Systems and methods for compiled video generation

1. A computer-implemented method comprising:

receiving, by a computing system, one or more source video clips comprising one or more video segments;

performing, by the computing system, object recognition to identify objects depicted in the one or more source video clips using one or more machine learning techniques;

determining, by the computing system, whether the one or more source video clips includes a video segment depicting at least one of a landmark or a particular person;

identifying, by the computing system, a first theme based on the determination whether the one or more source video clips includes a video segment depicting at least one of a landmark or a particular person;

selecting, by the computing system, a plurality of video segments from the one or more source video clips, based on the first theme;

excluding, by the computing system, a first video segment from the plurality of video segments based on:

a determination that the first video segment should not be cropped when a video segment duration of the first video segment is longer than a specified video segment duration; and

generating, by the computing system, a compiled video comprising the plurality of video segments.

2. The computer-implemented method of claim 1 , wherein the first theme is an automatically determined theme based on video characteristics of the one or more source video clips.

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

identifying a second theme;

selecting a second plurality of video segments from the one or more source video clips based on the second theme; and

generating a second compiled video comprising the second plurality of video segments.

4. The computer-implemented method of claim 3 , further comprising presenting the compiled video and the second compiled video for selection by a user.

5. The computer-implemented method of claim 1 , wherein the plurality of video segments are selected based on at least one of object recognition or facial recognition performed using the one or more machine learning techniques.

6. The computer-implemented method of claim 1 , wherein the plurality of video segments are selected based on user characteristic information comprising at least one of an interest, a tendency, or a preference of a user as determined based on previous content postings of the user to a social networking system.

7. The computer-implemented method of claim 1 , further comprising performing video normalization of the plurality of video segments in the compiled video.

8. The method of claim 1 , wherein the first video segment comprises a speech longer than the specified video segment duration.

9. A system comprising:

at least one processor; and

a memory storing instructions that, when executed by the at least one processor, cause the system to perform a method comprising:

receiving one or more source video clips comprising one or more video segments;

performing object recognition to identify objects depicted in the one or more source video clips using one or more machine learning techniques;

determining whether the one or more source video clips includes a video segment depicting at least one of a landmark or a particular person;

identifying a first theme based on the determination whether the one or more source video clips includes a video segment depicting at least one of a landmark or a particular person;

selecting a plurality of video segments from the one or more source video clips;

based on the first theme;

excluding a first video segment from the plurality of video segments based on:

a determination that the first video segment should not be cropped when a video segment duration of the first video segment is longer than a specified video segment duration; and

generating a compiled video comprising the plurality of video segments.

10. The system of claim 9 , wherein the first theme is an automatically determined theme based on video characteristics of the one or more source video clips.

11. The system of claim 9 , wherein the instructions cause the system to further perform:

identifying a second theme;

selecting a second plurality of video segments from the one or more source video clips based on the second theme; and

generating a second compiled video comprising the second plurality of video segments.

12. The system of claim 11 , wherein the instructions cause the computing system to further perform presenting the compiled video and the second compiled video for selection by a user.

13. The system of claim 9 , wherein the plurality of video segments are selected based on user characteristic information comprising at least one of an interest, a tendency, or a preference of a user as determined based on previous content postings of the user to a social networking system.

14. The system of claim 9 , wherein the first video segment comprises a speech longer than the specified video segment duration.

15. A non-transitory computer-readable storage medium including instructions that, when executed by at least one processor of a computing system, cause the computing system to perform a method comprising:

receiving one or more source video clips comprising one or more video segments;

performing object recognition to identify objects depicted in the one or more source video clips using one or more machine learning techniques;

determining whether the one or more source video clips includes a video segment depicting at least one of a landmark or a particular person;

identifying a first theme based on the determination whether the one or more source video clips includes a video segment depicting at least one of a landmark or a particular person;

selecting a plurality of video segments from the one or more source video clips, based on the first theme;

excluding a first video segment from the plurality of video segments based on:

a determination that the first video segment should not be cropped when a video segment duration of the first video segment is longer than a specified video segment duration; and

generating a compiled video comprising the plurality of video segments.

16. The non-transitory computer-readable storage medium of claim 15 , wherein the first theme is an automatically determined theme based on video characteristics of the one or more source video clips.

17. The non-transitory computer-readable storage medium of claim 15 , wherein the method further comprises:

identifying a second theme;

selecting a second plurality of video segments from the one or more source video clips based on the second theme; and

generating a second compiled video comprising the second plurality of video segments.

18. The non-transitory computer-readable storage medium of claim 17 , wherein the method further comprises presenting the compiled video and the second compiled video for selection by a user.

19. The non-transitory computer-readable storage medium of claim 15 , wherein the plurality of video segments are selected based on user characteristic information comprising at least one of an interest, a tendency, or a preference of a user as determined based on previous content postings of the user to a social networking system.

20. The non-transitory computer-readable storage medium of claim 15 , wherein the first video segment comprises a speech longer than the specified video segment duration.