Abstract: A computer-implemented method of training a convolutional neural network configured to morph content features of an input image with style features of a style image is provided. The computer-implemented method includes selecting a training style image; extracting style features of the training style image; selecting a training content image; extracting content features of the training content image; processing the training content image through the convolutional neural network to generate a training output image including the content features of the training content image morphed with the style features of the training style image; extracting content features and style features of the training output image; computing a total loss; and tuning the convolutional neural network based on the total loss including a content loss, a style loss, and a regularization loss.

Abstract: An image processing method and device, and a computer-readable storage medium are disclosed. The method includes: performing a channel expansion process on the input image to obtain a first intermediate image; performing a channel decomposition process for multiple times based on the first intermediate image, wherein each time of channel decomposition process includes: decomposing an image to be processed into a first decomposition image and a second decomposition image; concatenating first decomposition images generated in each time of channel decomposition process and second decomposition image generated in the last time of channel decomposition process to obtain a concatenated image; performing a post-processing process on the concatenated image to obtain a second intermediate image; and fusing the second intermediate image with the input image to obtain the first output image.

Abstract: A user equipment (UE) includes a first subscriber identification module (SIM) and a second SIM. The UE is configured to establish a first cellular network connection based on, at least, the first SIM and a second cellular network connection based on, at least, the second SIM. The UE detects a collision between i) multiple paging occasions or ii) multiple paging frames. The UE then initiates a procedure for updating a paging occasion for the first cellular network connection. The UE monitors for a page over the first cellular network connection during the paging occasion.

Abstract: The present disclosure provides an image processing method, an image processing device, and a display device. The image processing method includes: acquiring image data including display data of all of pixels of an image; and performing, on the display data of each of the pixels, operations of: determining Euclidean distances from the display data of the pixel to the display data of a first pure color, the display data of a second pure color, and the display data of a third pure color in a set color space; and replacing the display data of the pixel with one of the display data of the first pure color, the display data of the second pure color and the display data of the third pure color according to the determined Euclidean distances and a preset rule.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for payment services are provided.

Abstract: An expression recognition method is described that includes acquiring a face image to be recognized, and inputting the face image into N different recognition models arranged in sequence for expression recognition and outputting an actual expression recognition result, the N different recognition models being configured to recognize different target expression types, wherein N is an integer greater than 1.

Abstract: A method for processing an image is provided, including: acquiring an input image; performing down-sampling and feature extraction on the input image by an encoder network to obtain multiple feature maps; and performing up-sampling and feature extraction on the multiple feature maps by a decoder network to obtain a target segmentation image; processing levels between the encoder network and the decoder network for outputting feature maps with the same resolution are connected with each other, and the encoder network and the decoder network each includes one or more dense calculation blocks, and at least one convolution module in any dense computation block includes at least one group of asymmetric convolution kernels.

Abstract: This disclosure relates to techniques for performing wireless communications using a split bearer. A user equipment device may perform a recovery operation for a lost uplink packet. The recovery operation may be in response to an indication from the network or may be initiated autonomously by the device.

Abstract: A trash sorting and recycling method, a trash sorting device and a trash sorting and recycling system are provided. The trash sorting and recycling method includes: acquiring a detection image of trash to be sorted; processing the detection image with a deep learning neural network to judge whether or not the trash to be sorted belongs to recyclable trash; if yes, sending a first control signal, to control to deliver the trash to be sorted into a recycling region; if no, sending a second control signal, to control to deliver the trash to be sorted into a non-recycling region.

Abstract: Provided are a method for enhancing a video resolution enhancement, a computer readable storage medium, and an electronic device. The method includes: obtaining multiple image frames as input data, and obtaining initial data by performing feature extraction on the input data using a first three-dimensional convolutional layer; obtaining first feature data by performing down-sampling on the initial data at a preset multiple; obtaining first reference data by performing a convolution operation on the first feature data using a second three-dimensional convolutional layer to merge the first feature data as one frame; and obtaining first output data by performing up-sampling on the first reference data at the preset multiple.

Abstract: An image processing method is disclosed. The image processing method may include inputting a first image and a third image to a pre-trained style transfer network model, the third image being a composited image formed by the first image and a second image; extracting content features of the third image and style features of the second image, normalizing the content features of the third image based on the style features of the second image to obtain target image features, and generating a target image based on the target image features and outputting the target image by using the pre-trained style transfer network model.

Abstract: There is provided an image representation method, including: converting a to-be-converted image from a first color space to a second color space; acquiring a target conversion color ratio corresponding to each pixel of the to-be-converted image and including ratios of plural target conversion colors, according to a color ratio allocation table based on the second color space; creating an array corresponding to the pixel according to the target conversion color ratio; calculating an index value corresponding to the pixel according to a position of the pixel in the to-be-converted image, and inputting the index value to the array as a subscript of the array, to acquire an element of the array as a target value corresponding to the pixel; and determining a target conversion color of the pixel according to the target value, to acquire a converted image including the plural target conversion colors.

Abstract: The present disclosure relates to the field of information display, and specifically to a method, device, computer readable storage medium, and electronic device for video frame interpolation. The method comprises: obtaining, based on two input frames, two initial optical flow maps corresponding to the two input frames; optimizing the initial optical flow maps to obtain target optical flow maps; obtaining an interpolation frame kernel, two depth maps and two context feature maps based on the two input frames; obtaining an output frame using a frame synthesis method based on the target optical flow maps, the depth maps, the context feature maps, and the interpolation frame kernel.

Abstract: The present application discloses a color image processing method, a color image processing device, an electronic ink screen, and a storage medium. The color image processing method includes: obtaining an original image, and transforming original color data of a pixel in the original image into corresponding set color data in a set color space; determining a target color corresponding to the pixel in a plurality of set colors according to the set color data corresponding to the pixel and a color ratio allocation table; and generating a target image according to the target color.

Abstract: The present disclosure provides an image classification method, apparatus, and device, and a readable storage medium. The image classification method includes: processing an image to be processed, by using a first convolutional network, to obtain a first feature map; processing the first feature map, by using a residual network, to obtain a second feature map, wherein the residual network includes a depth separable convolutional layer; and processing the second feature map, by using a second convolutional network, to determine a category label of the image to be processed.

Abstract: An image processing method and apparatus, a device, a video processing method and a storage medium are provided. The image processing method includes: receiving an input image; and processing the input image by using the convolutional neural network to obtain an output image. A definition of the output image is higher than a definition of the input image. Processing the input image by using the convolutional neural network to obtain the output image includes: performing feature extraction on the input image; concatenating the input image and the plurality of first images; performing the feature extraction on the first image group; fusing the plurality of second images and the plurality of first images; concatenating the input image and the plurality of third images to obtain a second image group; and performing the feature extraction on the second image group to obtain the output image.

Abstract: A video frame interpolation method and device, and a computer-readable storage medium are described.

Abstract: A computer-implemented method is provided. The computer-implemented method includes inputting a low-resolution image into a generator, and generating a high-resolution image using the generator based on the low-resolution image. Generating the high-resolution image includes processing the low-resolution image through a plurality of super-resolution generating units arranged in series in the generator. A respective output from a respective one of the plurality of super-resolution generating units has a respective increased image resolution as compared to a respective input to the respective one of the plurality of super-resolution generating units.

Abstract: The present disclosure provides a semiconductor device and a fabrication method thereof. The semiconductor device includes a III-V material layer and a gate structure. The gate structure includes a first portion and a second portion on the first portion. The first portion is on the III-V material layer. The first portion has a first surface and a second surface opposite to the first surface and adjacent to the III-V material layer. A length of the second surface of the first portion of the gate structure is less than a length of the first surface of the first portion of the gate structure. A length of the second portion of the gate structure is less than the length of the first portion of the gate structure.

Abstract: The present disclosure discloses a method for generating a face image, an electronic device, and a non-transitory computer-readable storage medium, the method includes: receiving a first face image and target facial expression information, and determining first facial expression information corresponding to the first face image; selecting a first reference face image matched with the first facial expression information and a second reference face image matched with the target facial expression information from a face image library; respectively extracting feature points in the first reference face image and the second reference face image, and determining face deformation information between the first reference face image and the second reference face image based on the feature points; and extracting feature points in the first face image, and generating a second face image based on the face deformation information and the feature points in the first face image.