Abstract: An image recognition method is provided. The method includes obtaining predicted locations of joints of a target person in a to-be-recognized image based on a joint prediction model, where the joint prediction model is pre-constructed by: obtaining a plurality of sample images; inputting training features of the sample images and a body model feature to a neural network and obtaining predicted locations of joints in the sample images outputted by the neural network; updating a body extraction parameter and an alignment parameter; and inputting the training features of the sample images and the body model feature to the neural network to obtain the joint prediction model.

Abstract: A flexible printed circuit and a display device are provided. The flexible printed circuit includes: a plurality of sub-circuit boards arranged in a stack, wherein the plurality of sub-circuit boards include at least a first sub-circuit board and a second sub-circuit board; and a pressure sensor arranged on the first sub-circuit board, wherein the first sub-circuit board includes: a substrate film; a conductive film arranged on a side of the substrate film away from the second sub-circuit board; an adhesive layer arranged on a side of the conductive film away from the substrate film; a cover layer arranged on a side of the adhesive layer away from the substrate film; and an electromagnetic shielding layer arranged on a side of the cover layer away from the substrate film, wherein at least a part of the conductive film is formed as an electrode of the pressure sensor.

Abstract: The present invention relates to crystalline polymorphs of imidacloprid for effective pest management strategies at lower dosages. The present invention further relates to processes of preparing the crystalline polymorphs, and to methods of controlling pests using the novel crystalline polymorphs.

Abstract: The present disclosure provides a display module, including a display panel and a cover plate covering a light-exiting surface of the display panel. The cover plate includes a display panel setting region and a functional module setting region, a light shielding structure is connected to a side wall of the display panel close to the functional module setting region, the functional module setting region includes a light shielding region and a light transmitting region for exposing a functional module, the light shielding region surrounds the light transmitting region, and the light shielding region is provided with an alignment mark for the attachment of a protective film configured for covering the light transmitting region. The present disclosure further provides a display device.

Abstract: A flexible printed circuit for bridging is provided. The flexible printed circuit has at least one via, at least one overflow groove is provided at a first distance from an edge of the via, and the overflow groove is provided in a cover layer on a side of a soldering surface of the flexible printed circuit.

Abstract: Embodiments of this application disclose a camera attitude tracking method and apparatus, a device, and a system in the field of augmented reality (AR). The method includes receiving, by a second device with a camera, an initial image and an initial attitude parameter that are transmitted by a first device; obtaining, by the second device, a second image acquired by the camera; obtaining, by the second device, a camera attitude variation of the second image relative to the initial image; and obtaining, by the second device, according to the initial attitude parameter and the camera attitude variation, a second camera attitude parameter, the second camera attitude parameter corresponding to the second image.

Abstract: There is provided a display device including a cover plate and a display panel; the cover plate includes a middle plane part, a first edge curved surface part, a second edge covered surface part and a corner curved surface part; the display panel includes a middle part, an edge part and a corner part; the middle part is arranged corresponding to the middle plane part; the edge part includes a first edge part and a second edge part; the first edge part and the first edge curved surface part are arranged correspondingly, and the second edge part and the second edge curved surface part are arranged correspondingly; the corner part and the corner curved surface part are correspondingly arranged; the middle part is in a display area; at least a portion of the edge part and the corner part adjacent to the middle part is in the display area.

Abstract: A terminal for generating music may identify, based on execution of scenario recognition, scenarios for images previously received by the terminal. The terminal may generate respective description texts for the scenarios. The terminal may execute keyword-based rhyme matching based on the respective description texts. The terminal may generate respective rhyming lyrics corresponding to the images. The terminal may convert the respective rhyming lyrics corresponding to the images into a speech. The terminal may synthesize the speech with preset background music to obtain image music.

Abstract: The present disclosure relates to a chip-on-film bonding structure, a display module, and a terminal equipment. The chip-on-film bonding structure includes: a chip on film including a first pin, the first pin including a first end and a second end that are arranged to be opposite to each other; and a flexible circuit board including a second pin connected to the first pin, the second pin including a third end and a fourth end that are arranged to be opposite to each other; in which the first end and the third end overlap to form a first active contact region; and the second end and the fourth end respectively extend outward from two opposite sides of the first active contact region, to form a first exposed region at the second end and to form a second exposed region at the fourth end.

Abstract: A story monitoring method when a robot takes an elevator is provided. The method including: obtaining gravity acceleration of the robot in a static state in an elevator and transient acceleration of the robot in a moving state in the elevator, a starting story number, and a story height of each story; obtaining an acceleration change waveform of the robot; comparing the acceleration change waveform by using an acceleration waveform classifier of the elevator, to obtain a movement status of the elevator at each moment; obtaining actual displacement of the elevator in a complete movement status of the elevator; and obtaining a story that the elevator is on after a complete movement status according to the actual displacement of the elevator, the starting story number, and the story height of each story.

Abstract: A display device includes: a display panel; a circuit board, one end of the circuit board being connected to the display panel, and the circuit board being at least partially disposed on a back surface of the display panel and includes a device region on a side distal from the display panel; at least one electronic device disposed in the device region; and an adhesive tape disposed on a side, distal from the display panel, of the circuit board and bonded to a back surface of at least a part of the circuit board and the back surface of at least a part of the display panel. At least a part of the at least one electronic device in the device region is disposed between the adhesive tape and the back surface of the display panel.

Abstract: An image processing method and a related apparatus are provided. The method is applied to an image processing device, and includes: obtaining an original image, the original image including a foreground object; extracting a foreground region from the original image through a deep neural network; identifying pixels of the foreground object from the foreground region; forming a mask according to the pixels of the foreground object, the mask including mask values corresponding to the pixels of the foreground object; and extracting the foreground object from the original image according to the mask.

Abstract: There is presented a method for geometrically modifying plasmonic structures on a support structure, such as for printing or recording, said method comprising changing a geometry specifically of plasmonic structures, wherein said changing the geometry is carried out by photothermally melting at least a portion of each of the plasmonic structures within the second plurality of plasmonic structures by irradiating, the plasmonic structures with incident electromagnetic radiation having an incident intensity in a plane of the second plurality of plasmonic structures, wherein said incident intensity is less than an incident intensity required to melt a film of a corresponding material and a corresponding thickness as the plasmonic structures within the second plurality of plasmonic structures.

Abstract: This application provides an example method for transmitting base station data. The method includes receiving a precoding matrix indication (PMI) value and reference signal received power (RSRP) that are sent by user equipment. The method also includes determining, based on the PMI value, a network area group corresponding to the user equipment. The method further includes determining, based on the RSRP, a network area in which the user equipment is located.

Abstract: This application provides a method for training a pose recognition model performed at a computer device. The method includes: inputting a sample image labeled with human body key points into a feature map model included in a pose recognition model, to output a feature map of the sample image; inputting the feature map into a two-dimensional (2D) model included in the pose recognition model, to output 2D key point parameters used for representing a 2D human body pose; input a target human body feature map cropped from the feature map and the 2D key point parameter into a three-dimensional (3D) model included in the pose recognition model, to output 3D pose parameters used for representing a 3D human body pose; constructing a target loss function based on the 2D key point parameters and the 3D pose parameters; and updating the pose recognition model based on the target loss function.

Abstract: Embodiments of this application disclose a foreground data generation method performed at a computer device. The method includes: obtaining a background image and a target image, the target image containing a target object and a background; removing the background from the target image according to the background image and the target image, to obtain initial foreground data of the target object in the target image; obtaining certain foreground data and uncertain data from the initial foreground data, wherein the uncertain data represents data whose value is between the certain foreground data and background data corresponding to the background; and segmenting the certain foreground data from the uncertain data, to obtain target foreground data of the target object in the target image.

Abstract: A computer device extracts a plurality of target windows from a target video. Each of the target windows comprises a respective plurality of consecutive video frames. For each of the target windows, the device performs action recognition on the respective plurality of consecutive video frames corresponding to the target window to obtain respective first action feature information of the target window. The device obtains a similarity between the first action feature information of the target window and preset feature information. The device determines, from the respective obtained similarities corresponding to the plurality of target windows, a highest first similarity and a first target window corresponding to the highest first similarity. The device also determines a dynamic action corresponding to the highest first similarity as the preset dynamic action in accordance with threshold settings.

Abstract: This application discloses a method for training a gaze tracking model, including: obtaining a training sample set; processing the eye sample images in the training sample set by using an initial gaze tracking model to obtain a predicted gaze vector of each eye sample image; determining a model loss according to a cosine distance between the predicted gaze vector and the labeled gaze vector for each eye sample image; and iteratively adjusting one or more reference parameters of the initial gaze tracking model until the model loss meets a convergence condition, to obtain a target gaze tracking model. According to the solution provided in this application, a gaze tracking procedure is simplified, a difference between a predicted value and a labeled value can be better represented by using the cosine distance as a model loss to train a model, to improve prediction accuracy of the gaze tracking model.

Abstract: An antenna port mapping method and a network device are disclosed. The method includes: determining, by a network device, a polarization direction of each of P physical antennas of the network device and an antenna array to which each of the P physical antennas belongs, where P is a multiple of 4; and respectively mapping, by the network device, a first antenna port and a second antenna port to a first group of physical antennas and a second group of physical antennas in the P physical antennas, and respectively mapping a third antenna port and a fourth antenna port to a third group of physical antennas and a fourth group of physical antennas in the P physical antennas.

Abstract: The present disclosure provides a display substrate, a display device, a control method and a control circuit. The display substrate includes a bending area. The bending area includes a plurality of first sub-pixels and a plurality of other sub-pixels having a light emission color different from a light emission color of the first sub-pixels. The plurality of first sub-pixels are electrically connected to a first power supply voltage terminal for providing a first power supply voltage. The other sub-pixels are electrically connected to other power supply voltage terminals different from the first power supply voltage terminal.