Deepmind Technologies Limited

Sony Interactive Entertainment Europe Limited

Christopher Paul Burgess

Alexander Lerchner

Arka Tilak Pal

Demis Hassabis

Irina Higgins

Loic Matthey-de-l'Endroit

Matthew Botvinick

Nicolas Sonnerat

Loic Matthey-De-L`ENDROIT

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for learning visual concepts using neural networks. One of the methods includes receiving a new symbol input comprising one or more symbols from a vocabulary; and generating a new output image that depicts concepts referred to by the new symbol input, comprising: processing the new symbol input using a symbol encoder neural network to generate a new symbol encoder output for the new symbol input; sampling, from the distribution parameterized by the new symbol encoder output, a respective value for each of a plurality of visual factors; and processing a new image decoder input comprising the respective values for the visual factors using an image decoder neural network to generate the new output image.

Learning visual concepts using neural networks

A method of subtitling comprises the steps of obtaining an audio file of dialogue in a first language, obtaining a file of script text corresponding to the dialogue in the audio file in the same first language, determining a timing correspondence between dialogue in the audio file and words in the script text, detecting at least a first pause during performance of the dialogue in the audio file, defining a respective breakable point in the script text corresponding to the or each detected pause, and dividing the script text out into a sequence of subtitle lines of text responsive to the location of one or more of the defined breakable points.

System and method of subtitling by dividing script text into two languages

Growing community of inventors

London, United Kingdom

Christopher Paul Burgess