Abstract: A method for generating a pre-trained language model, includes: obtaining sample files; obtaining typography structure information and text information of the sample files by parsing the sample files; obtaining a plurality of task models of a pre-trained language model; obtaining a trained pre-trained language model by jointly training the pre-trained language model and the plurality of task models according to the typography structure information and the text information; and generating a target pre-trained language model by fine-tuning the trained pre-trained language model according to the typography structure information and the text information.

Abstract: A method includes receiving a plurality of depth values corresponding to a plurality of areas depicted in an image captured by an image sensor. The method also includes generating a depth histogram categorizing each depth value of the plurality of depth values into a depth value range of a plurality of depth value ranges. The method further includes determining an autofocus distance based on the depth histogram. The method additionally includes causing the image sensor to capture an image based on the autofocus distance.

Abstract: A method for generating a pre-trained language model, includes: obtaining sample files; obtaining typography structure information and text information of the sample files by parsing the sample files; obtaining a plurality of task models of a pre-trained language model; obtaining a trained pre-trained language model by jointly training the pre-trained language model and the plurality of task models according to the typography structure information and the text information; and generating a target pre-trained language model by fine-tuning the trained pre-trained language model according to the typography structure information and the text information.

Abstract: Example implementations relate to halftone image creation. An example non-transitory machine-readable medium can include instructions executable to determine a highlight core shape and a shadow core shape of a microcell within a supercell. The instructions can be executable to determine growth sequences for a plurality of pixels within the highlight core and the shadow core and between the microcell and other microcells within the supercell, divide each of the plurality of pixels into a plurality of subpixels, and create a halftone image for an unequal resolution printing device using a constrained direct binary search model and based on the highlight core shape, shadow core shape, growth sequences, and the plurality of subpixels.

Abstract: Example implementations relate to halftone image creation. An example non-transitory machine-readable medium can include instructions executable to determine a highlight core shape and a shadow core shape of a microcell within a supercell. The instructions can be executable to determine growth sequences for a plurality of pixels within the highlight core and the shadow core and between the microcell and other microcells within the supercell, divide each of the plurality of pixels into a plurality of subpixels, and create a halftone image for an unequal resolution printing device using a constrained direct binary search model and based on the highlight core shape, shadow core shape, growth sequences, and the plurality of subpixels.