Systems, apparatuses, and methods for detecting a user gesture or eye tracking for selecting of an object, and responding to the selection, are disclosed. A gesture or eye tracker may be placed near a user, along with a camera positioned to share at least a portion of a field of view with the user. The user may look or gesture to an object within the portion of the field of view, indicating its selection. The object may be recognized, and the user presented with one or more actions to take in response to the selected object.