The present disclosure is directed to identifying three-dimensional-human-gesture input. In particular, the methods and systems of the present disclosure can: receive from one or more sensors, data describing one or more three-dimensional motions comprising a three-dimensional-human-gesture input; generate, based at least in part on the data describing the one or more three-dimensional motions, two-dimensional data at least partially describing at least one motion of the one or more three-dimensional motions; and identify, based at least in part on the two-dimensional data, the three-dimensional-human-gesture input.