Abstract: A device may receive unprocessed images to be labeled, and may utilize a first neural network model to identify objects of interest in the unprocessed images and bounding boxes for the objects of interest. The device may annotate the objects of interest to generate annotated objects of interest, and may utilize a second neural network model to group the annotated objects of interest into clusters. The device may utilize a third neural network model to determine labels for the clusters, and may request manually-generated labels for clusters for which labels are not determined. The device may receive the manually-generated labels, and may label the unprocessed images with the labels and the manually-generated labels to generate labeled images. The device may generate a training dataset based on the labeled images, and may train a computer vision model with the training dataset to generate a trained computer vision model.

Abstract: An image processing method is performed by a processor. The image processing method includes following operations: generating an average brightness value of each of a plurality windows in image data; generating a pixel ratio value according to the image data; generating a weight value of the each of the windows according to the pixel ratio value, a first brightness weight, and a second brightness weight; generating an adjusted brightness value according to the average brightness values of the windows and the weight values of the windows; and performing an auto exposure process according to the adjusted brightness value to generate final image data. The final image data is for a display panel to display.

Abstract: An array of antennas includes transmitter and receiver circuits. The transmitter includes a digital-to-analog converter (DAC), splitter and filter circuits, mixer circuits, and antennas. The DAC circuit converts a digital signal into an analog signal. The splitter and filter circuits separate frequencies of the analog signal into split signals. The mixer circuits multiply frequencies from the split signals by different frequencies of carrier signals to generate modulated signals that are converted by the antennas into radio frequency (RF) signals. The receiver includes antennas, mixer circuits, a summing circuit, and an analog-to-digital converter (ADC). The antennas in the receiver receive RF signals that are converted into electrical signals. The mixer circuits multiply frequencies from the electrical signals with different frequencies of carrier signals. The outputs of the mixer circuits are summed by the summing circuit to generate a summed signal that is converted to digital by the ADC.

Abstract: A payment processor system includes a point-of-sale device having at least one first sensor, a processor, a memory storing a plurality of users and a plurality of virtual payment accounts, wherein the processor is configured to apply semantic drift to select a virtual payment account in rapport with an item semantic identity in a payment transaction initiated at the point of sale.

Abstract: In various examples, detected object data representative of locations of detected objects in a field of view may be determined. One or more clusters of the detected objects may be generated based at least in part on the locations and features of the cluster may be determined for use as inputs to a machine learning model(s). A confidence score, computed by the machine learning model(s) based at least in part on the inputs, may be received, where the confidence score may be representative of a probability that the cluster corresponds to an object depicted at least partially in the field of view. Further examples provide approaches for determining ground truth data for training object detectors, such as for determining coverage values for ground truth objects using associated shapes, and for determining soft coverage values for ground truth objects.

Abstract: Methods and systems are provided for manufacturing an appliance for correcting malocclusions of a patient's teeth. The method may include measuring the positions of a patient's teeth and receiving tooth movement constraints. The method may also include generating an initial treatment plan based on the measured tooth positions and the tooth movement constraints and measuring the malocclusions of the patient's teeth for one or more types of dental malocclusions. The method may also include generating a plurality of treatment plans from the initial treatment plan based on the measured malocclusion and generating a model of an appliance for each stage of the treatment plan. The method may also include generating instructions for fabricating the appliance for each stage of the treatment plan based on the model of the appliance for each stage of the treatment plan.

Abstract: Systems, and method and computer readable media that store instructions for calculating signatures, utilizing signatures and the like, wherein for a low-power calculation of a signature, the method comprises: receiving or generating a media unit of multiple objects: processing the media unit by performing multiple iterations, determining a relevancy of the spanning elements of the iteration; completing the dimension expansion process by relevant spanning elements of the iteration and reducing a power consumption of irrelevant spanning; determining identifiers that are associated with significant portions of an output of the multiple iterations; and providing a signature that comprises the identifiers and represents the multiple objects.

Abstract: An electronic device and a controlling method thereof are provided. A controlling method of an electronic device according to the disclosure includes: performing first learning for a neural network model for acquiring a video sequence including a talking head of a random user based on a plurality of learning video sequences including talking heads of a plurality of users, performing second learning for fine-tuning the neural network model based on at least one image including a talking head of a first user different from the plurality of users and first landmark information included in the at least one image, and acquiring a first video sequence including the talking head of the first user based on the at least one image and pre-stored second landmark information using the neural network model for which the first learning and the second learning were performed.

Abstract: A semantic sensing system includes a processor, a memory, a plurality of wireless communication enabled devices and at least one sensing element, the memory storing a plurality of mapped endpoints wherein the processor is configured to apply semantic drift or entropy to determine affirmative and non-affirmative circumstances based on inputs from the at least one sensing element to cause the system to perform semantic augmentation towards a first endpoint supervisor in relation with the affirmative and non-affirmative determinations.

Abstract: A system comprising a server and a camera. The server may be configured to receive a rental offer for a location from a first user, receive a rental request for the location from a second user, generate a rental agreement comprising conditions in response to the rental offer and the rental request and generate a feature set based on the conditions. The camera may be configured to receive the feature set from the server, convert the feature set to parameters for the camera, generate a plurality of video frames of the location, perform video operations to detect objects in the video frames, extract data about the objects using the video operations, compare the data to the parameters and generate a notification in response to the data matching the parameters. The video frames may be discarded after performing the video operations. The video operations may be performed locally by the camera.

Abstract: A wireless device transmits, to a base station, at least one first measurement report of at least one synchronization signal of a cell. An indication, of one or more channel state information reference signals (CSI-RSs) of the cell, is received from the base station based on: the at least one first measurement report. and a first antenna port of the one or more CSI-RSs being quasi-collocated with a second port of the at least one synchronization signal. Based on the indication, at least one second measurement report of the one or more CSI-RSs is transmitted. Based on the at least one second measurement report, a downlink control information is received that initiates a random access procedure of the cell based on at least one first CSI-RS from the one or more CSI-RSs.

Abstract: Systems and methods are disclosed herein for determining a diagnosis based on a base skin tone of a patient. In an embodiment, the system receives a base skin tone image of a patient, generates a calibrated base skin tone image by calibrating the base skin tone image using a reference calibration profile, and determines a base skin tone of the patient based on the calibrated base skin tone image. The system receives a concern image of a portion of the patient's skin, and selects a set of machine learning diagnostic models from a plurality of sets of candidate machine learning diagnostic models based on the base skin tone of the patient, each of the sets of candidate machine learning diagnostic models trained to receive the concern image and output a diagnosis of a condition of the patient.

Abstract: A method and a device for performing plane detection are provided. The method includes acquiring an input image, extracting features of the input image using a deep neural network and estimating a depth map of the input image based on the extracted features, performing region segmentation using the depth map to detect plane regions in the input image.

Abstract: An automatic topology mapping processing method and system. The automatic topology mapping processing method includes the steps of: obtaining, by the automatic topology mapping processing system, a plurality of images, wherein at least two of the plurality of images include a common area in which a common space is captured; extracting, by the automatic topology mapping processing system, from respective images, features of the respective images through a feature extractor using a neural network; and determining, by the automatic topology mapping processing system, mapping images of the respective images on the basis of the features extracted from the respective images.

Abstract: A communication system includes a first communication terminal and a second communication terminal that shares a plurality of images with the first communication terminal. The first communication terminal includes first circuitry that receives a change of a display order of the plurality of images displayed on a display of the first communication terminal; and transmit information regarding the changed display order of the plurality of images to the second communication terminal. The second communication terminal includes second circuitry to change the display order of the plurality of images displayed on a display of the second communication terminal in accordance with the information regarding the display order of the plurality of images received from the first communication terminal. A method for communicating, performed by a communication terminal, the communication terminal, and a non-transitory recording medium executing the method for communicating are provided.

Abstract: Techniques for tracing back a projectile to the projectile origin are described. A method includes detecting projectile track(s) in image(s). Each projectile track crosses multiple pixels in each image. The projectile track(s) correspond to projectile(s). The projectile track(s) in the image(s) are translated to traceback path(s). The traceback path includes a known location and a projectile origin (e.g. the location at which the projectile originated, also termed the shooter's location).

Abstract: An apparatus for generating an HDR image includes an input image generator that generates a first image and a second image and an HDR image generator that generates a high dynamic range (HDR) in which a dynamic range of an original image is extended from the first image and the second image using a pre-trained model including a first neural network, a second neural network, and a third neural network, in which the first neural network is pre-trained to output a third image, the second neural network is pre-trained to output a fourth image and the third neural network is pre-trained to generate the HDR image based on the third image and the fourth image.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may transmit an indication of a capability to use a set of beamforming configurations associated with a beamforming circuit architecture of the UE. The UE may receive an indication of a selected beamforming configuration to use for one or more communications. Numerous other aspects are described.

Abstract: An error determination device includes a class estimation process observation unit configured to acquire data in a process of being estimated, from a class estimation unit that estimates a class of data to be classified and generate an estimation process feature vector based on the acquired data; and an error determination unit configured to accept input of the estimation process feature vector generated by the class estimation process observation unit and a classification result output from the class estimation unit and determine whether the classification result is correct or incorrect based on the estimation process feature vector and the classification result, wherein the error determination unit is a functional part generated by machine learning based on an estimation process feature vector list created by adding a pseudo feature vector to an estimation process feature vector list generated by the class estimation process observation unit and on a learning error-correction list indicating that a class co

Abstract: Systems, apparatuses, and methods for implementing an auto generation and tuning tool for convolution kernels are disclosed. A processor executes multiple tuning runs of a given layer of a neural network while using a different set of operating parameter values for each tuning run. The operating parameters can include one or more of input dataset fetch group size, output channel group size, and other parameters. The processor captures performance data for each tuning run and then after all tuning runs have finished, the processor determines which set of operating parameter values resulted in a better performance for the given neural network layer. The processor uses these operating parameter values for subsequent iterations of the given layer. The processor also performs the same techniques for other layers to determine which set of operating parameter values to use for each layer so as to maximize performance of the neural network.