there myself.
Ill get you next time CPU!
I would really like to know how this works because the captions are... interesting.
The singularity is not going to be an AI revolution, it's when we decode the human brain's signals.
http://www.cs.toronto.edu/~nitish/nips2014demo/results/84824...
Generated caption: "a man appears to be a banana on a tree"
"a woman in a kitchen, leaps in the air while attempting to balance a glass cup in one hand."
and
"a young man playing wii in front of a large knife."