Devices, computer-readable media, and methods for changing the state of a network-connected device in response to at least one facial gesture of a user are disclosed. For example, a processing system including at least one processor captures images of a face of a user, detects at least one facial gesture of the user from the images, determines an intention to change a state of a network-connected device from the at least one facial gesture, generates a command for the network-connected device in accordance with the intention, and outputs the command to cause the state of the network-connected device to change.