Abstract: Embodiments of this application provide a voice signal output method and an electronic device. The method includes: generating a first voice signal as an interfering signal based on a downlink voice signal; generating a second voice signal by performing delay processing on the downlink voice signal, where the second voice signal has a same delay as the first voice signal; and at a same output time, outputting the second voice signal using a first sound production assembly close to a human ear, and outputting the first voice signal using a second sound production assembly far from the human ear. This masks the downlink voice signal with the interfering signal, preventing others from clearly hearing the call content of the user and protecting user privacy.

Abstract: Provided in the embodiments of the present disclosure are a video generation method, and a training method for a video generation model. The video generation method includes: acquiring a first video, wherein the first video includes a first object image; and inputting the first video into a pre-trained video generation model to obtain a second video, wherein the video generation model is obtained by means of performing training on the basis of a target image and a plurality of sample image pairs obtained from a plurality of first sample images, an object image in the second video is generated on the basis of a preset animal image in the target image and the first object image, and a background image of the second video is generated on the basis of a first background image of the first video.

Abstract: The present disclosure relates to an information presentation method and apparatus, an electronic device and a storage medium. The method includes: presenting a target page, wherein the target page includes an object detail presentation area and a candidate object set presentation area, and the candidate object set presentation area is used for presenting first abstract information of each candidate object in a candidate object set; and in response to a selection operation for one piece of first abstract information in the candidate object set presentation area, presenting detail information of a first target object in the object detail presentation area, wherein the first target object is a candidate object corresponding to the selected first abstract information. Therefore, the operation steps of browsing the detail information of different objects can be simplified, and the operation time consumption can be shortened.

Abstract: Conventional email filtering services are not suitable for recognizing sophisticated malicious emails, and therefore may allow sophisticated malicious emails to reach inboxes by mistake. Introduced here are threat detection platforms designed to take an integrative approach to detecting security threats. For example, after receiving input indicative of an approval from an individual to access past email received by employees of an enterprise, a threat detection platform can download past emails to build a machine learning (ML) model that understands the norms of communication with internal contacts (e.g., other employees) and/or external contacts (e.g., vendors). By applying the ML model to incoming email, the threat detection platform can identify security threats in real time in a targeted manner.

Abstract: The present disclosure provides an image processing method and device. The image processing method includes: performing, by an encoder and a first model, multiple iterations on an initial image to obtain a target image feature corresponding to the initial image; and performing, by a second model, image reconstruction based on the target image feature to obtain a reconstructed image of the initial image, both of the first model and the second model being neural networks for image reconstruction, wherein in the multiple iterations, an image feature extracted by the first model in the image reconstruction and an output image of the first model are feedback information for the encoder to assist the encoder in encoding the initial image.

Abstract: The present disclosure provides an expression driving method and apparatus, and a training method and apparatus of an expression driving model. The expression driving method includes acquiring a first video; and inputting the first video into a pre-trained expression driving model to obtain a second video. The expression driving model is trained based on a target sample image and a plurality of first sample images. A facial image in the second video is generated based on the target sample image. A gesture expression feature of the facial image in the second video is the same as a gesture expression feature of a facial image in the first video.

Abstract: An image generation system is described. The system comprises a neural network model configured to perform a diffusion process to generate a set of multi-view images from a same input prompt. The set of multi-view images have a same subject from different view orientation. The neural network model comprises a self-attention layer configured to relate pixels across the set of multi-view images.

Abstract: The present disclosure provides a method of generating an image with metallic texture, and a method of training a metallic texture image generation model. The method of generating an image with metallic texture includes: acquiring a first video; and inputting the first video into a pre-trained metallic texture image generation model to obtain a second video. Each frame of images in the second video is an image with metallic texture. The metallic texture image generation model is trained based on a plurality of first sample images and second sample images with metallic texture corresponding to each first sample image.

Abstract: The present disclosure provides a video generation method and device. The video generation method includes: extracting a first image feature from a first image; obtaining a plurality of intermediate image features by means of nonlinear interpolation according to the first image feature and a second image feature, wherein the second image feature is an image feature of a second image; and performing image reconstruction by means of an image generation model based on the first image feature, the second image feature, and the plurality of intermediate image features, so as to generate a target video, wherein the target video is used for presenting a process of a gradual change from the first image to the second image.

Abstract: A target tracking method and device, relating to the field of vehicles. The method comprises: reading a target fusion list at the current moment, wherein the target fusion list comprises a target attribute set corresponding to each environment target in one or more environment targets, and the target attribute set comprises parameter attribute sets, measured by one or more sensors, of the environment targets; determining whether the target fusion list at the current moment is an initial target fusion list or not; and if the target fusion list at the current moment is not the initial target fusion list, determining a target tracking list at the current moment according to the target fusion list at the current moment and a stored target tracking list at the previous moment, wherein the target tracking list comprises a parameter attribute set corresponding to each screened environment target and a fusion tracking ID.

Abstract: A backlight module, a display module, and a display device are provided. The backlight module includes a light-emitting area including a first light-emitting area and a second light-emitting area. The second light-emitting area at least partially surrounds the first light-emitting area. The backlight module also includes a light-emitting structure including a plurality of light-emitting elements distributed in the light-emitting area, and a diffusion plate located on a side of a light exiting surface of the light-emitting structure and at least partially located in the light-emitting area. The backlight module also includes a reflection structure located on a surface of the diffusion plate facing the light-emitting structure. The reflection structure overlaps with the first light-emitting area.

Abstract: The present disclosure provides one or more engineered nucleases and systems, compositions, and methods thereof, wherein the one or more engineered nucleases can be used to effect binding, cleaving, and/or editing a target polynucleotide sequence. The one or more engineered nucleases can be engineered variants of a small CRISPR/Cas protein.

Abstract: Embodiments of this application provide a frequency response consistency calibration method and an electronic device, to solve a problem that when a screen sound production component of an electronic device plays a sound signal, a frequency response curve of the sound signal greatly fluctuates. The frequency response consistency calibration method includes: An electronic device plays a test audio signal. The electronic device stores a calibration parameter. The calibration parameter is a running parameter of an equalizer calibration module. The calibration parameter is determined based on a frequency response of a first audio signal and a standard frequency response of the test audio signal. The first audio signal is obtained by a calibration device by acquiring the test audio signal played by the electronic device. The calibration parameter is used to adjust a frequency response of the second audio signal played by the electronic device.

Abstract: Systems and methods are provided that include a processor executing a program to receive input text from a user. The processor is further configured to, for a predetermined number of iterations, input an initial image into a diffusion process to generate a processed image, back-propagate the processed image through a text-image match gradient calculator to calculate a gradient against the input text, and update the initial image with an image generated by applying the calculated gradient to the processed image. The pixel values of the processed image during a first portion of the predetermined number of iterations are value clamped to a first range, and pixel values of the processed image during a second portion of the predetermined number of iterations are value clamped to a second range that is a subset of the first range.

Abstract: Systems and methods are provided that include a processor executing a program to receive an input from a user, where the input including a first input text and a second input text. The processor is further configured to provide an initial image and, for a predetermined number of iterations, define a first and second regions of the initial image associated with the first and second input texts, respectively, define a plurality of patches of the initial image, input the initial image into a diffusion process to generate a processed image, back-propagate the processed image through a text-image match gradient calculator by generating an image embedding based on the processed image, generating a text embedding based on the region and the input text that are associated with a patch, and calculating a differential between the image embedding and the text embedding.

Abstract: A display module and a display device are disclosed. The display module includes a display panel and a back panel. The back panel includes a first sub-panel disposed on a backside of the display panel, and the first sub-panel includes a plurality of first regions spaced apart and a second region adjacent to the first regions, wherein a thickness of the first sub-panel in the first regions is greater than 0 and less than a thickness of the first sub-panel in the second region.

Abstract: Systems and methods are provided that include a processor executing a program to process an initial image through a first diffusion stage to generate a final first stage image, wherein the first diffusion stage includes using a diffusion model, a gradient estimator model smaller than the diffusion model, and a text-image match gradient calculator. The processor further executes the program to process the final first stage image through a second diffusion stage to generate a final second stage image. The second diffusion stage includes, for a second predetermined number of iterations, inputting the final first stage image to through the diffusion model, back-propagate the image through the text-image match gradient calculator to calculate a second stage gradient against the input text, and update the final first stage image by applying the second stage gradient to the final first stage image.

Abstract: An audio processing method is provided. The method includes: at a first time point, obtaining a first audio signal and a second audio signal, where the first audio signal is used to indicate information acquired by the first microphone, and the second audio signal is used to indicate information acquired by the second microphone; determining according to a correlation between the first audio signal and the second audio signal, that the first audio signal includes a first noise signal and that the second audio signal includes no first noise signal; and performing processing on the first audio signal to obtain a third audio signal, where the third audio signal includes no first noise signal.

Abstract: The present disclosure provides systems and methods for generating a synthesized image of a user with a trained machine learning diffusion model. In one example, a computing system includes one or more processors configured to execute instructions stored in memory to execute a trained machine learning diffusion model including an image encoder, a text encoder, and a diffusion model. The image encoder is configured to receive an image of a user and generate a set of embeddings that semantically describe visual features of the user based at least on the image of the user. The text encoder is configured to receive the set of embeddings and generate an input feature vector based at least on the set of embeddings. The diffusion model is configured to receive the input feature vector and generate a synthesized image of the user based at least on the input feature vector.