Abstract: One or more computing devices, systems, and/or methods for tracking user interaction with objects based upon eye gazing movements are provided. A canvas is populated with grids corresponding to locations of objects and is populated with an eye cursor positioned to track a gaze of a user. A plurality of image frames captured by a camera are evaluated to track interaction of users with the objects. For an image frame, a midpoint between eyes of a user are identified based upon facial landmarks of the user. A current position of the eye cursor is set within the canvas based upon the midpoint. In response to detecting that the eye cursor intersects a first grid in the canvas, the user is identified as interacting with a first object associated with the first grid.

Abstract: An exemplary system includes a cloud server configured to provide a service to a client device by way of a network. The system further includes an edge computing device configured to provide, from an edge of the network to the client device, a latency-sensitive task associated with the service. The cloud server and the edge computing device are configured to operate on distinct and matching datasets to provide the service to the client device.