Back to results
US 2019/0200083 A1Published application
Systems and methods for presenting content
AssigneeFacebook, Inc.
InventorDavid Young Joon Pio
Life of this patent
Estimating the term…
Abstract
Systems, methods, and non-transitory computer-readable media can determine a request for a content item from a computing device. One or more view directions of a user operating the computing device can be predicted during playback of the content item. One or more frames of the content item are quantized based at least in part on the predicted view directions.
Claims20
A computer-implemented method comprising:
- determining, by a computing system, a request for a content item;
- predicting, by the computing system, one or more view directions during playback of the content item;
- and
- quantizing, by the computing system, one or more frames of the content item based at least in part on the predicted view directions, wherein the quantizing comprises providing frame blocks, corresponding to the predicted view directions, that appear at a higher video quality than content outside of the predicted view directions, the view directions being predicted based at least in part on a saliency prediction model.
1 more element
(canceled)
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 a request for a content item;
- predicting one or more view directions during playback of the content item;
- and
- quantizing one or more frames of the content item based at least in part on the predicted view directions, wherein the quantizing comprises providing frame blocks, corresponding to the predicted view directions, that appear at a higher video quality than content outside of the predicted view directions, the view directions being predicted based at least in part on a saliency prediction model.
4 more elements
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 a request for a content item;
- predicting one or more view directions during playback of the content item;
- and
- quantizing one or more frames of the content item based at least in part on the predicted view directions, wherein the quantizing comprises providing frame blocks, corresponding to the predicted view directions, that appear at a higher video quality than content outside of the predicted view directions, the view directions being predicted based at least in part on a saliency prediction model.
1 more element
Dependencies are inferred from the claim text.