| CPC G06F 3/04845 (2013.01) [G06F 3/0485 (2013.01)] | 20 Claims |
|
1. A computing system for providing one or more content items for display, the computing system comprising:
one or more processors; and
one or more non-transitory computer-readable media that collectively store instructions that, when executed by the one or more processors, cause the computing system to perform operations, the operations comprising:
providing for display a user interface, wherein the user interface comprises a content item provided for display in a display container, wherein the display container is a first size, wherein the content item is displayed with a first masking level based on the first size;
obtaining a first input, wherein the first input is descriptive of a navigation input to scroll through the user interface, wherein the navigation input moves the display container from a first position to a second position;
processing the first content item with a first machine-learned model to generate one or more object detection outputs:
processing the one or more object detection outputs with a second machine-learned model to generate a focal point classification descriptive of a foreground object being determined;
determining a portion of the first content item to provide for display and a portion to mask based on the focal point classification; and
providing for display an updated user interface, wherein the updated user interface comprises the content item provided for display in an updated display container of a second size, wherein the second size is smaller than the first size, wherein the content item is displayed with a second masking level based on the second size, wherein the second masking level masks a larger portion of the content item than the first masking level, and wherein the foreground object of the first content item continues to be provided for display as the first container decreases in size based on the focal point classification.
|