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, while visiting for IDFA DocLab. NeuralTalk is trained on the MS COCO dataset, which guides the kind of captions that are generated MS COCO contains 100k image-caption pairs covering a wide variety of situations.