Abstract: A display panel includes a pixel circuit. An operation process of the pixel circuit includes a first data refresh period, a data adjustment stage, and a second data refresh period set in sequence, the data adjustment stage includes a first data adjustment stage. The first data adjustment stage includes T1 first sub-data adjustment stages set in sequence, each first sub-data adjustment stage includes m1 data writing frames and n1 holding frames. The operation process of the pixel circuit further includes a first data refresh frequency F21 and a second data refresh frequency F22, and F21<F22. When the pixel circuit is operated at the first data refresh frequency F21, the first data adjustment stage includes T11 first sub-data adjustment stages set in sequence. When the pixel circuit is operated at the second data refresh frequency F22, the first data adjustment stage includes T21 first sub-data adjustment stages set in sequence. T11>T21.

Abstract: Method for source localization for cable cut prevention using distributed fiber optic sensing (DFOS)/distributed acoustic sensing (DAS) is described that is robust/immune to underground propagation speed uncertainty. The method estimates the location of a vibration source while considering any uncertainty of vibration propagation speed and formulates the localization as an optimization problem, and both location of the sources and the propagation speed are treated as unknown. This advantageously enables our method to adapt to variances of the velocity and produce a better generalized performance with respect to environmental changes experienced in the field. Our method operates using a DFOS system and AI techniques as an integrated solution for vibration source localization along an entire optical sensor fiber cable route and process real-time DFOS data and extract features that are related to a location of a source of vibrations that may threaten optical fiber facilities.

Abstract: A display panel includes a pixel circuit. An operation process of the pixel circuit includes a first data refresh period, a data adjustment stage, and a second data refresh period set in sequence, the data adjustment stage includes a first data adjustment stage, a second data adjustment stage, and a third data adjustment stage set in sequence. The first data adjustment stage includes T1 first sub-data adjustment stages set in sequence, each first sub-data adjustment stage includes m1 data writing frames and n1 holding frames. The second data adjustment stage includes T2 second sub-data adjustment stages set in sequence, each second sub-data adjustment stage includes m2 data writing frames and n2 holding frames. The third data adjustment stage includes T3 third sub-data adjustment stages set in sequence, each third sub-data adjustment stage includes m3 data writing frames and n3 holding stages set in sequence.

Abstract: A display panel and a display device are provided. The display panel includes a pixel circuit. An operation process of the pixel circuit includes a first data refresh period, a data adjustment stage, and a second data refresh period set in sequence, the data adjustment stage includes a first data adjustment stage and a second data adjustment stage set in sequence. The first data adjustment stage includes T1 first sub-data adjustment stages set in sequence, each first sub-data adjustment stage includes m1 data writing frames and n1 holding frames, T1?1, m1?0, n1?0, and m1+n1?1. The second data adjustment stage includes T2 second sub-data adjustment stages set in sequence, each second sub-data adjustment stage includes m2 data writing frames and n2 holding frames, T2?1, m2?0, n2?0, and m2+n2?1. T1>T2, T1/T2=(m2+n2)/(m1+n1).

Abstract: A display panel includes a pixel circuit and a light-emitting element. The working process of the pixel circuit includes a data write stage and a bias stage. The working process of the pixel circuit includes a first light emission stage and a first non-light emission stage. In the first non-light emission stage, a bias maintaining stage is from the start moment of the bias stage to the start moment of the first light emission stage. Working modes of the display panel include a first mode and a second mode. The display brightness of the display panel in the first mode is different from the display brightness of the display panel in the second mode. The length of the bias maintaining stage in the first mode is different from the length of the bias maintaining stage in the second mode.

Abstract: This disclosure describes methods, non-transitory computer readable storage media, and systems that generate synthetized digital images using class-specific generators for objects of different classes. The disclosed system modifies a synthesized digital image by utilizing a plurality of class-specific generator neural networks to generate a plurality of synthesized objects according to object classes identified in the synthesized digital image. The disclosed system determines object classes in the synthesized digital image such as via a semantic label map corresponding to the synthesized digital image. The disclosed system selects class-specific generator neural networks corresponding to the classes of objects in the synthesized digital image. The disclosed system also generates a plurality of synthesized objects utilizing the class-specific generator neural networks based on contextual data associated with the identified objects.

Abstract: An image inpainting system is described that receives an input image that includes a masked region. From the input image, the image inpainting system generates a synthesized image that depicts an object in the masked region by selecting a first code that represents a known factor characterizing a visual appearance of the object and a second code that represents an unknown factor characterizing the visual appearance of the object apart from the known factor in latent space. The input image, the first code, and the second code are provided as input to a generative adversarial network that is trained to generate the synthesized image using contrastive losses. Different synthesized images are generated from the same input image using different combinations of first and second codes, and the synthesized images are output for display.

Abstract: This disclosure describes methods, non-transitory computer readable storage media, and systems that generate synthetized digital images via multi-resolution generator neural networks. The disclosed system extracts multi-resolution features from a scene representation to condition a spatial feature tensor and a latent code to modulate an output of a generator neural network. For example, the disclosed systems utilizes a base encoder of the generator neural network to generate a feature set from a semantic label map of a scene. The disclosed system then utilizes a bottom-up encoder to extract multi-resolution features and generate a latent code from the feature set. Furthermore, the disclosed system determines a spatial feature tensor by utilizing a top-down encoder to up-sample and aggregate the multi-resolution features. The disclosed system then utilizes a decoder to generate a synthesized digital image based on the spatial feature tensor and the latent code.

Abstract: This disclosure describes methods, non-transitory computer readable storage media, and systems that generate synthetized digital images via multi-resolution generator neural networks. The disclosed system extracts multi-resolution features from a scene representation to condition a spatial feature tensor and a latent code to modulate an output of a generator neural network. For example, the disclosed systems utilizes a base encoder of the generator neural network to generate a feature set from a semantic label map of a scene. The disclosed system then utilizes a bottom-up encoder to extract multi-resolution features and generate a latent code from the feature set. Furthermore, the disclosed system determines a spatial feature tensor by utilizing a top-down encoder to up-sample and aggregate the multi-resolution features. The disclosed system then utilizes a decoder to generate a synthesized digital image based on the spatial feature tensor and the latent code.

Abstract: This disclosure describes methods, non-transitory computer readable storage media, and systems that generate synthetized digital images using class-specific generators for objects of different classes. The disclosed system modifies a synthesized digital image by utilizing a plurality of class-specific generator neural networks to generate a plurality of synthesized objects according to object classes identified in the synthesized digital image. The disclosed system determines object classes in the synthesized digital image such as via a semantic label map corresponding to the synthesized digital image. The disclosed system selects class-specific generator neural networks corresponding to the classes of objects in the synthesized digital image. The disclosed system also generates a plurality of synthesized objects utilizing the class-specific generator neural networks based on contextual data associated with the identified objects.