NeuralTalk, Stanford, California, USA

[Airicist]

NeuralTalk (https://github.com/karpathy/neuraltalk) on GitHub

NeuralTalk2 (https://github.com/karpathy/neuraltalk2) on GitHub

Deep Visual-Semantic Alignments for Generating Image Descriptions (https://cs.stanford.edu/people/karpathy/deepimagesent)

"Deep Visual-Semantic Alignments for Generating Image Descriptions (https://cs.stanford.edu/people/karpathy/cvpr2015.pdf)"

by Andrej Karpathy (https://pr.ai/showthread.php?t=13336), Li Fei-Fei (https://pr.ai/showthread.php?12399-Fei-Fei-Li)
Department of Computer Science, Stanford University

Article "Researchers Announce Advance in Image-Recognition Software (https://www.nytimes.com/2014/11/18/science/researchers-announce-breakthrough-in-content-recognition-software.html)"

by John Markoff
November 17, 2014

[Airicist]

http://vimeo.com/146492001

NeuralTalk and Walk
from Kyle McDonald
November 21, 2015


Andrej Karpathy's "NeuralTalk" code slightly modified to run from a webcam feed. I recorded this live while walking near the bridge at Damstraat and Oudezijds Voorburgwal in Amsterdam.
All processing is done on my 2013 MacBook Pro with the NVIDIA 750M and only 2GB of GPU memory. I'm walking around with my laptop open pointing it at things, hence the shaky footage and people staring at themselves. The openFrameworks code for streaming the webcam and reading from disk is available at gist.github.com/kylemcdonald/b02edbc33942a85856c8 (https://gist.github.com/kylemcdonald/b02edbc33942a85856c8)