Researchers Andrej Karpathy and Li Fei-Fei presents in Deep Visual-Semantic Alignments for Generating Image Descriptions a model for estimating natural language description of images.
They share part of the code on Github so people can train their neural network to describe images.
Visual information and its correspondent descriptions such as below:
“girl in pink dress is jumping in air.”
“woman is holding bunch of bananas.”
“a young boy is holding a baseball bat.”
this is generated in layers of smantic correspondence, such as below:
