Abstract: Hybrid natural language understanding (NLU) systems and methods are provided that capitalize on the strengths of the rule-based models and the statistical models, lowering the cost of development and increasing the speed of construction, without sacrificing control and accuracy. Two models are used for intent recognition, one statistical and one rule-based. Both models define the same set of intents, but the rule-based model is devoid of any grammars or patterns initially. Each model may or may not be hierarchical in that it may be composed of a set of specialized models that are in a tree form or it may be just a singular model.

Abstract: A computer implemented method of generating at least one anonymous image, comprises: extracting and preserving at least one real facial region from at least one real image of a real human face, and generating at least one anonymous image comprising a synthetic human face and the preserved at least one real facial region, wherein an identity of the real human face is non-determinable from the at least one anonymous image.

Abstract: A vision-based system for identifying textual sentiment present in a text source image, comprising a camera module adapted to capture the text source image, and a vision-based text analyzing device adapted to analyze the input image, identify a text input string, and determine the sentiment embodied by the text input string, the vision-based text analyzing device is further adapted to revise the text input string to embody an alternate sentiment, the vision-based system has an output display for presenting sentiment classification results and the revised text string via in an augmented reality format.

Abstract: Artificial intelligence based document analysis systems and methods are disclosed. Embodiments of document analysis systems may allow the manipulation of datasets and associated codes by determining representations for these codes or datasets based on a machine learning model. The codes or datasets can then be manipulated using the associated representations.

Abstract: Systems and methods enabling rendering an avatar attuned to a user. The systems and methods include receiving audio-visual data of user communications of a user. Using the audio-visual data, the systems and methods may determine vocal characteristics of the user, facial action units representative of facial features of the user, and speech of the user based on a speech recognition model and/or natural language understanding model. Based on the vocal characteristics, an acoustic emotion metric can be determined. Based on the speech recognition data, a speech emotion metric may be determined. Based on the facial action units, a facial emotion metric may be determined. An emotional complex signature may be determined to represent an emotional state of the user for rendering the avatar attuned to the emotional state based on a combination of the acoustic emotion metric, the speech emotion metric and the facial emotion metric.

Abstract: In an inspection method and apparatus, when thermal image data with respect to cap sealing of a particular container is analyzed and a low confidence score is obtained, products are classified into a user check product by a rejection-process of separating the products, without determining the products to be good products or not good products.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-readable media, for obtaining a first image from a first sensor; detecting a first object within the first image; extracting discriminative features of the first object into a first feature vector; obtaining a second image from a second sensor; detecting a second object within the second image; extracting discriminative features of the second object into a second feature vector; and determining, based on a comparison between the first feature vector and the second feature vector, that the second object is same as the first object.

Abstract: Methods, systems and apparatus, including computer programs encoded on computer storage media. One of the methods includes receiving an audio waveform that includes a respective audio sample for each of a plurality of time steps, processing the audio waveform using an encoder neural network to generate a plurality of feature vectors representing the audio waveform, generating a respective coded representation of each of the plurality of feature vectors using a plurality of vector quantizers that are each associated with a respective codebook of code vectors, wherein the respective coded representation of each feature vector identifies a plurality of code vectors, including a respective code vector from the codebook of each vector quantizer, that define a quantized representation of the feature vector, and generating a compressed representation of the audio waveform by compressing the respective coded representation of each of the plurality of feature vectors.

Abstract: We propose a neural network-based base caller that detects and accounts for stationary, kinetic, and mechanistic properties of the sequencing process, mapping what is observed at each sequence cycle in the assay data to the underlying sequence of nucleotides. The neural network-based base caller combines the tasks of feature engineering, dimension reduction, discretization, and kinetic modelling into a single end-to-end learning framework. In particular, the neural network-based base caller uses a combination of 3D convolutions, 1D convolutions, and pointwise convolutions to detect and account for assay biases such as phasing and prephasing effect, spatial crosstalk, emission overlap, and fading.

Abstract: Methods and systems for a cascading model architecture for providing information on a reply email. Training sample data can be created using a user's incoming reply emails from external computer devices to a user's computer device. A receptivity neural network model can be trained using the training sample data of the reply emails, and a trained receptivity neural network model can be used to determine a receptivity classification for whether new reply emails are positive reply emails or non-positive reply emails. Sample data of non-positive reply emails can be augmented, and an objection identification neural network model can be trained on the augmented sample data of the non-positive reply emails. A trained objection identification neural network model can be used to determine a objection classification for new non-positive reply emails.

Abstract: An artificial document generation method generating a larger set of artificial documents which mimics a smaller set of source documents. The method may include deriving metadata parameters from source documents, each parameter characterizing the source documents and having more than one possible value. The deriving may include: determining which ratio of the source documents has each of the values, defining metadata ratios characteristic of the source documents; training a model, on the source documents, to output artificial documents; and running the model as trained thereby to output artificial documents and overriding at least some words generated by the model in the draft artificial documents. Overriding is configured to ensure that at least some of the ratios characteristic of the smaller set of source documents are retained in the larger set.

Abstract: An information processing apparatus that detects a voice command via a microphone in order to activate the device and execute certain applications. The apparatus comprises a digital signal processor (DSP) and a host controller which are responsible for processing the voice commands. The DSP recognizes and processes voice commands intermittently while the host processor is in a sleep state, thereby reducing the overall power consumption of the apparatus. Further, when the DSP is configured to recognize voice commands intended, only to activate the device, a memory having a sufficiently lower storage capacity suffices.

Abstract: A computer-implemented visual interface for identifying and revealing objects from video-based media provides visual cues to enable users to interact with video-based media. Objects in videos are inferred and identified based upon automatic interpretations of the video and/or audio that is associated with the video. The automatic interpretations may be performed by a computer-implemented neural network. The computer-implemented visual interface is integrated with the video to enable users to interact with the identified objects. User interactions with the visual interface may be through either touch or non-touch means. Information is delivered to users that is based upon the identified objects, including in augmented or virtual reality-based form, responsive to user interactions with the computer-implemented visual interface.

Abstract: Systems and methods are provided for analyzing messages generated by a plurality of computing devices associated with a plurality of users in a messaging system to generate training data to train a machine learning model to determine a probability that a media content item was generated inside an enclosed location or outside, receiving a media content item from a computing device, analyzing the media content item using the trained machine learning model to determine a probability that the media content item was generated inside an enclosed location or outside, determining, based on the probability generated by the trained machine learning model, that the media content item was generated inside an enclosed location, and determining an inside temperature associated with the venue based on messages generated by a plurality of computing devices in a messaging system comprising media content items and temperature information for the venue or a similar venue type.

Abstract: In the present invention, a method for processing an image on the basis of an intra prediction mode and an apparatus therefor are disclosed. Particularly, the method for processing an image on the basis of an intra prediction mode may comprise the steps of: partitioning a block to be processed, on the basis of an intra prediction mode of the block to be processed; and performing intra prediction for the split block to be processed, wherein the direction in which the block to be processed is split is perpendicular to the prediction direction of the intra prediction mode of the block to be processed.

Abstract: Local detail enhancement (LDE) is an imagery contrast enhancement method applied to visible and uncooled long wave imagery. It enhances local spatial detail through the use of a median based high/band pass filter. The generated detail channel is blended with a histogram-equalized version of the image, creating an image that contains both local detail as well as retaining some amount of global intensity. Retaining global intensity coherency allows for easier target acquisition when compared to fully local forms of contrast enhancement.

Abstract: Systems and methods for training a classifier binary model of a natural language understanding (NLU) system are disclosed herein. A determination is made as to whether a text string, with a content entity, includes an obsequious expression. In response to determining the text string includes an obsequious expression, a determination is made as to whether the obsequious expression describes the content entity. The model is trained based on a determination of at least one of: an absence of an obsequious expression in response to determining the obsequious expression describes the content entity; a presence of an obsequious expression in response to determining the obsequious expression describes the content entity; an absence of an obsequious expression in response to determining the obsequious expression does not describe the content entity, and a presence of an obsequious expression in response to determining the obsequious expression does not describe the content entity.

Abstract: A decoder is configured to decode a plurality of texels from a received block of texture data encoded according to the Adaptive Scalable Texture Compression (ASTC) format, and includes a parameter decode unit configured to decode configuration data for the received block of texture data, a colour decode unit configured to decode colour endpoint data for the plurality of texels of the received block in dependence on the configuration data, a weight decode unit configured to decode interpolation weight data for each of the plurality of texels of the received block in dependence on the configuration data, and at least one interpolator unit configured to calculate a colour value for each of the plurality of texels of the received block using the interpolation weight data for that texel and a pair of colour endpoints from the colour endpoint data.

Abstract: A medical picture archive integration system includes a de-identification system that includes a first memory designated for protected health information (PHI), operable to perform a de-identification function is on a DICOM image, received from a medical picture archive system, to identify at least one patient identifier and generate a de-identified medical scan that does not include the at least one patient identifier. The medical picture archive integration system further includes a de-identified image storage system that stores the de-identified medical scan in a second memory that is separate from the first memory, and an annotating system, operable to utilize model parameters received from a central server to perform an inference function on the de-identified medical scan, retrieved from the second memory to generate annotation data for transmission to the medical picture archive system as an annotated DICOM file.

Abstract: An abnormality detection apparatus including a feature extraction circuit configured to extract a feature point and a feature value of a first image, and a feature point and a feature value of a second image, a flow calculation circuit configured to calculate, based on the feature value of the first image, a first abnormality detection circuit configured to detect an abnormality in the first image based on a first optical flow, and to detect an abnormality in the second image based on a third optical flow, and a second abnormality detection circuit configured to detect an abnormality in the first or second image based on a result of a comparison between the second optical flow and a fourth optical flow.