Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating, transmitting, directing, receiving, and processing optical subcarriers. In some implementations, a system includes a Tier 1 switch that supplies a plurality of data channels; a transmitter that receives the plurality of data channels, the transmitter including an optical modulator that supplies a plurality of optical subcarriers based on the plurality of data channels; an optical platform that receives the plurality of optical subcarriers, the optical platform having a plurality of outputs, each of which supplying at least one of the plurality of subcarriers; a plurality of receivers, each receiving one or more of the plurality of optical subcarriers and supplying one or more of the plurality of data channels; and a plurality of servers, each of which receiving one or more of the plurality of data channels.

Abstract: Embodiments are disclosed for health assessment and diagnosis implemented in an artificial intelligence (AI) system. The AI system takes as input information from a multitude of sensors measuring different biomarkers in a continuous or intermittent fashion. The proposed techniques disclosed herein address the unique challenges encountered in implementing such an AI system.

Abstract: An image processing device includes an extraction unit configured to extract a two-dimensional feature regarding a part of a person in an image, a conversion unit configured to convert the two-dimensional feature into a three-dimensional feature regarding a human body structure, and a training data generation unit configured to generate training data using the three-dimensional feature and a label indicating a physical state of the person.

Abstract: Discloses are weakly supervised semantic segmentation device and method based on pseudo-masks. The device includes a localization map generator configured to generate a plurality of first localization maps by providing an image to a first classifier; a saliency map processor configured to calculate a saliency loss through a saliency map used to identify a boundary line and a co-occurring pixel based on the plurality of first localization maps; a multi-label processor configured to predict a multi-label based on the plurality of first localization maps and calculate a classification loss; and a pseudo-masks generator configured to generate a second classifier obtained by updating the first classifier based on the saliency loss and the classification loss, and generate the pseudo-masks based on a plurality of second localization maps by the second classifier.

Abstract: Methods, devices, and systems related to determining biometric data using an array of infrared (IR) illuminators are described. In an example, a method can include projecting a number of IR dots on a user using a dot projector and an array of IR illuminators, capturing an IR image of the number of IR dots using an IR camera, comparing a number of pixels of the captured IR image to a number of corresponding pixels of a baseline IR image using a processing resource, and determining biometric data of the user at least partially based on comparing the captured IR image to the baseline IR image using the processing resource.

Abstract: Disclosed are a multi-task training technique and resulting model for detecting distracted driving. In one embodiment, a method is disclosed comprising inputting a plurality of labeled examples into a multi-task network, the multi-task network comprising: a backbone network, the backbone network generating one or more feature vectors corresponding to each of the labeled examples, and a plurality of prediction heads coupled to the backbone network; minimizing a joint loss based on outputs of the plurality of prediction heads, the minimizing the joint loss causing a change in parameters of the backbone network; and storing a distraction classification model after minimizing the joint loss, the distraction classification model comprising the parameters of the backbone network and parameters of at least one of the prediction heads.

Abstract: In an embodiment, an apparatus includes: a sensor to sense real world information; a digitizer coupled to the sensor to digitize the real world information into digitized information; a signal processor coupled to the digitizer to process the digitized information into an image; a discriminator coupled to the signal processor to determine, based at least in part on the image, whether the real world information comprises an anomaly, where the discriminator is trained via a generative adversarial network; and a controller coupled to the discriminator.

Abstract: System and method for reducing false negatives in object detection, including: extracting an object of interest from a respective image in a first set of training data that includes in distribution (ID) data. For each of the object of interest extracted from the respective image in the first set of training data: fusing the object of interest with an image from a second set of data that does not include any objects of interest to form a fused image; adding the fused image to the training data; and using the training data to train a detection model for object detection.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. One of the methods includes processing each training input using the neural network and in accordance with the current values of the network parameters to generate a network output for the training input; computing a respective loss for each of the training inputs by evaluating a loss function; identifying, from a plurality of possible perturbations, a maximally non-linear perturbation; and determining an update to the current values of the parameters of the neural network by performing an iteration of a neural network training procedure to decrease the respective losses for the training inputs and to decrease the non-linearity of the loss function for the identified maximally non-linear perturbation.

Abstract: A method for mosaicking and normalizing ortho-rectified images includes selecting imagery from a database using a query tool. The method also includes producing a GeoTIFF a digital elevation model (DEM) or creating a virtual mosaic from the selected imagery.

Abstract: A lane line detection method, an electronic device, and a storage medium, related to the field of artificial intelligence, and particularly related to computer vision and deep learning technologies, which can be applied to intelligent traffic scenes, are provided. The method includes: dividing an image into a foreground region and a background region; determining a solid line and a dotted line included in the foreground region; determining, according to the solid line and the dotted line comprised in the foreground region, whether a dotted-and-solid line is included in the foreground region; and determining a lane line detection result according to the solid line, the dotted line, and whether a dotted-and-solid line is comprised in the foreground region. According to the technical solution, the accuracy of lane line detection can be improved.

Abstract: An active interaction method, an electronic device and a readable storage medium, relating to the field of deep learning and image processing technologies, are disclosed. According to an embodiment, the active interaction method includes: acquiring a video shot in real time; extracting a visual target from each image frame of the video, and generating a first feature vector of each visual target; for each image frame of the video, fusing the first feature vector of each visual target and identification information of the image frame to which the visual target belongs to generate a second feature vector of each visual target; aggregating the second feature vectors with the same identification information respectively to generate a third feature vector corresponding to each image frame; and initiating active interaction in response to determining that the active interaction is to be performed according to the third feature vector of a preset image frame.

Abstract: The present disclosure provides an image processing method. An image to be classified is input into a feature extraction model to generate N dimensional features. Dimension fusion is performed on M features of the N dimensional features to obtain M dimension fusion features. The image to be classified is processed based on M dimension fusion features and remaining features of the N dimensional features other than the M features.

Abstract: Computer-implemented methods and systems are provided for digitally signing predetermined arrays of digital data. Such a method may provide a secret neural network model trained to classify arrays of digital data in dependence on data content of the arrays. The array of the arrays may be signed by supplying the array to the secret neural network model to obtain an initial classification result; and effecting a modification of data in the array to change the initial classification result to a predetermined, secret classification result, the modification being effected via a backpropagation process in the secret neural network model to progressively modify the array in response to backpropagated errors dependent on a difference between a current classification result for the array and the secret classification result.

Abstract: A system for categorizing seeds of plants into hybrid and non-hybrid categories. Seeds sorted according to the disclosed system are also disclosed.

Abstract: Methods, systems, and computer storage media are provided for data extraction. A target document representation may be generated based on modified text of a target electronic document. A measure of similarity may be determined between the target document representation and a reference document representation, which may be based on modified text of a reference electronic document. Based on the measure of similarity, the reference document representation may be selected. An extraction model associated with the selected reference document representation can then be used to extract data from the target document.

Abstract: Methods and systems for training a neural network include generate an image of a mask. A copy of an image is generated from an original set of training data. The copy is altered to add the image of a mask to a face detected within the copy. An augmented set of training data is generated that includes the original set of training data and the altered copy. A neural network model is trained to recognize masked faces using the augmented set of training data.

Abstract: A terminal (1050) includes a light receiver (151) that receives a light signal emitted by an apparatus (1000), the light signal including an identifier (SSID) of at least one base station (470); a receiver (153) that performs a reception process on the received light signal to output reception data; a data analyzer (155) that selects one base station based on the identifier of the at least one base station that is included in the reception data; and a radio device (453) that establishes a wireless connection with the selected base station (470) by using the identifier of the base station (470) and wirelessly communicates with the base station (470).

Abstract: Embodiments of the present disclosure provide systems and methods for training a machine-learning model for predicting emotions from received media data. Methods according to the present disclosure include displaying a user interface. The user interface includes a predefined media content, a plurality of predefined emotion tags, and a user interface control for controlling a recording of the user imitating the predefined media content. Methods can further include receiving, from a user, a selection of one or more emotion tags from the plurality of predefined emotion tags, receiving the recording of the user imitating the predefined media content, storing the recording in association with the selected one or more emotion tags, and training, based on the recording, the machine-learning model configured to receive input media data and predict an emotion based on the input media data.

Abstract: Aspects of the present invention disclose a method for a distance-based vector classification in anomaly detection. The method includes one or more processors identifying one or more audio communications from a first user to a second user, wherein the one or more audio communications is transmitted utilizing a first computing device. The method further includes determining an objective of the first user based at least in part on the audio communication of the first user. The method further includes determining a set of conditions corresponding to the one or more audio communications and the objective, wherein the set of conditions indicate a vulnerability of personal data of the first user. The method further includes prohibiting the first computing device from transmitting audio data that includes the personal data of the first user.