Abstract: A system for image reconstruction includes an input for receiving image data, a processor, and a memory. The memory stores instructions that cause the processor to reconstruct an image from the image data using a self-supervised deep learning model.

Abstract: Biometric information is obtained from a user. A determination is made that the obtained biometric information matches at least one entry in a biometric database. In response to determining that the obtained biometric information matches the at least one entry in the biometric database, non-biometric verification information is obtained. A determination is made as to whether at least a portion of the non-biometric verification information matches at least a portion of preset non-biometric verification information associated with the user. In response to determining that the at least a portion of the non-biometric verification information matches, a determination is made that an identity of the user is verified. In response to determining that the at least a portion of the non-biometric verification information does not match, a determination is made that the identity of the user is not verified.

Abstract: A processor in an object detection device is configured to: acquire settings data for one or more radar grids, each radar grid being set for a measurement area of a corresponding radar and consisting of radar cells; acquire settings data for a processing grid for clustering operations, the processing grid being set for the one or more measurement areas and consisting of processing cells; calculate, for each processing cell, one or more likelihoods associated with measurements of one or more related radar cells based on distances between the processing cell and the one or more related radar cells; calculate a grid value of each of the processing cells in the processing grid based on the one or more likelihoods; and perform a clustering operation on each processing cell based on distances between and/or grid values of the processing cell and one or more different processing cells.

Abstract: The present invention discloses a control system and a control method of a refrigerator. The control system comprises a collection unit and a fan control unit, and the fan control unit controls a heat dissipation fan to operate at different rotation speeds according to a power-on signal of the refrigerator, a closing signal and an opening signal of the first air port collected by the collection unit. The present invention solves the problem that the hot air discharged out of the compressor compartment blends with cold air and re-enters the compressor compartment, and the problem of poor heat dissipation of the refrigerator when the refrigerator is embedded in the cupboard.

Abstract: A method and a system for filtering ill corpus are provided. The method includes following steps: acquiring a text corpus to be recognized, and preprocessing the text corpus to be recognized to obtain a basic text corpus; extracting entities in the basic text corpus, and performing matching search on the entities of the basic text corpus according to an ill-text knowledge graph to obtain a first recognition result; detecting and recognizing the basic text corpus according to a corpus recognition model to obtain a second recognition result; and filtering the text corpus to be recognized according to the first or/and the second recognition result, and updating the ill-text knowledge graph according to the second recognition result. With semantic network essence and strong correlation ability of knowledge graph technology, candidate ill entities can be obtained, thus facilitating filtering of obscure ill information in forms of pinyin, homophonic words and split words.

Abstract: Embodiments of this application provide a multi-window display terminal device and method. The terminal device includes: two displays and two cameras that are respectively located on different sides, a microphone, and a processor. The terminal device may determine a display used by a user by using images collected by the two cameras, to adjust a position of a window, so that a front-rear display technology of the display can be implemented. The terminal device may also determine a distance between the user and the terminal device by using the images collected by the two cameras, to adjust a size and/or position of the window based on the distance of the user. The terminal device may also collect a sound of the user by using the microphone, to identify the user's needs and adjust a size and/or position of the window based on the user's needs.

Abstract: This application provides a display method and a device and relates to the field of communications technologies, so as to display different content on a terminal and an external display apparatus. A specific solution includes: displaying, by the terminal, a first screen, and instructing the external display apparatus to display a first desktop including a first application but not including a second application, where the first screen is different from the first desktop; and displaying, by the terminal in response to a first input of a user on the first screen, a second screen including the first application and the second application on the terminal, and instructing the external display apparatus to display a second desktop including the first application and the second application.

Abstract: A method and an apparatus for video production, a device and a storage medium are provided by the embodiment of the present disclosure, where information of a song list and a target song in the song list are acquired in response to a first instruction of a user, video materials are generated according to the information of the song list and a video is generated according to the video materials and a preset animation effect, and the target song and the video are merged to obtain a video file. In the embodiment of the present disclosure, by making the song list into a video containing more elements, better displaying of the information of the song list is realized, thus rendering it attractive for a user to click and play in a more effective manner, thereby effectively improving the click rate and playback amount of the song list.

Abstract: This application provides a display method and a device and relates to the field of communications technologies, so as to display different content on a terminal and an external display apparatus. A specific solution includes: displaying, by the terminal, a first screen, and instructing the external display apparatus to display a first desktop including a first application but not including a second application, where the first screen is different from the first desktop; and displaying, by the terminal in response to a first input of a user on the first screen, a second screen including the first application and the second application on the terminal, and instructing the external display apparatus to display a second desktop including the first application and the second application.

Abstract: To enable a risk of collision between moving objects such as a pedestrian and a vehicle to be quickly and accurately determined in a roadside device, when the roadside device receives a message including state information indicating that a pedestrian is in a risky state from a pedestrian terminal, the roadside device acquires position information of a vehicle present around the pedestrian in the risky state based on a result of detecting vehicles on roads by a radar, determines a risk of collision between the pedestrian in the risky state and the vehicle based on the position information of the vehicle, and when the risk of collision exists, transmits a message including alarm information indicating that the risk of collision exists to the terminal.

Abstract: This application provides a display method and a device and relates to the field of communications technologies, so as to display different content on a terminal and an external display apparatus. A specific solution includes: displaying, by the terminal, a first screen, and instructing the external display apparatus to display a first desktop including a first application but not including a second application, where the first screen is different from the first desktop; and displaying, by the terminal in response to a first input of a user on the first screen, a second screen including the first application and the second application on the terminal, and instructing the external display apparatus to display a second desktop including the first application and the second application.

Abstract: An object determination method involves acquiring radar data including information records of a radar reflection intensity and a velocity for each orientation and each distance; generating a radar detection image in which each pixel has a plurality of channels for containing data records of a radar reflection intensity, a velocity, and a distance, respectively, the data records corresponding to the position of the pixel; and by using a machine learning model for image recognition trained for object determination, acquiring an object determination result determined based on the radar detection image. In particular, the method includes, based on position data of an object area detected from the radar data of an entire observation area, extracting radar data of the object area from the radar data of the entire observation area; and generating the radar detection image of the object area based on the radar data of the object area.

Abstract: The present disclosure provides an evaluation method, a model establishing method, a teaching device, system, and an electrical apparatus. The method includes: collecting image information containing a user's image; acquiring an action model corresponding to training actions that the user refers to; performing evaluation on action information of at least one part of the user's body in the image information by using the action model to obtain an evaluation result; outputting the evaluation result on the action information of at least one part of the user's body.

Abstract: A processor in an object detection device is configured to: acquire settings data for one or more radar grids, each radar grid being set for a measurement area of a corresponding radar and consisting of radar cells; acquire settings data for a processing grid for clustering operations, the processing grid being set for the one or more measurement areas and consisting of processing cells; calculate, for each processing cell, one or more likelihoods associated with measurements of one or more related radar cells based on distances between the processing cell and the one or more related radar cells; calculate a grid value of each of the processing cells in the processing grid based on the one or more likelihoods; and perform a clustering operation on each processing cell based on distances between and/or grid values of the processing cell and one or more different processing cells.

Abstract: To enable a risk of collision between moving objects such as a pedestrian and a vehicle to be quickly and accurately determined in a roadside device, when the roadside device receives a message including state information indicating that a pedestrian is in a risky state from a pedestrian terminal, the roadside device acquires position information of a vehicle present around the pedestrian in the risky state based on a result of detecting vehicles on roads by a radar, determines a risk of collision between the pedestrian in the risky state and the vehicle based on the position information of the vehicle, and when the risk of collision exists, transmits a message including alarm information indicating that the risk of collision exists to the terminal.

Abstract: This application provides a display method and a device and relates to the field of communications technologies, so as to display different content on a terminal and an external display apparatus. A specific solution includes: displaying, by the terminal, a first screen, and instructing the external display apparatus to display a first desktop including a first application but not including a second application, where the first screen is different from the first desktop; and displaying, by the terminal in response to a first input of a user on the first screen, a second screen including the first application and the second application on the terminal, and instructing the external display apparatus to display a second desktop including the first application and the second application.

Abstract: An object detection apparatus includes: capture region extraction circuitry receives measurement information generated by a radar apparatus using reflected waves from each object and uses the measurement information to extract second unit regions as first capture regions from among first unit regions, the first unit regions being regions into which a measuring range of the radar apparatus has been divided, the second unit regions being regions in which each object has been captured; preliminary grouping circuitry that forms a preliminary group including a second capture region that is present within a determined range; feature quantity acquisition circuitry that calculates a feature quantity that represents an association between the preliminary group and the second capture region; discrimination circuitry that discriminates a type of each object that belongs to the second capture region; and object determination circuitry that groups the second capture region according to the type to detect that object.

Abstract: Frequency analysis of each of a plurality of reception antennas and each of reception signals received by the plurality of reception antennas is performed, a power spectrum is calculated for each of the reception antennas, a standard deviation indicating a degree of conformity in a peak of the power spectrum among the plurality of reception antennas is calculated, the power spectra are corrected with use of the standard deviation, a peak is detected based on the corrected power spectra, and a target object is detected based on the detected peak.

Abstract: An object detection device includes a sub-cluster generating circuitry which, in operation, divides a cluster generated by a cluster generator into one or more first sub-clusters each corresponding to a part of an object having a different traveling direction or traveling speed from a main part of the object and a second sub-cluster corresponding to the main part of the object; and a speed calculating circuitry which, in operation, uses one or more capture points belonging to the second sub-cluster and calculates a traveling speed of the object.

Abstract: A radar signal processing apparatus includes: clutter detection area setting circuitry acquiring profile information indicating reflected power of received power of reflected signal, per unit area obtained by dividing, at determined intervals, an area defined by the transmission direction of radar signal acquired by and distance from an radar apparatus, and sets a clutter detection area in the profile information; clutter characteristic calculation circuitry calculating a first representative value of reflected power of clutter in the clutter detection area and corresponding first distance; suppression filter setting circuitry calculating, based on these first representative value and distance, a parameter indicating a correspondence relation between the reflected power of clutter and a distance from the radar apparatus; and suppression processing circuitry calculating threshold based on the parameter, and determines an area in the profile information having a value of reflected power at or below the threshol