Systems and methods for automatically generating stitched media content

1. A computer-implemented method comprising:

identifying, by a computing system, a set of videos;

identifying, by the computing system, one or more overlapping portions in the set of videos, wherein the one or more overlapping portions are determined from at least overlapping audio portions;

generating, by the computing system, a directed acyclic graph based on the one or more overlapping portions determined from at least overlapping audio portions, wherein the directed acyclic graph comprises a plurality of nodes associated with the set of videos and sorted based on start times of the set of videos;

traversing, by the computing system, the directed acyclic graph based on the one or more overlapping portions determined from at least overlapping audio portions to identify a path of traversal resulting in a longest length for a stitched media content item, wherein the path of traversal comprises a set of nodes of the plurality of nodes, the set of nodes being associated with one or more videos from the set of videos; and

generating, by the computing system, the stitched media content item based on the path of traversal and at least a subset of the set of videos, wherein the stitched media content item comprises visual content from each video of the one or more videos.

2. The computer-implemented method of claim 1 , wherein

the directed acyclic graph further comprises a plurality of edges connecting the plurality of nodes, and

an edge of the plurality of edges is associated with an overlapping portion of the one or more overlapping portions.

3. The computer-implemented method of claim 2 , wherein a node of the plurality of nodes in the directed acyclic stores length information for its respective associated video, and an edge of the plurality of edges stores length information indicative of a length of an overlap between two connected nodes.

4. The computer-implemented method of claim 1 , wherein the identifying the one or more overlapping portions in the set of videos comprises identifying one or more overlapping audio portions in the set of videos.

5. The computer-implemented method of claim 1 , wherein the identifying the set of videos comprises identifying a set of related videos.

6. The computer-implemented method of claim 5 , wherein each video in the set of related videos is associated with a particular event.

7. The computer-implemented method of claim 6 , wherein the identifying the set of related videos further comprises querying a database for videos associated with the particular event.

8. The computer-implemented method of claim 1 , wherein each video of the set of videos is a video uploaded by a user to a social networking system.

9. A system comprising:

at least one processor; and

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

identifying a set of videos;

identifying one or more overlapping portions in the set of videos, wherein the one or more overlapping portions are determined from at least overlapping audio portions;

generating a directed acyclic graph based on the one or more overlapping portions determined from at least overlapping audio portions, wherein the directed acyclic graph comprises a plurality of nodes associated with the set of videos and sorted based on start times of the set of videos;

traversing the directed acyclic graph based on the one or more overlapping portions determined from at least overlapping audio portions to identify a path of traversal resulting in a longest length for a stitched media content item, wherein the path of traversal comprises a set of nodes of the plurality of nodes, the set of nodes being associated with one or more videos from the set of videos; and

generating the stitched media content item based on the path of traversal and at least a subset of the set of videos, wherein the stitched media content item comprises visual content from each video of the one or more videos.

10. The system of claim 9 , wherein

the directed acyclic graph further comprises a plurality of edges connecting the plurality of nodes, and

each edge of the plurality of edges is associated with an overlapping portion of the one or more overlapping portions.

11. The system of claim 10 , wherein a node of the plurality of nodes in the directed acyclic stores length information for its respective associated video, and an edge of the plurality of edges stores length information indicative of a length of an overlap between two connected nodes/videos.

12. The system of claim 9 , wherein the identifying the one or more overlapping portions in the set of videos comprises identifying one or more overlapping audio portions in the set of videos.

13. The system of claim 9 , wherein the identifying the set of videos comprises identifying a set of related videos.

14. The system of claim 13 , wherein each video in the set of related videos is associated with a particular event.

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:

identifying a set of videos;

identifying one or more overlapping portions in the set of videos, wherein the one or more overlapping portions are determined from at least overlapping audio portions;

generating a directed acyclic graph based on the one or more overlapping portions determined from at least overlapping audio portions, wherein the directed acyclic graph comprises a plurality of nodes associated with the set of videos and sorted based on start times of the set of videos;

traversing the directed acyclic graph based on the one or more overlapping portions determined from at least overlapping audio portions to identify a path of traversal resulting in a longest length for a stitched media content item, wherein the path of traversal comprises a set of nodes of the plurality of nodes, the set of nodes being associated with one or more videos from the set of videos; and

generating the stitched media content item based on the path of traversal and at least a subset of the set of videos, wherein the stitched media content item comprises visual content from each video of the one or more videos.

16. The non-transitory computer-readable storage medium of claim 15 , wherein

the directed acyclic graph further comprises a plurality of edges connecting the plurality of nodes, and

each edge of the plurality of edges is associated with an overlapping portion of the one or more overlapping portions.

17. The non-transitory computer-readable storage medium of claim 16 , wherein a node of the plurality of nodes in the directed acyclic stores length information for its respective associated video, and an edge of the plurality of edges stores length information indicative of a length of an overlap between two connected nodes/videos.

18. The non-transitory computer-readable storage medium of claim 15 , wherein the identifying the one or more overlapping portions in the set of videos comprises identifying one or more overlapping audio portions in the set of videos.

19. The non-transitory computer-readable storage medium of claim 15 , wherein the identifying the set of videos comprises identifying a set of related videos.

20. The non-transitory computer-readable storage medium of claim 19 , wherein each video in the set of related videos is associated with a particular event.