Systems and methods for generating content
Systems, methods, and non-transitory computer-readable media can receive a source content item. A crop window is automatically determined for the source content item based on framing criteria. A cropped media asset is automatically generated based on the source content item and the crop window. In certain embodiments, an object of interest is automatically identified in the source content item and the crop window is determined based on the object of interest.
1. A computer-implemented method comprising:
receiving, by a computing system, a source content item;
identifying, by the computing system, an object in the source content item;
determining, by the computing system, a crop window for the source content item based on framing criteria, wherein the framing criteria specify a plurality of changes to the crop window to feature the object within the crop window, and the plurality of changes includes a change to at least a size or a position of the crop window with respect to the source content item so that a location of the object within the crop window is unchanged; and
generating, by the computing system, a plurality of cropped media assets from the source content item based on the crop window;
ranking, by the computing system, the plurality of cropped media assets based on a likelihood of receiving a user interaction; and
based on the ranking, providing, by the computing system, at least one cropped media asset from the plurality of cropped media assets for publication.
2. The computer-implemented method of claim 1 , wherein the framing criteria specify one or more preferred positions for the object within the crop window.
3. The computer-implemented method of claim 2 , wherein at least a subset of the preferred positions is determined based on the Rule of Thirds.
4. The computer-implemented method of claim 1 , wherein the framing criteria specify an aspect ratio for the crop window.
5. The computer-implemented method of claim 4 , wherein the source content item has a widescreen aspect ratio.
6. The computer-implemented method of claim 5 , wherein the framing criteria specify a vertical aspect ratio for the crop window.
7. The computer-implemented method of claim 5 , wherein the framing criteria specify a square aspect ratio for the crop window.
8. The computer-implemented method of claim 1 , wherein the framing criteria are determined based on a machine learning model.
9. The computer-implemented method of claim 8 , wherein the machine learning model is trained to specify framing criteria based on a likelihood of receiving a user interaction, wherein the user interaction includes at least one of a number of likes, a number of comments, a number of shares, or a number of clicks a media content item receives.
10. 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 a source content item;
identifying an object in the source content item;
determining a crop window for the source content item based on framing criteria, wherein the framing criteria specify a plurality changes to the crop window to feature the object within the crop window, and the plurality of changes includes a change to at least a size or a position of the crop window with respect to the source content item so that a location of the object within the crop window is unchanged;
generating a plurality of cropped media assets from the source content item based on the crop window;
ranking the plurality of cropped media assets based on a likelihood of receiving a user interaction; and
based on the ranking, providing at least one cropped media asset from the plurality of cropped media assets for publication.
11. The system of claim 10 , wherein the framing criteria specify one or more preferred positions for the object within the crop window.
12. The system of claim 11 , wherein at least a subset of the preferred positions is determined based on the Rule of Thirds.
13. The system of claim 10 , wherein the framing criteria specify an aspect ratio for the crop window.
14. The system of claim 13 , wherein the source content item has a widescreen aspect ratio.
15. The system of claim 14 , wherein the framing criteria specify a vertical aspect ratio for the crop window.
16. The system of claim 14 , wherein the framing criteria specify a square aspect ratio for the crop window.
17. 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 a source content item;
identifying an object in the source content item;
determining a crop window for the source content item based on framing criteria, wherein the framing criteria specify a plurality of changes to the crop window to feature the object within the crop window, and the plurality of changes includes a change to at least a size or a position of the crop window with respect to the source content item so that a location of the object within the crop window is unchanged;
generating a plurality of cropped media assets from the source content item based on the crop window;
ranking the plurality of cropped media assets based on a likelihood of receiving a user interaction; and
based on the ranking, providing at least one cropped media asset from the plurality of cropped media assets for publication.
18. The non-transitory computer-readable storage medium of claim 17 , wherein the framing criteria specify one or more preferred positions for the object within the crop window.
19. The non-transitory computer-readable storage medium of claim 18 , wherein at least a subset of the preferred positions is determined based on the Rule of Thirds.
20. The non-transitory computer-readable storage medium of claim 17 , wherein the framing criteria specify an aspect ratio for the crop window.