Contextual-based method and system for identifying and revealing selected objects from video

A computer-implemented system comprising one or more processor-based devices configured to:

• receive a video stream comprising a sequence of images;
• direct a focus of attention to a first image of the sequence of images;
• determine automatically a probability that is associated with identifying a representation of an object by using a computer-implemented neural network to interpret a plurality of pixels within the first image;
• update the probability in accordance with an automatically inferred context that is associated with the first image;
• and
• deliver to a user a communication that is in accordance with the updated probability, wherein the communication comprises a plurality of syntactical elements that reference attributes of the object.

A computer-implemented method, comprising:

• receiving a video stream comprising a sequence of images;
• directing a focus of attention of a computer-implemented system to a first image of the sequence of images;
• determining automatically a probability that is associated with identifying a representation of an object by using a computer-implemented neural network that is trained to identify the representation of the object to interpret a plurality of pixels within the first image;
• updating the probability in accordance with an automatically inferred context that is inferred by a computer-implemented neural network that is trained to identify the context, and
• enabling the user, in accordance with the updated probability, to direct a command to the representation of the object.