Abstract: The mask includes a first surface and a second surface that are arranged opposite to each other. The first surface includes a plurality of first grooves, the second surface includes a plurality of second grooves, the plurality of second grooves and the plurality of first grooves are in a one-to-one correspondence, and each second groove and a respective first groove corresponding to the each second groove penetrate the mask. On the second surface, the distance between adjacent second grooves is greater than a preset distance, where the preset distance is greater than zero.

Abstract: A vehicle control method and a vehicle. The method includes: obtaining running states of a plurality of control chips; when the running state of a first control chip in the plurality of control chips indicates that any of set events occurs in the first control chip, sending, to a second control chip among the plurality of control chips, a configuration instruction of running first application software, wherein the first application software is an application module currently run by the first control chip.

Abstract: An image segmentation apparatus according to an embodiment of the present disclosure includes processing circuitry. The processing circuitry is configured to obtain a massive region to which labeling information is attached and a tubular region to which labeling information is attached. By using the labeling information of the massive region and the labeling information of the tubular region, the processing circuitry is configured to generate a region to be segmented and a non-boundary region, by carrying out a distance transformation. The processing circuitry is configured to generate a classifier for classifying spatial coordinates, by using the labeling information of the non-boundary region and labeling information in a specific position determined on the basis of the region to be segmented and the tubular region. The processing circuitry is configured to segment voxels in the region to be segmented by using the classifier and to thus determine a final segmentation result.

Abstract: A display panel includes a display area and a non-display area; the display area includes multiple first sub-pixel minimum repeating units; the multiple first sub-pixel minimum repeating units are sequentially and periodically arranged in a first direction, and in the first direction, a center distance between any two adjacent ones of the multiple first sub-pixel minimum repeating units is d1; the non-display area includes a first offset mark A1 and a second offset mark A2 arranged in the first direction; a center distance L1 between the first offset mark A1 and the second offset mark A2 is an integral multiple of the center distance d1 between the first sub-pixel minimum repeating units.

Abstract: Embodiments of the present disclosure provide an audio processing method and apparatus, an electronic device and a storage medium, wherein the method comprises: obtaining first music data and a processing instruction in text form associated with the first music data; extracting, by a music processing model, a first chord progression feature and an audio feature of the first music data, and a text feature of the processing instruction; processing, by the music processing model, the audio feature in accordance with the first chord progression feature and the text feature, to generate second music data; wherein a similarity between a first chord progression feature of the first music data and a second chord progression feature of the second music data is greater than a similarity threshold.

Abstract: The present application discloses a display panel. The display panel comprises a display region, a hole region, and a transition region located between the display region and the hole region. The display panel further comprises a substrate; a pixel defining layer located on a side of the substrate, the pixel defining layer comprising at least one pixel defining portion and a pixel opening enclosed by the pixel defining portion; a light-emitting layer comprising at least one light-emitting unit located within the pixel opening; and an inorganic encapsulation layer located on a side of the light-emitting unit facing away from the substrate. The inorganic encapsulation layer comprises a first hole configured to avoid cutting damage.

Abstract: A display panel and a display apparatus are described. In an embodiment, the display panel includes a display area and a bezel area; a first support structure located in the display area, the first support structure including a plurality of first support portions; an encapsulation adhesive located in the bezel area; a second support structure located in the bezel area. In an embodiment, at different positions of the bezel area, the second support structure and the encapsulation adhesive are at an equal distance from each other within a preset error range; the second support structure includes at least one second support portion; and in a direction perpendicular to a plane in which the display panel is located, at least some of the second support portions each has orthographic projection area larger than orthographic projection area of the first support portion.

Abstract: A mask strip and a mask device are provided. The mask strip includes a body part, the body part includes two connecting ends arranged in a first direction, the body part further includes at least two evaporation region sets, the evaporation region sets are located between the two connecting ends, each of the evaporation region sets includes at least one evaporation region, each of the evaporation regions includes a plurality of evaporation openings, a number density of the evaporation openings within each of the evaporation regions is a predetermined density, and the predetermined density within any one of the evaporation regions of the evaporation region sets located adjacent to a middle position of the mask strip in the first direction is larger than the predetermined density of any one of the evaporation regions of the evaporation region sets located away from the middle position.

Abstract: The present application relates to an array substrate (1) and a liquid crystal display panel.

Abstract: Systems and techniques are provided for generating disparity information from two or more images. For example, a process can include obtaining first disparity information corresponding to a pair of images, the pair of images including a first image of a scene and a second image of the scene. The process can include obtaining confidence information associated with the first disparity information. The process can include processing, using a machine learning network, the first disparity information and the confidence information to generate second disparity information corresponding to the pair of images. The process can include combining, based on the confidence information, the first disparity information with the second disparity information to generate a refined disparity map corresponding to the pair of images.

Abstract: Systems and techniques are provided for conserving resources when performing motion estimation. An example process can include determining, based on an input image and a reference image, motion vectors identifying motion between the input image and the reference image; determining whether the motion indicated by the motion vectors is below a first threshold; based on a determination that the motion indicated by the motion vectors is below the first threshold, refraining from determining a local motion between the input image and the reference image; determining a transform matrix based on the motion vectors and without using a local motion between the input image and the reference image; and adjusting the input image based on the transform matrix.

Abstract: The present invention proposes an ensemble deep learning method for identifying unsafe behaviors of operators in maritime working environment. Firstly, extract features of maritime images with the You Only Look Once (YOLO) V3 model, and then enhance a multi-scale detection capability by introducing a feature pyramid structure. Secondly, obtain instance-level features and time memory features of the operators and devices in the maritime working environment with the Joint Learning of Detection and Embedding (JDE) paradigm. Thirdly, transfer spatial-temporal interaction information into a feature memory pool, and update the time memory features with the asynchronous memory updating algorithm. Finally, identify the interaction between the operators, the devices, and unsafe behaviors with an asynchronous interaction aggregation network. The proposed invention can accurately determine the unsafe behaviors of the operators, and thus provide operation decisions for maritime management relevant activities.

Abstract: The application relates to an efficient particle filter node positioning method for ocean sensor networks, including the following steps: 1) obtaining a first state vector of mean value of posterior probability at k?1 moment; 2) establishing the state model of the nonlinear system; 3) obtaining the observation model of the nonlinear system; 4) propagating particles, and calculating the state vector ?+k at the next moment according to the particle vector at k?1 moment; 5) obtaining the observed value and calculating the weight; 6) judging whether it is degraded, if not, the weight is used to calculate the position expectation, otherwise, 7) is executed; 7) modifying small-weight particles; 8) resampling the improved residual and normalizing the weights; and 9) using the weight of 8) to calculate the position expectation and realize node positioning.

Abstract: A medical image processing method according to an embodiment of the present disclosure includes: training a deep neural network by using labeled image data; obtaining a first augmented image by carrying out a weak data augmentation on unlabeled image data; performing a predicting process on the first augmented image by using the deep neural network and determining whether each of the pixels in the first augmented image is able to serve as a pseudo-label on the basis of prediction information of the pixel; obtaining a second augmented image by carrying out a strong data augmentation on the first augmented image; training the deep neural network by using the second augmented image and the pseudo-labels; and updating the deep neural network on the basis of training results of the labeled image data and the unlabeled image data and processing a medical image by using the updated deep neural network.

Abstract: The present invention discloses a narrow-band, low-noise Raman fiber laser with a random fiber laser pump, pertaining to the technical field of fiber lasers and comprising an ytterbium-doped random fiber laser for producing ytterbium-doped random fiber lasing as the pump of a cascaded Raman random laser; the ytterbium-doped random fiber laser consists of a pump light source, a pump combiner, an ytterbium-doped fiber and a single-mode fiber connected in sequence, as well as a first narrow-band reflector connected to the signal end of the pump combiner. Ytterbium-doped random fiber lasing as the pump of the pump light source disclosed in the present invention is produced by an ytterbium-doped random fiber laser consisting of a narrow-band point reflector, an ytterbium-doped fiber, and a single-mode fiber and further serves as the pump of a Raman light source to achieve random laser output.

Abstract: A segmentation model learning method according to an embodiment includes learning that, based on a loss function value, includes performing supervised learning of the voxels in medical image data according to the region to which the voxels belong.

Abstract: A mask plate and an evaporation system. The mask plate includes at least one mask strip. Folding structures are connected to two opposite sides of the at least one mask strip. At least one group of effective evaporation area and transition area located around the effective evaporation areas are arranged on the at least one mask strip. Each folding structure includes a foldable part and a support part connected to each other. The foldable part is connected to the support part and the mask strip. The foldable part and at least part of the support part are sequentially stacked on one side of the two opposite sides of the mask strip, and the foldable part covers at least part of the transition area close to the folding structure of the mask strip.

Abstract: A data encoding method, an electronic device, and a storage medium are disclosed. The data encoding method may include: writing information bits into at least two cache blocks, where the cache blocks store parity bits corresponding to the information bits, and two adjacent bits of data of the parity bits are stored in different cache blocks; and performing low density parity check code (LDPC) encoding according to the information bits and the parity bits in the cache blocks.

Abstract: Disclosed are a battery housing, a lithium battery and an electronic product thereof. The battery housing includes a housing, a first cover plate and a second cover plate, an accommodation cavity being formed in the housing, an upper end and a lower end of the housing each being open, and a first through hole being formed in a side wall of the housing; the first cover plate is fixedly mounted at the upper end of the housing, the first cover plate covering the opening at the upper end of the housing; the second cover plate is fixedly mounted at the lower end of the housing, the second cover plate covering the opening at the lower end of the housing.

Abstract: The present invention provides a vessel traffic pattern identification method via data quality control and data compression, and includes the steps of assorting a collection of Automatic Identification System (AIS) data points according to Maritime Mobile Service Identity (MMSI) code; sorting each collection result by time ascending order; deleting duplicated vessel AIS data points considering time stamp, latitude, longitude and vessel speed over ground; segmenting vessel trajectories; obtaining high-quality AIS data with an AIS data anomaly detection; repairing and compressing each vessel trajectory with the Douglas-Peucker algorithm; clustering vessel trajectories with the Quick Bundles algorithm; and identifying a maritime traffic pattern. The invention can efficiently identify vessel traffic patterns and help maritime traffic management departments to accurately identify a traffic situation.