Generating breakpoints in media playback

A computer-implemented method, comprising:

• determining, by one or more computing devices, a candidate set of breakpoints within a media item;
• determining a first set of features of multiple entities detected within a portion of the media item that is within a specified distance of a first candidate breakpoint;
• determining, for the first candidate breakpoint, a second set of features representing the presentation features of the media item at different incremental distances from the first candidate breakpoint, wherein the second set of features is different from the first set of features of the first candidate breakpoint;
• generating, using the machine learning model, a score for the first candidate breakpoint based on the first set of features and the second set of features;
• selecting a final set of breakpoints from among the set of candidate breakpoints based on a combination of the score generated by the machine learning model for each particular candidate breakpoint in the set of candidate breakpoints and a location of the particular candidate breakpoint relative to a different candidate breakpoint in the subset of candidate breakpoints;
• and
• during playback of the media item, providing, to a client device, a digital component that is presented at the client device when the media item reaches a given breakpoint among the final set of breakpoints stored for the media item, wherein the digital component is not part of the media item.

A system, comprising:

• a data storage device storing instructions;
• and
• one or more computing devices configured to execute instructions that, upon execution, cause the one or more computing devices to perform operations comprising:
• determining a candidate set of breakpoints within a media item;
• determining a first set of features of multiple entities detected within a portion of the media item that is within a specified distance of a first candidate breakpoint;
• determining, for the first candidate breakpoint, a second set of features representing the presentation features of the media item at different incremental distances from the first candidate breakpoint, wherein the second set of features is different from the first set of features of the first candidate breakpoint;
• generating, using the machine learning model, a score for the first candidate breakpoint based on the first set of features and the second set of features;
• selecting a final set of breakpoints from among the set of candidate breakpoints based on a combination of the score generated by the machine learning model for each particular candidate breakpoint in the set of candidate breakpoints and a location of the particular candidate breakpoint relative to a different candidate breakpoint in the subset of candidate breakpoints;
• and
• during playback of the media item, providing, to a client device, a digital component that is presented at the client device when the media item reaches a given breakpoint among the final set of breakpoints stored for the media item, wherein the digital component is not part of the media item.

A non-transitory computer readable medium storing instructions that, when executed by one or more data processing apparatus, cause the one or more data processing apparatus to perform operations comprising:

• determining a candidate set of breakpoints within a media item;
• determining a first set of features of multiple entities detected within a portion of the media item that is within a specified distance of a first candidate breakpoint;
• determining, for the first candidate breakpoint, a second set of features representing the presentation features of the media item at different incremental distances from the first candidate breakpoint, wherein the second set of features is different from the first set of features of the first candidate breakpoint;
• generating, using the machine learning model, a score for the first candidate breakpoint based on the first set of features and the second set of features;
• selecting a final set of breakpoints from among the set of candidate breakpoints based on a combination of the score generated by the machine learning model for each particular candidate breakpoint in the set of candidate breakpoints and a location of the particular candidate breakpoint relative to a different candidate breakpoint in the subset of candidate breakpoints;
• and
• during playback of the media item, providing, to a client device, a digital component that is presented at the client device when the media item reaches a given breakpoint among the final set of breakpoints stored for the media item, wherein the digital component is not part of the media item.