<body><script type="text/javascript"> function setAttributeOnload(object, attribute, val) { if(window.addEventListener) { window.addEventListener('load', function(){ object[attribute] = val; }, false); } else { window.attachEvent('onload', function(){ object[attribute] = val; }); } } </script> <div id="navbar-iframe-container"></div> <script type="text/javascript" src="https://apis.google.com/js/platform.js"></script> <script type="text/javascript"> gapi.load("gapi.iframes:gapi.iframes.style.bubble", function() { if (gapi.iframes && gapi.iframes.getContext) { gapi.iframes.getContext().openChild({ url: 'https://www.blogger.com/navbar/9924031?origin\x3dhttp://apathycurve.blogspot.com', where: document.getElementById("navbar-iframe-container"), id: "navbar-iframe" }); } }); </script>

Wednesday, April 27, 2016

CaptionBot

Microsoft has released a public test site for their CaptionBot, an artificial intelligence which attempts to analyze images uploaded by you and then provide a coherent English language description of them. For example, when I uploaded this photo of my dog...



...CaptionBot responded: "I think it's a dog laying on the ground." Not bad. Can't really expect a disconnected intelligence born in cyberspace to understand the distinction between a deck and the ground with such meager visual cues. A few more test images yielded similarly impressive results, sometimes with minor errors of interpretation.

Then I uploaded this photo and the response is pure gold:



"I think it's a person holding a sign and he seems 😐"

"He..." ROFLMAO.

0 Comments:

Post a Comment

<< Home