Abstract: According to an embodiment, an information processing device include: one or more processors. The processors input data based on input data including first input data belonging to a first domain and second input data belonging to a second domain different from the first domain, to a first model, and acquire first output data indicating an execution result of a first task with the first model. The processors input data based on the input data to a second model, and acquire second output data indicating an execution result of a second task with the second model. The processors convert the first output data into first conversion data expressed in a form of an execution result of the second task. The processors generate supervised data of the second model for the first input data, based on the first conversion data and the second output data.

Abstract: A machine-learning-based monochromatic CT image reconstruction method is described for quantitative CT imaging. The neural network is configured to learn a nonlinear mapping function from a training data set to map a CT image, which is reconstructed from a single spectral current-integrating projection data set, to monochromatic projections at a pre-specified energy level, realizing monochromatic CT imaging and overcoming beam hardening. An apparatus, method and/or system are configured to determine, by a trained artificial neural network (ANN), a monochromatic projection data set based, at least in part, on a measured CT image. The measured CT image may be reconstructed based, at least in part, on measured projection data. The measured projection data may be polychromatic. The apparatus, method and/or system may be further configured to reconstruct a monochromatic CT image based, at least in part, on the monochromatic projection data set.

Abstract: A multicore hardware implementation of a deep neural network includes a plurality of layers arranged in plurality of layer groups. The input data to the network comprises a multidimensional tensor including one or more traversed dimensions, being dimensions that are traversed by strides in at least one layer of a first layer group. The hardware implementation is configured to split the input data for the first layer group into at least a first tile and a second tile, along at least one of the traversed dimensions, each tile comprising a plurality of data elements in each of the one or more traversed dimensions. A first core is configured to evaluate multiple layer groups, depth-first, based on the first tile. A second core is configured to evaluate multiple layer groups, depth-first, based on the second tile.

Abstract: A character recognition method includes: performing feature extraction on an image to be recognized to obtain a first feature map; processing the first feature map to at least obtain N first candidate carrier detection boxes, each first candidate carrier detection box being configured to outline a region of a character carrier; screening the N first candidate carrier detection boxes to obtain K first target carrier detection boxes; performing a feature extraction on the first feature map to obtain a second feature map; processing the second feature map to obtain L first candidate character detection boxes, each first candidate character detection box being configured to outline a region containing at least one character; screening the L first candidate character detection boxes to obtain J first target character detection boxes; and recognizing characters in the J first target character detection boxes to obtain J target character informations.

Abstract: Described are systems and methods for fixture identification in test systems. A method for fixture identification in a test system may include capturing image data representative of a first fixture of the test system with an imaging device. The method may further include transmitting the image data representative of the first fixture from the imaging device to a processor running an image recognition application. The method may also include identifying the first fixture based on the image data with the processor running the image recognition application.

Abstract: Systems and techniques are provided for performing holistic video understanding. For example a process can include obtaining a first video and determining, using a machine learning model decision engine, a first machine learning model from a set of machine learning models to use for processing at least a portion of the first video. The first machine learning model can be determined based on one or more characteristics of at least the portion of the first video. The process can include processing at least the portion of the first video using the first machine learning model.

Abstract: Embodiments are disclosed for deblurring motion in video. A method of deblurring motion in video can include receiving an input frame from a digital video, extracting a plurality of features of the input frame using an encoder network, determining, using a neural network, a plurality of spatial alignment kernels and a plurality of deblur kernels each corresponding to a feature of the input frame, wherein the plurality of spatial alignment kernels include different sizes of spatial alignment kernels and wherein the plurality of deblur kernels include different sizes of deblur kernels, generating, by the neural network, a plurality of output features for the input frame using the plurality of spatial alignment kernels and the plurality of deblur kernels, and generating a deblurred output frame from the plurality of output features using a decoder network.

Abstract: Techniques are described for using computing devices to perform automated operations to generate mapping information of a defined area via analysis of visual data of images, including by using attribute information exchanged between paired or otherwise grouped images of multiple types to generate enhanced images, and for using the generated mapping information in further automated manners, including to use the generated mapping information for automated navigation and/or to display or otherwise present the generated mapping information. In some situations, the defined area includes an interior of a multi-room building, and the generated information includes at least one or more enhanced images and/or a partial floor plan and/or other modeled representation of the building, with the generating performed in some cases without having measured depth information about distances from the images' acquisition locations to walls or other objects in the surrounding building.

Abstract: A method for generating an output image may include obtaining an input image having a first exposure value, generating a plurality of levels that are each respectively associated with a respective representation of the input image, based on the input image, generating the output image having a second exposure value, based on a deep neural network (DNN) including a set of sub-networks and the plurality of levels, and providing the output image.

Abstract: The technology disclosed relates to constructing a convolutional neural network-based classifier for variant classification. In particular, it relates to training a convolutional neural network-based classifier on training data using a backpropagation-based gradient update technique that progressively match outputs of the convolutional neural network-based classifier with corresponding ground truth labels. The convolutional neural network-based classifier comprises groups of residual blocks, each group of residual blocks is parameterized by a number of convolution filters in the residual blocks, a convolution window size of the residual blocks, and an atrous convolution rate of the residual blocks, the size of convolution window varies between groups of residual blocks, the atrous convolution rate varies between groups of residual blocks. The training data includes benign training examples and pathogenic training examples of translated sequence pairs generated from benign variants and pathogenic variants.

Abstract: A system and method for online real-time multi-object tracking is disclosed. A particular embodiment can be configured to: receive image frame data from at least one camera associated with an autonomous vehicle; generate similarity data corresponding to a similarity between object data in a previous image frame compared with object detection results from a current image frame; use the similarity data to generate data association results corresponding to a best matching between the object data in the previous image frame and the object detection results from the current image frame; cause state transitions in finite state machines for each object according to the data association results; and provide as an output object tracking output data corresponding to the states of the finite state machines for each object.

Abstract: An image processing system is described which has a memory holding at least one image depicting at least one person previously unseen by the image processing system. The system has a trained probabilistic model which describes a relationship between image features, context, identities and a plurality of names of people, wherein at least one of the identities identifies a person depicted in the image without an associated name in the plurality of names. The system has a feature extractor which extracts features from the image, and a processor which predicts an identity of the person depicted in the image using the extracted features and the probabilistic model.

Abstract: Aspects described herein provide a method of processing data in a machine learning model, including: receiving first domain input data; transforming the first domain input data to second domain input data via a domain transformation function; providing the second domain input data to a first layer of a machine learning model; processing the second domain input data in the first layer of the machine learning model according to a set of layer weights; and outputting second domain output data from the first layer of the machine learning model.

Abstract: In some aspects, the disclosure is directed to methods and systems for a multi-model message response generation system. A computing device may identify a first message. The computing device may determine that the first message is an initial message of a thread or includes an error log. Responsive to determining that the first message is the initial message of the thread or includes an error log, the computing device generates a response to the first message from a solution associated with a problem matching the first message. The computing device may identify a second message. The computing device may input the second message into a response generation model in response to determining the second message is not an initial message of a thread. The computing device may generate a second response from output data of the response generation model.

Abstract: Embodiments of the present disclosure are directed to a method for object detection. The method includes receiving sensor data indicative of one or more objects for each of a camera subsystem, a LiDAR subsystem, and an imaging RADAR subsystem. The sensor data is received simultaneously and within one frame for each of the subsystems. The method also includes extracting one or more feature representations of the objects from camera image data, LiDAR point cloud data and imaging RADAR point cloud data and generating image feature maps, LiDAR feature maps and imaging RADAR feature maps. The method further includes combining the image feature maps, the LiDAR feature maps and the imaging RADAR feature maps to generate merged feature maps and generating object classification, object position, object dimensions, object heading and object velocity from the merged feature maps.

Abstract: Systems and methods to estimate 3D TOF scatter include acquisition of 3D TOF data, determination of 2D TOF data from the first TOF data, determination of first estimated scatter based on the second TOF data, reconstruction of a first estimated image based on the first estimated scatter and the second TOF data, determination of attenuated unscattered true coincidences based on the first estimated image, determination of second estimated scatter based on the first TOF data and the attenuated unscattered true coincidences, and reconstruction of an image of the object based on the first TOF data and the second estimated scatter.

Abstract: A multiplexer includes a filter on a first path connecting a common terminal and an input/output terminal, and a second filter on a second path connecting the common terminal and a second terminal, the second filter having a passband that overlaps a generation frequency of Rayleigh wave ripples in the filter. The filter includes series arm resonators on the first path and a parallel arm resonator, the series arm resonators and the parallel arm resonator utilize an SH wave as a main mode, and a number of electrode finger pairs of the series arm resonator is fewest among numbers of electrode finger pairs of the series arm resonators.

Abstract: Methods, non-transitory computer readable media, and arthroscopic video analysis apparatuses and systems that facilitate improved analysis of videos of arthroscopic procedures are disclosed. With this technology, analytical data related to the video feed of an arthroscopic surgery can be obtained using machine learning models and associated with the video feed. The generated videos can be output in real-time to provide contextual information related to the surgical procedure, or can be saved for playback for training or informational purposes.

Abstract: A method and information storage media having instructions stored thereon for supervised Deep Learning (DL) systems to learn directly from unlabeled data without any user annotation. The annotation-free solutions incorporate a new learning module, the Localization, Synthesis and Teacher/Annotation Network (LSTN) module, which features a data synthesis and generation engine as well as a Teacher network for object detection and segmentation that feeds the processing loop with new annotated objects detected from images captured at the field. The first step in the LSTN module learns how to localize and segment the objects within a given image/scene following an unsupervised approach as no annotations about the objects' segmentation mask or bounding box are provided.

Abstract: Systems and methods are provided for generating textual embeddings by tokenizing text data and generating vectors to be provided to a transformer system, where the textual embeddings are vector representations of semantic meanings of text that is part of the text data. The vectors may be averaged for every token of the generated textual embeddings and concatenating average output activations of two layers of the transformer system. Image embeddings may be generated with a convolutional neural network (CNN) from image data, wherein the image embeddings are vector representations of the images that are part of the image data. The textual embeddings and image embeddings may be combined to form combined embeddings to be provided to the transformer system.