Systems and methods for automatically generating stitched media content

Abstract

Systems, methods, and non-transitory computer-readable media can identify a set of videos. One or more overlapping portions in the set of videos are automatically identified. A stitched media content item is automatically generated based on the one or more overlapping portions and at least a subset of the set of videos.

What is claimed is: 
     
         1 . A computer-implemented method comprising:
 identifying, by a computing system, overlapping audio portions in a set of videos;   generating, by the computing system, a graph comprising a plurality of nodes associated with the set of videos, one or more nodes indicating that associated videos were uploaded by followers of a user;   traversing, by the computing system, the graph along a path of traversal that maximizes a number of nodes indicating that associated videos were uploaded by the followers; and   generating, by the computing system, a stitched media content item for the user based on the path of traversal.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein a node stores follower information of the user. 
     
     
         3 . The computer-implemented method of  claim 1 , wherein the graph is generated based on the overlapping audio portions. 
     
     
         4 . The computer-implemented method of  claim 1 , wherein the plurality of nodes are sorted based on start times of the set of videos. 
     
     
         5 . The computer-implemented method of  claim 1 , wherein the graph is a directed acyclic graph. 
     
     
         6 . The computer-implemented method of  claim 1 , wherein the graph further comprises a plurality of edges connecting the plurality of nodes, an edge of the plurality of edges associated with an overlapping audio portion of two videos. 
     
     
         7 . The computer-implemented method of  claim 1 , wherein the set of videos is associated with a particular event. 
     
     
         8 . The computer-implemented method of  claim 1 , wherein the traversing is based on generation of the stitched media content item that has a maximum time duration. 
     
     
         9 . The computer-implemented method of  claim 1 , wherein the traversing is based on generation of the stitched media content item such that each video does not exceed a clip length threshold. 
     
     
         10 . The computer-implemented method of  claim 1 , wherein the traversing is based on generation of the stitched media content item that has a maximum number of videos. 
     
     
         11 . 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 overlapping audio portions in a set of videos;   generating a graph comprising a plurality of nodes associated with the set of videos, one or more nodes indicating that associated videos were uploaded by followers of a user;   traversing the graph along a path of traversal that maximizes a number of nodes indicating that associated videos were uploaded by the followers; and   generating a stitched media content item for the user based on the path of traversal.   
     
     
         12 . The system of  claim 11 , wherein a node stores follower information of the user. 
     
     
         13 . The system of  claim 11 , wherein the graph further comprises a plurality of edges connecting the plurality of nodes, an edge of the plurality of edges associated with an overlapping audio portion of two videos. 
     
     
         14 . The system of  claim 11 , wherein the traversing is based on generation of the stitched media content item that has a maximum time duration. 
     
     
         15 . The system of  claim 11 , wherein the traversing is based on generation of the stitched media content item that has a maximum number of videos. 
     
     
         16 . 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 overlapping audio portions in a set of videos;   generating a graph comprising a plurality of nodes associated with the set of videos, one or more nodes indicating that associated videos were uploaded by followers of a user;   traversing the graph along a path of traversal that maximizes a number of nodes indicating that associated videos were uploaded by the followers; and   generating a stitched media content item for the user based on the path of traversal.   
     
     
         17 . The non-transitory computer-readable storage medium of  claim 16 , wherein a node stores follower information of the user. 
     
     
         18 . The non-transitory computer-readable storage medium of  claim 16 , wherein the graph further comprises a plurality of edges connecting the plurality of nodes, an edge of the plurality of edges associated with an overlapping audio portion of two videos. 
     
     
         19 . The non-transitory computer-readable storage medium of  claim 16 , wherein the traversing is based on generation of the stitched media content item that has a maximum time duration. 
     
     
         20 . The non-transitory computer-readable storage medium of  claim 16 , wherein the traversing is based on generation of the stitched media content item that has a maximum number of videos.