Abstract: Systems and method are provided for detecting the boundaries of media relative to linear media programming. A display device may receive a first cue from a first video frame of media being presented by a display device and generate, using a trained machine-learning model and the first cue, a first prediction of a first content type represented by the first video frame. The display device may subsequently receive a second cue from a second video frame of media being presented by the display device and generate a second prediction of a second content type represented by the second video frame. The display device can determine a probability that the first content type does not match the second content type based on the first prediction and the second prediction thereby identifying a boundary between different media being presented by the display device.