Abstract: A technical document scanner disclosed herein determines and categorizes various common issues among a large number of documents. An implementation of the technical document scanner is implemented using various computer process instructions including scanning a technical document to extract content, applying named entity recognition on the extracted content from the technical document to extract named entities, applying relation extraction on the named entities to extract relations between the named entities, and analyzing the relations between the entities to compose lists of high relevance entities for issue checking.

Abstract: Techniques are described for identifying and/or authenticating entities using a combination of independent identification technologies and/or platforms. In one embodiment, a system can comprising a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a reception component that receives image data captured of a person, and an identification component that employs two or more independent identification technologies and/or platforms to determine an identity of the person based on the image data. In some embodiments, the two or more independent identification technologies are selected from a group consisting of: facial recognition, object recognition, text recognition, and gait recognition.

Abstract: The present subject matter provides various technical solutions to technical problems facing advanced driver assistance systems (ADAS) and autonomous vehicle (AV) systems. In particular, disclosed embodiments provide systems and methods that may use cameras and other sensors to detect objects and events and identify them as predefined signal classifiers, such as detecting and identifying a red stoplight. These signal classifiers are used within ADAS and AV systems to control the vehicle or alert a vehicle operator based on the type of signal. These ADAS and AV systems may provide full vehicle operation without requiring human input. The embodiments disclosed herein provide systems and methods that can be used as part of or in combination with ADAS and AV systems.

Abstract: Systems and methods for predicting user interaction with vehicles. A computing device receives an image and a video segment of a road scene, the first at least one of an image and a video segment being taken from a perspective of a participant in the road scene and then generates stimulus data based on the image and the video segment. Stimulus data is transmitted to a user interface and response data is received, which includes at least one of an action and a likelihood of the action corresponding to another participant in the road scene. The computing device aggregates a subset of the plurality of response data to form statistical data and a model is created based on the statistical data. The model is applied to another image or video segment and a prediction of user behavior in the another image or video segment is generated.

Abstract: Deep recurrent neural networks applied to speech recognition. The deep recurrent neural networks (RNNs) are preferably implemented by stacked long short-term memory bidirectional RNNs. The RNNs are trained using end-to-end training with suitable regularisation.

Abstract: Systems and methods are presented for cross-fading (or other multiple clip processing) of information streams on a user or client device, such as a telephone, tablet, computer or MP3 player, or any consumer device with audio playback. Multiple clip processing can be accomplished at a client end according to directions sent from a service provider that specify a combination of (i) the clips involved; (ii) the device on which the cross-fade or other processing is to occur and its parameters; and (iii) the service provider system. For example, a consumer device with only one decoder, can utilize that decoder (typically hardware) to decompress one or more elements that are involved in a cross-fade at faster than real time, thus pre-fetching the next element(s) to be played in the cross-fade at the end of the currently being played element.

Abstract: A similarity calculation unit (213) treats each of a plurality of classifications as a target classification, and calculates a similarity between a reference feature value, which is a feature value extracted from image data of the target classification, and a recognition feature value, which is a feature value extracted from recognition target data, which is image data to be recognized. An influence calculation unit (214) calculates an influence on the similarity with regard to each partial image of the recognition target data by taking as input the similarity with regard to each of the classifications and the recognition feature value. A feature identification unit (215) changes the recognition feature value in accordance with the influence.

Abstract: Enclosed are embodiments for scoring one or more trajectories of a vehicle through a given traffic scenario using a machine learning model that predicts reasonableness scores for the trajectories. In an embodiment, human annotators, referred to as a “reasonable crowd,” are presented with renderings of two or more vehicle trajectories traversing through the same or different traffic scenarios. The annotators are asked to indicate their preference for one trajectory over the other(s). Inputs collected from the human annotators are used to train the machine learning model to predict reasonableness scores for one or more trajectories for a given traffic scenario. These predicted trajectories can be used to rank trajectories generated by a route planner based on their scores, compare AV software stacks, or used by any other application that could benefit from a machine learning model that scores vehicle trajectories.

Abstract: Systems and methods of improving alignment in dense prediction neural networks are disclosed. A method includes identifying, at a computing system, an input data set and a label data set with one or more first parts of the input data set corresponding to a label. The computing system processes the input data set using a neural network to generate a predicted label data set that identifies one or more second parts of the input data set predicted to correspond to the label. The computing system determines an alignment result using the predicted label data set and the label data set and a transformation of the one or more first parts, including a shift, rotation, scaling, and/or deformation, based on the alignment result. The computing system computes a loss score using the transformation, label data and the predicted label data set and updates the neural network based on the loss score.

Abstract: Provided is a medical image processing system that can stably control the light emission amount of narrow-band light of a short wavelength in a case where the narrow-band light of the short wavelength is used for illumination of an observation target. A light source circuit emits specific narrow-band light of a short wavelength. An image sensor includes a first pixel group including a B pixel and a second pixel group including a G pixel. The B pixel has a higher sensitivity to the specific narrow-band light than the G pixel. The G pixel has a sensitivity to light in a green band and the specific narrow-band light. The light source control unit controls the light emission amount of the specific narrow-band light on the basis of a pixel value of the B pixel and a pixel value of the G pixel.

Abstract: The technology disclosed relates to artificial intelligence-based base calling. The technology disclosed relates to accessing a progression of per-cycle analyte channel sets generated for sequencing cycles of a sequencing run, processing, through a neural network-based base caller (NNBC), windows of per-cycle analyte channel sets in the progression for the windows of sequencing cycles of the sequencing run such that the NNBC processes a subject window of per-cycle analyte channel sets in the progression for the subject window of sequencing cycles of the sequencing run and generates provisional base call predictions for three or more sequencing cycles in the subject window of sequencing cycles, from multiple windows in which a particular sequencing cycle appeared at different positions, using the NNBC to generate provisional base call predictions for the particular sequencing cycle, and determining a base call for the particular sequencing cycle based on the plurality of base call predictions.

Abstract: A surgical system and method involve a robotic system that has a moveable arm that supports an end effector relative to a surgical site to remove material from a bone. A scanner scans the surgical site and detects a vessel on the bone. Controller(s) is/are coupled to the robotic system and the scanner. The controller(s) obtain image data of the bone and receive, from the scanner, positional information of the vessel on the bone. The controller(s) input the positional information of the vessel to the image data of the bone and generate a boundary for the vessel. The controller(s) register the boundary to the bone for navigation and control the robotic system to remove material from the bone with the end effector and prevent interaction between the end effector and the vessel with the boundary.

Abstract: Various embodiments discussed herein enable applications to seamlessly contribute to executing voice commands of users via voice assistant functionality. In response to receiving a user request to open an application or web page, the application can request and responsively receive a voice assistant runtime component along with the application or web page. The application, using a particular universal application interface component can compile or interpret the voice assistant runtime component from a source code format to an intermediate code format. In response to the application or web page being rendered and the detection of a key word or phrase, the application can activate voice assistant command execution functionality. The user can issue a voice command after which the application along with specific services can help execute the voice command.

Abstract: In part, the disclosure relates to methods, and systems suitable for evaluating image data from a patient on a real time or substantially real time basis using machine learning (ML) methods and systems. Systems and methods for improving diagnostic tools for end users such as cardiologists and imaging specialists using machine learning techniques applied to specific problems associated with intravascular images that have polar representations. Further, given the use of rotating probes to obtain image data for OCT, IVUS, and other imaging data, dealing with the two coordinate systems associated therewith creates challenges. The present disclosure addresses these and numerous other challenges relating to solving the problem of quickly imaging and diagnosis a patient such that stenting and other procedures may be applied during a single session in the cath lab.

Abstract: A method for training, by a processor, a machine learning model for determining an operation of a medical tool control device may comprise the steps of: obtaining an operation command to move a medical tool of the medical tool control device on the basis of the machine learning model from guide data generated using a blood vessel image; generating evaluation data of a position to which the distal end of the medical tool has been moved according to the operation command in a blood vessel image; and updating a parameter of the machine learning model by using the evaluation data, so as to train the machine learning model.

Abstract: Some embodiments provide a method for training a machine-trained (MT) network that processes inputs using network parameters. The method propagates a set of input training items through the MT network to generate a set of output values. The set of input training items comprises multiple training items for each of multiple categories. The method identifies multiple training item groupings in the set of input training items. Each grouping includes at least two training items in a first category and at least one training item in a second category. The method calculates a value of a loss function as a summation of individual loss functions for each of the identified training item groupings. The individual loss function for each particular training item grouping is based on the output values for the training items of the grouping. The method trains the network parameters using the calculated loss function value.

Abstract: A face key point detection method includes determining, according to an image containing a face, a multi-channel feature map of the image; converting the multi-channel feature map into a predetermined channel quantity of target feature maps; performing a convolution operation on each target feature map in the predetermined channel quantity of target feature maps by using a convolution kernel corresponding to each target feature map; generating a feature vector corresponding to the image based on a result of the convolution operation on each target feature map; and determining key point coordinates of the face on the image according to the feature vector.

Abstract: Techniques for determining predictions on a top-down representation of an environment based on object movement are discussed herein. Sensors of a first vehicle (such as an autonomous vehicle) may capture sensor data of an environment, which may include object(s) separate from the first vehicle (e.g., a vehicle, a pedestrian, a bicycle). A multi-channel image representing a top-down view of the object(s) and the environment may be generated based in part on the sensor data. Environmental data (object extents, velocities, lane positions, crosswalks, etc.) may also be encoded in the image. Multiple images may be generated representing the environment over time and input into a prediction system configured to output a trajectory template (e.g., general intent for future movement) and a predicted trajectory (e.g., more accurate predicted movement) associated with each object. The prediction system may include a machine learned model configured to output the trajectory template(s) and the predicted trajector(ies).

Abstract: An apparatus, method, system and computer readable medium for video tracking. An exemplar crop is selected to be tracked in an initial frame of a video. Bayesian optimization is applied with each subsequent frame of the video by building a surrogate model of an objective function using Gaussian Process Regression (GPR) based on similarity scores of candidate crops collected from a search space in a current frame of the video. A next candidate crop in the search space is determined using an acquisition function. The next candidate crop is compared to the exemplar crop using a Siamese neural network. Comparisons of new candidate crops to the exemplar crop are made using the Siamese neural network until the exemplar crop has been found in the current frame. The new candidate crops are selected based on an updated surrogate model.

Abstract: Disclosed are systems and methods for extracting content based on image analysis. A method may include receiving content including at least an image depicting a coupon; converting the received content into a larger image including the image depicting the coupon; determining, utilizing one or more neural networks, the image depicting the coupon within the larger image, wherein determining the image depicting the coupon comprises: segmenting a foreground bounding box including the image depicting the coupon from background image portions of the image; cropping the larger image based on the bounding box, wherein the cropped image consists of the image depicting the coupon; determining text included in the cropped image; and extracting information included in the coupon based on the determined text.