Creating a narrative description of media content and applications thereof

1. A computer-implemented method comprising:

recognizing a first object in a first image to determine a first content data that identifies the first object, wherein recognizing the first object comprises recognizing a first landmark;

recognizing a second object in a second image to determine a second content data that identifies the second object, wherein recognizing the second object comprises recognizing a second landmark;

determining a parameter value based at least in part on the first content data and the second content data, wherein determining the parameter value comprises identifying a first location of the first landmark and a second location of the second landmark; and

generating a narrative description according to a parameterized template, wherein the narrative description includes the parameter value.

2. The computer-implemented method of claim 1 , wherein determining the parameter value further comprises:

determining a region that encompasses the first location and the second location based on a hierarchy of regions.

3. The computer-implemented method of claim 2 , wherein the region is the smallest region in the hierarchy of regions that encompasses the first location and the second location.

4. The computer-implemented method of claim 1 , further comprising:

determining a third location associated with a third image, based at least in part on metadata of the third image, wherein determining the parameter value is further based on the third location.

5. The computer-implemented method of claim 1 , further comprising:

inserting the parameter value into the parameterized template.

6. The computer-implemented method of claim 1 , further comprising:

determining a first timestamp associated with the first image;

determining a second timestamp associated with the second image;

calculating a time period that encompasses the first timestamp and the second timestamp; and

inserting the time period into the parameterized template.

7. A computer-implemented method comprising:

recognizing a first object in a first image to determine a first content data that identifies the first object, wherein recognizing the first object comprises recognizing a first face and wherein the first content data corresponds to a first name associated with the first face;

recognizing a second object in a second image to determine a second content data that identifies the second object, wherein recognizing the second object comprises recognizing a second face and wherein the second content data corresponds to a second name associated with the second face;

determining a parameter value based at least in part on the first content data and the second content data, wherein the determining comprises aggregating the first name and the second name into a list; and

generating a narrative description according to a parameterized template, wherein the narrative description includes the parameter value.

8. The computer-implemented method of claim 7 , further comprising inserting the parameter value into the parameterized template.

9. The computer-implemented method of claim 7 , further comprising:

determining a first timestamp associated with the first image;

determining a second timestamp associated with the second image;

calculating a time period that encompasses the first timestamp and the second timestamp; and

inserting the time period into the parameterized template.

10. A non-transitory computer-readable medium with instructions stored thereon that, when executed by a processor, cause the processor to perform operations comprising:

recognizing a first object in a first image to determine a first content data that identifies the first object, wherein recognizing the first object comprises recognizing a first landmark;

recognizing a second object in a second image to determine a second content data that identifies the second object, wherein recognizing the second object comprises recognizing a second landmark;

determining a parameter value based at least in part on the first content data and the second content data, wherein determining the parameter value comprises identifying a first location of the first landmark and a second location of the second landmark; and

generating a narrative description according to a parameterized template, wherein the narrative description includes the parameter value.

11. The non-transitory computer-readable medium of claim 10 , wherein determining the parameter value further comprises determining a region that encompasses the first location and the second location based on a hierarchy of regions.

12. The non-transitory computer-readable medium of claim 11 , wherein the region is the smallest region in the hierarchy of regions that encompasses the first location and the second location.

13. The non-transitory computer-readable medium of claim 10 , with further instructions stored thereon that cause the processor to perform operations comprising determining a third location associated with a third image, based at least in part on metadata of the third image, wherein determining the parameter value is further based on the third location.

14. The non-transitory computer-readable medium of claim 10 , with further instructions stored thereon that cause the processor to perform operations comprising inserting the parameter value into the parameterized template.

15. The non-transitory computer-readable medium of claim 10 , with further instructions stored thereon that cause the processor to perform operations comprising:

determining a first timestamp associated with the first image;

determining a second timestamp associated with the second image;

calculating a time period that encompasses the first timestamp and the second timestamp; and

inserting the time period into the parameterized template.