INTERESTING.JPG explores the capabilities and limitations of the current state-of-the-art in image analysis and feature detection. Working with a model developed by the University of Toronto’s Deep Learning Group, it attempts to generate captions for images of breaking news events. It automatically posts the images and their captions to a twitter account, and source is available on github.

a man stands in front of his pants was wearing a black hat .

a group of people standing in front of a tunnel .

a man racing on a stage in front of a large crowd of spectators .

a group of people standing near a pile of rocks .

a group of people that are on top of a goat .

a close up of a frozen desert .

a man in a white shirt is eating a sandwich at a table .

a plane is flying in the sky .

there is a person sitting on the ground .

a group of people that are standing in front of a building .

a man sits in the back of a car .

a woman in a red shirt is holding her hand .

a man on a moped is walking down the street .

a man is standing on a large rock ledge in the forest .

a man is standing at a dock in a stadium in front of a ceiling fan .

a woman stands in front of a forest .

a man pushing a ladder on a fence in the background .

a lot of people are watching things on the lawn .

there is a man who is wearing a hat .

helicopter is on the ground in the desert .