Abstract: Aspects described herein provide a method including: receiving input data at a machine learning model, comprising: a plurality of processing layers; a plurality of gate logics; a plurality of gates; and a fully connected layer; determining based on a plurality of gate parameters associated with the plurality of gate logics, a subset of the plurality of processing layers with which to process the input data; processing the input data with the subset of the plurality of processing layers and the fully connected layer to generate an inference; determining a prediction loss based on the inference and a training label associated with the input data; determining an energy loss based on the subset of the plurality of processing layers used to process the input data; and optimizing the machine learning model based on: the prediction loss; the energy loss; and a prior probability associated with the training label.

Abstract: Systems and methods for presenting sensor data are provided and include collecting physiological data and meta data from a subject via a sensor system, wherein the sensor system comprises a sensor element, a signal processor, and memory in communication with the signal processor. The subject meta data is processed by the signal processor to determine metric features, the metric features are processed by the signal processor to determine a subject-specific metric statistic for the subject, and the physiological data is processed by the signal processor to generate a sensor metric. The sensor metric is then presented for display via a display.

Abstract: A system and method for operating a neural network. In some embodiments, the neural network includes a variational autoencoder, and the training of the neural network includes training the variational autoencoder with a plurality of samples of a first random variable; and a plurality of samples of a second random variable, the plurality of samples of the first random variable and the plurality of samples of the second random variable being unpaired, the training of the neural network including updating weights in the neural network based on a first loss function, the first loss function being based on a measure of deviation from consistency between: a conditional generation path from the first random variable to the second random variable, and a conditional generation path from the second random variable to the first random variable.

Abstract: A method and system for providing integrated augmented reality (AR) images and content to multiple vehicle occupants having AR devices and methods of generating user-based AR expressions including content control of user generated content.

Abstract: A method for estimating human body temperature includes receiving, via a thermal camera, a thermal image captured of a real-world environment, the thermal image including thermal intensity values for each of a plurality of pixels of the thermal image. A position of a human face is identified within the thermal image, the human face corresponding to a human subject. An indication of a distance between the human subject and the thermal camera is received. Based on the distance, a distance correction factor is applied to one or more thermal intensity values of one or more pixels corresponding to the human face to give one or more distance-corrected thermal intensity values. Based on the one or more distance-corrected thermal intensity values an indication of a body temperature of the human subject is reported.

Abstract: A method for distributing information includes producing a symbol to be overlaid on at least one primary image presented on a first display screen, the symbol encoding a specified digital value in a set of color elements having different, respective colors. A message is received from a client device containing an indication of the specified digital value decoded by the client device upon capturing and analyzing a secondary image of the first display screen. In response to the message, an item of information relating to the primary image is transmitted to the client device, for presentation on a second display screen associated with the client device.

Abstract: An information retrieval system (IPS). The system comprises an input interface (IN) for receiving a query related to an object of interest. A concept mapper (CM) is configured to map the query to one or more associated concept entries of a hierarchic graph data structure (ONTO). The entries in said structure encode linguistic descriptors of components of a model (GM) for said object (OB). A metric-mapper (MM) is configured to map the query to one or more metric relationship descriptors. A geo-mapper (GEO) is configured to map said concept entries against the geometric model linked to the hierarchic graph data structure to obtain spatio-numerical data associated with said linguistic descriptors. A metric component (MTC) is configured to compute one or more metric or spatial relationships between said object components based on the spatio-numerical data and the one or more metric relationship descriptors.

Abstract: Described herein are methods and apparatuses to obtain an image, or a set of images, of a patient's teeth from one or more predetermined viewing angles. These methods and apparatuses may include the use an overlay comprising an outline of teeth for each predetermined viewing angle. The overlay may be used for automatically capturing, focusing and/or illuminating the teeth. Also described herein are methods and apparatuses for using a series of images of the patient's teeth including a set of predetermined views to determine if a patient is a candidate for an orthopedic procedure.

Abstract: An information processing apparatus that performs deep learning using a neural network includes a memory, and an arithmetic processing device that performs a process for layers of the neural network in a predetermined direction. The process for the layers includes: pre-determining a decimal point position of a fixed-point number of an intermediate data obtained by an operation of each of the layers; performing the arithmetic operation for each layer with the pre-determined decimal point position to obtain the intermediate data and acquiring first statistical information of a distribution of bits of the intermediate data; determining a decimal point position of the intermediate data based on the statistical information; and performing the arithmetic operation for each layer with the determined decimal point position again when the difference of the determined decimal point position and the pre-determined decimal point position is greater than a threshold value.

Abstract: An information processing apparatus (10) is for supporting work by a user who uses drawings for a plant. The information processing apparatus (10) includes a controller (15). The controller (15) is configured to convert a drawing including elements configuring the plant into an abstract model represented by element information indicating the elements and connection information indicating a connection relationship between the elements. The controller (15) is configured to generate display information, when it is judged that a difference exists between one abstract model based on one drawing and another abstract model based on another drawing, for displaying the differing portion in a different form than another portion.

Abstract: A notification system includes a memory, an output device and activity, localization, and tracking modules. The memory stores an activity history log associated with a supporting structure. The activity module: receives signals from sensors or electrical devices; and tracks activities at least one of in or within a set distance of the supporting structure to generate the activity history log. The localization module relates the activities to aspects of the supporting structure and generates corresponding localization data. The tracking module tracks states of the aspects of the supporting structure contacted at least one of directly or indirectly by one or more animate objects and determine at least one of contamination levels or sanitization levels of the aspects based on the localization data and the activity history log. The output device indicates the at least one of the contamination levels or the sanitization levels.

Abstract: A distributed, cross reality system efficiently and accurately compares location information that includes image frames. Each of the frames may be represented as a numeric descriptor that enables identification of frames with similar content. The resolution of the descriptors may vary for different computing devices in the distributed system based on degree of ambiguity in image comparisons and/or computing resources for the device. A descriptor computed for a cloud-based component operating on maps of large areas that can result in ambiguous identification of multiple image frames may use high resolution descriptors. High resolution descriptors reduce computationally intensive disambiguation processing. A portable device, which is more likely to operate on smaller maps and less likely to have the computational resources to compute a high resolution descriptor, may use a lower resolution descriptor.

Abstract: Systems, devices, media, and methods are presented for presentation of modified objects within a video stream. The systems and methods receive a set of images within a video stream and identify at least a portion of a face in a first subset of images. The systems and methods determine face characteristics by analyzing the portion of the face in the first subset of images. The systems and methods apply a graphical representation of glasses to the face based on the face characteristics and cause presentation of a modified video stream including the portion of the face with the graphical representation of the glasses in a second subset of images of the set of images while receiving the video stream.

Abstract: Training a generator G of a GAN includes generating, by G and in response to receiving a first input Z, a first output G(Z); generating, by an encoder E of the GAN and in response to receiving the first output G(Z) as input, a second output E(G(Z)); generating, by G and in response to receiving the second output E(G(Z)) as input, a third output G(E(G(Z))); generating, by E and in response to receiving the third output G(E(G(Z))) as input, a fourth output E(G(E(G(Z)))); training E to minimize a difference between the second output E(G(Z)) and the fourth output E(G(E(G(Z)))); and using the second output E(G(Z)) and fourth output E(G(E(G(Z)))) to constrain a training of the generator G. G(Z) is an ambient space representation Z. E(G(Z)) is a latent space representation of G(Z). G(E(G(Z))) is an ambient space representation of E(G(Z)). E(G(E(G(Z)))) is a latent space representation of G(E(G(Z))).

Abstract: A particular voxel is identified within a volume and a hash table is used to obtain volumetric data describing the particular voxel within the volume. Values of x-, y- and z-coordinates in the volume associated with the particular voxel are determined an index value associated with the particular voxel is determined according to a hashing algorithm, where the index value is determined from summing weighted values of the x-, y- and z-coordinates, and the weighted values are based on a variable value corresponding to a dimension of the volume. A particular entry is identified in the hash table based on the index value, where the particular entry includes volumetric data, and the volumetric data identifies, for the particular voxel, whether the particular voxel is occupied.

Abstract: The present invention is directed to solving an issue arising when a background image is generated. An image processing system generates a foreground image containing a foreground object based on an image captured by an imaging apparatus included in a first imaging apparatus group. The image processing system generates a background image not containing the foreground object based on an image of the imaging region captured by an imaging apparatus included in a second imaging apparatus group different from the first imaging apparatus group. The image processing system generates a virtual viewpoint image based on the generated foreground image and background image.

Abstract: A display control device displays, on an electronic inner mirror, a composite image composited by performing image processing on a rear image captured by a rear camera and rear lateral images captured by an outer camera unit such that the rear image and the rear lateral images become a continuous image. A subject vehicle virtual image superimposition display unit of the display control device generates a virtual image of a subject vehicle virtually showing a subject vehicle and displays the virtual image of the subject vehicle superimposed on the composite image. A subject vehicle travel trajectory superimposition display unit of the display control device generates a virtual image of travel trajectory, which extends from left and right rear wheels toward the rear of the vehicle in the composite image, and displays the virtual image of travel trajectory superimposed on the composite image.

Abstract: The present invention relates to a method and a system for three-dimensional automatic scan based primitive, and estimates a three-dimensional model of an object from three-dimensional scan data of the object, recognizes a shape of the three-dimensional model by using fitting with at least one primitive, evaluates confidence of each of surface points of the three-dimensional model based on similarity between the at least one primitive used for shape recognition and the shape of the three-dimensional model, and scans the object in a series of views determined based on the confidence of each of the surface points, and thus, accuracy of the three-dimensional scan of the object is improved and time required for scan may be reduced.

Abstract: Disclosed techniques relate to memory space management for graphics processing. In some embodiments, first and second graphics cores are configured to execute instructions for multiple threadgroups. In some embodiments, the threads groups include a first threadgroup with multiple single-instruction multiple-data (SIMD) groups configured to execute a first shader program and a second threadgroup with multiple SIMD groups configured to execute a second, different shader program. Control circuitry may be configured to provide access to data stored in memory circuitry according to a shader memory space. The shader memory space may be accessible to threadgroups executed by the first graphics shader core, including the first and second threadgroups, but is not accessible to threadgroups executed by the second graphics shader core. Disclosed techniques may reduce latency, increase bandwidth available to the shader, reduce coherency cost, or any combination thereof.

Abstract: Systems, methods, and apparatus are disclosed for determining quantitative hormone and chemical analyte results from qualitative test results. An image is taken of an ovulation test device. The image is analyzed to identify a color intensity ratio (T/C ratio) between a color density of a test-line to a color density of a control-line. Additionally, a quantitative substance level may be determined using the T/C ratio, by identifying the type of test device and referencing a data structure that relates quantitative substance levels to T/C ratios for the identified type of test device.