Abstract: Systems, methods and/or techniques for automatic content recognition protocols are described. A method may be executed in a media device having an automatic content recognition application programming interface. The method may include generating one or more video fingerprints that correspond to video content that displays on the media device. The method may include communicating the one or more video fingerprints to an automatic content recognition backend system. The automatic content recognition backend system compares the one or more video fingerprints with one or more stored video fingerprints and determines whether a match occurs. If the match occurs, one or more event identifiers associated with the one or more video fingerprints may be received from the automatic content recognition backend system. The one or more event identifiers may be communicated to an application server, and one or more interactive events may be received from the application server.