Abstract: Provided are a method of judgment for in or out, and a recording medium and an apparatus for performing the same. The method performed by the apparatus for judging whether an object landed inside or outside of a line, includes: capturing a sport environment image provided with the line according to a preset rule, wherein the sport environment image includes an audio signal and an image signal; separating the audio signal and the image signal included in the sport environment image; detecting the line by analyzing the image signal; detecting a landing point-in-time of the object by analyzing each of the audio signal and the image signal; and judging whether the object landed inside or outside of the line by comparing the line with a location of the object at the landing point-in-time of the object.

Abstract: A target detection method comprises performing corner point feature extraction processing on an input image to obtain a pair of target corner points, generating a target frame based on the pair of target corner points, and outputting a target detection result of a target object when determining that a calibration area in the target frame comprises a target feature point.

Abstract: Generally discussed herein are devices, systems, and methods for on-device detection of a wake word. A device can include a memory including model parameters that define a custom wake word detection model, the wake word detection model including a recurrent neural network transducer (RNNT) and a lookup table (LUT), the LUT indicating a hidden vector to be provided in response to a phoneme of a user-specified wake word, a microphone to capture audio, and processing circuitry to receive the audio from the microphone, determine, using the wake word detection model, whether the audio includes an utterance of the user-specified wake word, and wake up a personal assistant after determining the audio includes the utterance of the user-specified wake word.

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: Systems, devices, media, and methods are presented for detecting and interpreting motion of a device and a remote object to control operations of the device. The systems and methods identify a sensor input within a drone. The sensor input indicates movement of the drone within a three dimensional space. The systems and methods determine one or more movement attributes from the sensor input and, in response to the one or more movement attributes, selects one or more maneuvers corresponding to at least one movement attribute. The system and methods then execute the one or more maneuvers by controlling one or more drone control components to move the drone within the three dimensional space.

Abstract: A system and method for predicting the near-term trajectory of a moving obstacle sensed by an autonomous driving vehicle (ADV) is disclosed. The method applies neural networks such as a LSTM model to learn dynamic features of the moving obstacle's motion based on its past trajectory up to its current position and a CNN model to learn the semantic map features of the driving environment in a portion of an image map. From the learned dynamic features of the moving obstacle and the learned semantic map features of the environment, the method applies a neural network to iteratively predict the moving obstacle's positions for successive time points of a prediction interval. To predict the moving obstacle's position at the next time point from the currently predicted position, the methods may update the learned dynamic features of the moving obstacle based on its past trajectory up to the currently predicted position.

Abstract: A smart makeup mirror device includes a main body, a display mirror unit rotatably mounted in the main body, and a speaker. The display mirror unit includes a display module, a makeup mirror, a support frame for fixing the makeup mirror, and a mood lamp mounted on a rear surface of the support frame. The support frame rotates with respect to the main body so that an angle with respect to the makeup mirror and the ground is changed, or rotate in a circumferential direction of the makeup mirror. The display module is oriented horizontally or vertically when the support frame is rotated in the circumferential direction of the makeup mirror. The mood lamp illuminates a mood light toward a floor surface when a rear surface of the display mirror unit is rotated at a specific angle with respect to the main body to face the floor surface.

Abstract: Evaluating intent authoring processes, by a processor in a computing environment. Results are received of a simulated intent labeling effort of a dataset comprising utterances of interactive dialog sessions between agents and clients for a given product or service. Figures of merits for respective algorithms used to perform the simulated intent labeling effort are computed. Each of the respective algorithms are evaluated according to the computed figures of merits; and one of the respective algorithms is implemented for labeling intents of a remaining corpus of the synthesized dataset according to parameters evaluated in the computed figures of merits.

Abstract: A voice assistant device comprises an input to receive data defining an audio command; and processing circuitry to perform an operation defined by the audio command responsive to an activation of the voice assistant device; wherein the activation comprises determining presence of an activation source within an activation region from one or more sensors.

Abstract: Described herein are systems, methods, storage media, and computer programs for tracking a plurality of feature points in a first image and a second image. In one embodiment, a first layer of a first image pyramid for the first image and a first layer of a second image pyramid for the second image are obtained. Based on expected pixel locations of the plurality of feature points in the first layer of the second image pyramid, a feature point is selected from the plurality of feature points. For the feature point, a first pixel in the first layer of the first image pyramid is determined, and a second pixel in the first layer of the second image pyramid is determined, where the first pixel substantially matches the second pixel.

Abstract: A system and method for automatically classifying compartments at a security checkpoint includes receiving a three-dimensional representation of a compartment from an imaging device connected to the computing system, and classifying the compartment into a first category or a second category using a trained neural network that analyzes the three-dimensional representation, wherein compartments classified into the first category are automatically cleared at the security checkpoint and compartments classified into the second category undergo further security checks.

Abstract: A method includes receiving a user object specified by a user. A similarity score is computed using a similarity function between the user object and one or more candidate objects in a database based on respective feature vectors. A first subset of the one or more candidate objects is presented to the user based on the respective computed similarity scores. First feedback is received from the user about the first subset of candidate objects. The similarity function is adjusted based on the received first feedback.

Abstract: A computer-implemented system: at least one processor communicably coupled to at least one nontransitory processor-readable storage medium storing processor-executable instructions or data receives segmentation learning data comprising a plurality of batches of labeled anatomical image sets, each image set comprising image data representative of a series of slices of a three-dimensional bony structure, and each image set including at least one label which identifies the region of a particular part of the bony structure depicted in each image of the image set, wherein the label indicates one of a plurality of classes indicating parts of the bone anatomy; trains a segmentation CNN, that is a fully convolutional neural network model with layer skip connections, to segment semantically at least one part of the bony structure utilizing the received segmentation learning data; and stores the trained segmentation CNN in at least one nontransitory processor-readable storage medium of the machine learning system.

Abstract: The disclosure relates to a reference plate for calibrating and/or checking a deflectometry sensor system, said deflectometry sensor system including an image generation device and a capturing device having at least one capturing element, wherein the reference plate includes a reflective surface, and wherein, for the purpose of checking at least one system parameter of said deflectometry sensor system, the reflective surface is provided with a predefined pattern including markings. A corresponding method for calibrating and/or checking a deflectometry sensor system is moreover indicated.

Abstract: An illustrative embodiment provides a computer implemented method for extracting named entity information from full text includes obtaining text data from a document. The method also includes tokenizing the text data as numbers to produce a tokenized layer. The method also includes creating an embedded layer from the tokenized layer by encoding the text data by indices. The method also includes creating a one-dimensional Xception layer from the embedded layer according to a one-dimensional convolution. The method also includes determining a sequence of classification for the text data according to the one-dimensional Xception layer. The method also includes determining a named entity value from the text data according to the sequence of classification, wherein each sequence of classification predicts one character of the named entity value.

Abstract: A method includes: acquiring a voice signal; sending the voice signal to a host; receiving a key code from the host; converting the key code to an identification code that is identified by the host; and sending the identification code to the host.

Abstract: A system and method for an automated pharmaceutical research data platform comprising a data curation platform which searches for and ingests a plurality of unstructured, heterogenous medical data sources, extracts relevant information from the ingested data sources, and creates a massive, custom-built and intricately related knowledge graph using the extracted data, and a data analysis engine which receives data queries from a user interface, conducts analyses in response to queries, and returns results based on the analyses. The system hosts a suite of modules and tools, integrated with the custom knowledge graph and accessible via the user interface, which may provide a plurality of functions such as statistical and graphical analysis, similarity based searching, and edge prediction among others.

Abstract: Example systems and methods may selection of video frames using a machine learning (ML) predictor program are disclosed. The ML predictor program may generate predicted cropping boundaries for any given input image. Training raw images associated with respective sets of training master images indicative of cropping characteristics for the training raw image may be input to the ML predictor, and the ML predictor program trained to predict cropping boundaries for raw image based on expected cropping boundaries associated training master images. At runtime, the trained ML predictor program may be applied to runtime raw images in order to generate respective sets of runtime cropping boundaries corresponding to different cropped versions of the runtime raw image. The runtime raw images may be stored with information indicative of the respective sets of runtime boundaries.

Abstract: Computer-implemented techniques are provided for machine recognition of gestures and transformation of recognized gestures to text or speech, for gestures communicate in a sign language such as American Sign Language (ASL). In an embodiment, a computer-implemented method comprises: storing a training dataset comprising a plurality of digital images of sign language gestures and an alphabetical letter assigned to each digital image of the plurality of digital images, training a neural network using the plurality of digital images of sign language gestures as input and the alphabetical letter assigned to each digital image as output, receiving a particular digital image comprising a particular sign language gesture, and using the trained neural network to classify the particular digital image as a particular alphabetical letter.

Abstract: A method of image processing in a computing device comprising an object detection system. The method comprises processing a first image frame, a second image frame, and one or more further image frames, the second image frame having been captured subsequent to the first image frame and the one or more further image frames having been captured subsequent to the second image frame. A feature extraction operation is performed on the first image frame and the second image frame. An object detection operation is performed, using feature data from said feature extraction operation, to produce object detection data. At least one parameter of said feature extraction operation, for processing said one or more further image frames, is modified in response to a characteristic of said object detection data.