Systems and methods for presenting content

1. A computer-implemented method comprising:

determining, by a computing system, saliency information describing one or more salient points of interest that appear during presentation of a content item, wherein the salient points of interest are predicted to be of interest to one or more users accessing the content item; and

embedding, by the computing system, the saliency information describing the salient points of interest into the content item, wherein the saliency information is capable of being processed during presentation of the content item to enhance the presentation of the content item, wherein the embedding further comprises:

inserting, by the computing system, a respective portion of the saliency information into at least one of the frames of the content item, wherein the respective portion of the saliency information is inserted in a region within the at least one frame that is predicted as being unlikely to be viewed by the one or more users.

2. The computer-implemented method of claim 1 , wherein the portion of the saliency information inserted in a frame provides information describing one or more salient points of interest that appear in the frame.

3. The computer-implemented method of claim 2 , wherein the information describing the salient points of interest that appear in the frame includes respective pixel coordinates for each of the salient points of interest.

4. The computer-implemented method of claim 2 , wherein the information describing the salient points of interest that appear in the frame includes respective locations of the salient points of interest that appear in the frame and corresponding filters to be applied to the salient points of interest, wherein a filter augments the appearance of a salient point of interest during presentation of the content item.

5. The computer-implemented method of claim 2 , wherein the information describing the salient points of interest that appear in the frame describes respective regions in the frame that correspond to each of the salient points of interest, wherein a region corresponding to a salient point of interest is defined using at least a set of pixel coordinates and a radius that originates from the pixel coordinates.

6. The computer-implemented method of claim 1 , wherein the portion of the saliency information inserted into a frame provides information describing a view direction corresponding to the frame.

7. The computer-implemented method of claim 1 , wherein the saliency information for a frame is inserted into a non-visible expansion region of the frame.

8. The computer-implemented method of claim 1 , wherein embedding the saliency information describing the salient points of interest into the content item further comprises:

inserting, by the computing system, one or more color sequences in the frame, wherein each color sequence is capable of being translated to determine the saliency information.

9. The computer-implemented method of claim 1 , wherein determining information describing one or more salient points of interest that appear during presentation of the content item further comprises:

obtaining, by the computing system, information describing the salient points of interest from a saliency prediction model that is trained to predict salient points of interest that appear during presentation of content items.

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:

determining saliency information describing one or more salient points of interest that appear during presentation of a content item, wherein the salient points of interest are predicted to be of interest to one or more users accessing the content item; and

embedding the saliency information describing the salient points of interest into the content item, wherein the saliency information is capable of being processed during presentation of the content item to enhance the presentation of the content item, wherein the embedding further comprises:

inserting a respective portion of the saliency information into at least some of the frames of the content item, wherein the respective portion of the saliency information is inserted in a region within the at least one frame that is predicted as being unlikely to be viewed by the one or more users.

11. The system of claim 10 , wherein the portion of the saliency information inserted in a frame provides information describing one or more salient points of interest that appear in the frame.

12. The system of claim 11 , wherein the information describing the salient points of interest that appear in the frame includes respective pixel coordinates for each of the salient points of interest.

13. The system of claim 11 , wherein the information describing the salient points of interest that appear in the frame includes respective locations of the salient points of interest that appear in the frame and corresponding filters to be applied to the salient points of interest, wherein a filter augments the appearance of a salient point of interest during presentation of the content item.

14. 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:

determining saliency information describing one or more salient points of interest that appear during presentation of a content item, wherein the salient points of interest are predicted to be of interest to one or more users accessing the content item; and

embedding the saliency information describing the salient points of interest into the content item, wherein the saliency information is capable of being processed during presentation of the content item to enhance the presentation of the content item, wherein the embedding further comprises:

inserting a respective portion of the saliency information into at least some of the frames of the content item, wherein the respective portion of the saliency information is inserted in a region within the at least one frame that is predicted as being unlikely to be viewed by the one or more users.

15. The non-transitory computer-readable storage medium of claim 14 , wherein the portion of the saliency information inserted in a frame provides information describing one or more salient points of interest that appear in the frame.

16. The non-transitory computer-readable storage medium of claim 15 , wherein the information describing the salient points of interest that appear in the frame includes respective pixel coordinates for each of the salient points of interest.

17. The non-transitory computer-readable storage medium of claim 15 , wherein the information describing the salient points of interest that appear in the frame includes respective locations of the salient points of interest that appear in the frame and corresponding filters to be applied to the salient points of interest, wherein a filter augments the appearance of a salient point of interest during presentation of the content item.