Abstract: Systems and methods are provided for generating training data for a machine-learning classifier. A knowledge representation synthesized based on an object of interest is used to assign labels to content items. The labeled content items can be used as training data for training a machine learning classifier. The labeled content items can also be used as validation data for the classifier.

Abstract: Methods and systems for determining relevance for a new document are described. Existing documents that have a high probability of relevance can be chosen. A vocabulary of words in the existing documents can be built. Each word can be mapped into a vector such that each existing document can be represented by a sequence of vectors and each sentence and/or paragraph in each existing document can be represented by a subsequence of vectors including a subset of the sequence of vectors. Data augmentation can be applied changing an order of the subsequences in order to create additional documents represented by the subsequences. A deep neural network can be trained using the subsequences that represent the existing documents and the subsequences that represent additional documents. The new documents can be trained using a trained deep neural network. A relevant document can be output using the trained deep neural network.

Abstract: A system and method for sequence extraction using screenshot images to generate a robotic process automation workflow is disclosed. The system and method include capturing a plurality of screenshots of steps performed by a user on an application using a processor, storing the screenshots in memory, determining action clusters from the captured screenshots by randomly clustering actions into an arbitrary predefined number of clusters, wherein screenshots of different variations of a same action is labeled in the clusters, extracting a sequence from the clusters, and discarding consequent events on the screen from the clusters, and generating an automated workflow based on the extracted sequences.

Abstract: An image display method applicable to a video conferencing system with a wide-angle webcam is disclosed. The wide-angle webcam is used to capture a panoramic image having an aspect ratio greater than or equal to 2:1. The method includes: framing multiple regions of interest (ROIs) according to the panoramic image, each ROI having at least one of attributes; selecting one from predetermined frame layouts as an output frame layout according to whether to insert a portion of the panoramic image and attributes, positions and the number of the ROIs; and inserting at least one of the portion of the panoramic image and the ROIs into corresponding windows in the output frame layout to form a composite frame according to the attributes of the ROIs.

Abstract: An apparatus that assists an survey of a crop cultivated in each of blocks obtained by dividing a field, comprising: an input unit configured to accept, for an survey executed for the crop, the input of identification information identifying at least one of the surveys, block information indicating the block where the survey has been executed, item information indicating an survey item, and measured values measured at survey positions; and a processing unit configured to cause a transition in the aggregating result to be displayed as a result of the survey, wherein the input unit further accepts the input of a user operation specifying part of the transition of a result of aggregating the input measured values; and of the measured values, the processing unit causes reliability information of the aggregating result of the part to be displayed.

Abstract: Provided is a method of DNN-based image processing by an imaging device. The method comprises obtaining, by the imaging device, at least one input image with a plurality of color channels, simultaneously extracting, by the imaging device, a semantic information from each of the color channels of the at least one input image and a color correlation information from each of the color channels of the at least one input image, and generating, by the imaging device, at least one output image based on the extracted semantic information and the extracted color correlation information.

Abstract: A group to be authenticated in face authentication is efficiently registered in a system. An information processing system includes a face detection unit configured to detect a face from an image in which a plurality of faces of persons are shown, a determination unit configured to determine whether or not the face detected by the face detection unit satisfies a predetermined condition, and a registration information generation unit configured to generate registration information, the registration information being information in which a partial image of each of a plurality of faces that have been determined to satisfy the predetermined condition is associated with an identifier identifying a group to be authenticated in face authentication.

Abstract: Dense feature scale detection can be implemented using multiple convolutional neural networks trained on scale data to more accurately and efficiently match pixels between images. An input image can be used to generate multiple scaled images. The multiple scaled images are input into a feature net, which outputs feature data for the multiple scaled images. An attention net is used to generate an attention map from the input image. The attention map assigns emphasis as a soft distribution to different scales based on texture analysis. The feature data and the attention data can be combined through a multiplication process and then summed to generate dense features for comparison.

Abstract: A method of creating an album. The method includes a setting step of setting a first condition for generating a first page included in a first album and a second condition for generating a second page included in a second album, and a creation step of creating the first album including the first page generated in accordance with the first condition and a common page common to the first album and the second album and creating the second album including the second page generated in accordance with the second condition and the common page. At the creation step, by performing control to make the same a total number of pages of the first album and a total number of pages of the second album, the first album and the second album having the same total number of pages are created.

Abstract: Techniques are described that exclude use of “stop-fingerprints” from media database formation and search query to an automatic content recognition (ACR) systems based on media content fingerprints updated by stop-fingerprint analysis. A classification process is presented which takes in fingerprints from reference media files as an input and produces a modified set of fingerprints as an output by applying a novel stop-fingerprint classification algorithm. Architecture for the distributed stop-fingerprint generation is presented. Various cases, as stop-fingerprints generation for the entire reference database, stop-fingerprints generation for the individual reference fingerprint files, and temporal fingerprint classification obtained through intermediate steps of the temporal fingerprint classification algorithm are presented. A hash-based signature classification algorithm is also described.

Abstract: The present disclosure provides systems and methods that use and/or generate image files according to a novel microvideo image format. For example, a microvideo can be a file that contains both a still image and a brief video. The microvideo can include multiple tracks, such as, for example, a separate video track, audio track, and/or one or more metadata tracks. As one example track, the microvideo can include a motion data track that stores motion data that can be used (e.g., at file runtime) to stabilize the video frames. A microvideo generation system included in an image capture device can determine a trimming of the video on-the-fly as the image capture device captures the microvideo.

Abstract: Dynamically changing a content based on a user-defined context includes receiving, by one or more processors, input data from a user, the input data includes at least one document with an annotated part identifying a first content element, the first content element is associated with a first content type. The one or more processors determine a context information associated with the annotated part and extract the annotated part. A first replacement for the first content element is retrieved from a first data source selected based on the content information. The one or more processors replace the first content element in the at least one document with the first replacement.

Abstract: A method, computer program product and computer system to generate a spatial visualization of topics contained in messages data is provided. A processor retrieves message data associated with a user. A processor determines one or more topics represented by the message data. A processor generates a spatial visualization of one or more user interface elements, where the spatial visualization includes a size and a location for the one or more user interface elements. A processor displays one or more user interface elements corresponding to the one or more topics.

Abstract: A method, computer program product and computer system to generate a spatial visualization of topics contained in messages data is provided. A processor retrieves message data associated with a user. A processor determines one or more topics represented by the message data. A processor generates a spatial visualization of one or more user interface elements, where the spatial visualization includes a size and a location for the one or more user interface elements. A processor displays one or more user interface elements corresponding to the one or more topics.

Abstract: [Object] There is provided a mechanism that makes it possible to efficiently specify an important region of a moving image including a dynamic content. [Solution] An information processor including a control unit that recognizes a motion of an operator with respect to an operation target in a moving image and specifies an important region of the operation target in the moving image on a basis of an operation position of the operator.

Abstract: A computer implemented method of document classification includes receiving a text document. A first classification is generated for the document, and a text corpus is searched for one or more terms from the document. Searched terms having an incidence in the text corpus lower than a threshold incidence are flagged, and at least one classification is generated after removing at least one flagged term from the document. An output is generated if the further classification is different from the first classification.

Abstract: Described is a system for online vehicle recognition in an autonomous driving environment. Using a learning network comprising an unsupervised learning component and a supervised learning component, images of moving vehicles extracted from videos captured in the autonomous driving environment are learned and classified. Vehicle feature data is extracted from input moving vehicle images. The extracted vehicle feature data is clustered into different vehicle classes using the unsupervised learning component. Vehicle class labels for the different vehicle classes are generated using the supervised learning component. Based on a vehicle class label for a moving vehicle in the autonomous driving environment, the system selects an action to be performed by the autonomous vehicle, and causes the selected action to be performed by the autonomous vehicle in the autonomous driving environment.

Abstract: An object is to provide a technique capable of reducing an inter-SoC communication volume. The screen generation device includes a first SoC, a second SoC, and an allocation unit. The allocation unit defines a plurality of superposition sequence layers having a superposition sequence and selected from the plurality of first drawing layers and the plurality of second drawing layers, allocates, among the plurality of superposition sequence layers, a consecutive superposition sequence layer cluster being consecutive two or more superposition sequence layers in the superposition sequence, to the first SoC, and allocates remaining superposition sequence layers being one or more superposition sequence layers other than the consecutive superposition sequence layer cluster to the second SoC.

Abstract: Technologies are provided for determining deficiencies in narrative textual data that may impact decision-making in a decisional context. A candidate text document and a reference corpus of text may be utilized to generate one or more topic models and document-term matrices, and then to determine a corresponding statistical perplexity and probabilistic coherence. The reference corpus may be known or normatively deemed to be epistemically persuasive and adequate with respect to a particular context. Statistical determinations of a degree to which the candidate deviates from the reference normative corpus are determined, in terms of the statistical perplexity and probabilistic coherence of the candidate as compared to the reference.

Abstract: A proactive operations (ProOps) platform is contemplated to facilitate processing data for purposes of turning included information into action, such as to enable operators to proactively manage network operations using information derived from mathematical analysis of raw data collected from network devices.

Abstract: A method and system for analyzing data based on a statistical model, wherein the statistical model is used in one or more contexts without needing intervention of data scientists. This statistical model is parameterized and uploaded in an analytics platform. Parameterizing the statistical model enables end users to select scope, constraints and variables of data analysis. Acceptance indicator of this tool indicates reliability of the model on user selected scope, constraints and variables. Based on user selections, a dynamic table is created which is an input to the statistical model for data analysis. Based on values of this dynamic table, data analysis is performed on stored data on the specific context. The report id generated based on the data analysis which is presented to user as visual output.

Abstract: Techniques are disclosed for detecting the bounds of borderless open tables in fixed-format structured documents, such as PDF documents, and grouping text lines into predicted borderless tables. The target document comprises a set of text lines each having a respective vertical and horizontal position in the target document. A sorted list of the text lines is generated based upon a vertical and horizontal position of each text line in the target document. For each text line in the sorted list, a respective probability that the text line in the sorted list belongs to a borderless table is then determined. According to one embodiment, the probability may be determined using a classifier that may employ a logistic regression algorithm.

Abstract: An automatic guided vehicle (AGV) comprising a mobile base including a drive train and configured to drive the AGV in a self-navigation mode within a facility, a first camera configured to capture first image data of objects within the facility, a second camera configured to capture second image data of objects within the facility, the second camera including a content filter, and a main control module configured to receive the first and second image data from the first and second cameras. The main control module executes a recognition neural network program. The neural network program recognizes targets in the first image data. The main control module also executes a supervisor program under user control. The supervisor program is receives the second image data and recognizes markers attached to targets in the second image data. The supervisor program produces a supervised outcome in which targets to which markers are attached are associated with categories based on user commands.

Abstract: Example embodiments described herein therefore relate to an object-model based event detection system that comprises a plurality of sensor devices, to perform operations that include: generating sensor data at the plurality of sensor devices; accessing the sensor data generated by the plurality of sensor devices; detecting an event, or precursor to an event, based on the sensor data, wherein the detected event corresponds to an event category; accessing an object model associated with the event type in response to detecting the event, wherein the object model defines a procedure to be applied by the event detection system to the sensor data; and streaming at least a portion of a plurality of data streams generated by the plurality of sensor devices to a server system based on the procedure, wherein the server system may perform further analysis or visualization based on the portion of the plurality of data streams.

Abstract: Video and corresponding metadata is accessed. Events of interest within the video are identified based on the corresponding metadata, and best scenes are identified based on the identified events of interest. A video summary can be generated including one or more of the identified best scenes. The video summary can be generated using a video summary template with slots corresponding to video clips selected from among sets of candidate video clips. Best scenes can also be identified by receiving an indication of an event of interest within video from a user during the capture of the video. Metadata patterns representing activities identified within video clips can be identified within other videos, which can subsequently be associated with the identified activities.

Abstract: A video feature extraction method and device are provided. The method includes extracting one or more frames from a video object to obtain one or more frames of images, obtaining one or more shift vectors for each of the one or more frames of images, using each of the one or more shift vectors, taking any pixel in each of the one or more frames of images as a starting point, determining a terminal point directed by the one or more shift vectors from the starting point, and determining an image feature of the one or more frames of images according to a difference between the starting point and the terminal point, and determining a video feature of the video object according to the image feature of the one or more frames of images.

Abstract: A method of delay measurement of a network node device is disclosed. The method includes obtaining a node delay value of a current packet when a preset time period starts. The method further includes determining, based on M+1 boundary values of preset M delay intervals, a delay interval in which the node delay value is located, and adding 1 to a value of a delay segment counter corresponding to the delay interval in which the node delay value is located, where M>1, M is a positive integer. The method further includes obtaining a node delay value of a next packet until the preset time period ends. The method further includes determining a cumulative probability Pacc.j that is greater than or equal to a target probability, and obtaining, as a delay threshold, a node delay value having the target probability.

Abstract: One variation of a method for monitoring occupancy in a work area includes, at a sensor block: transitioning from an inactive state into an active state when an output of a motion sensor indicates motion in a work area; during a scan cycle in the active state, recording an image through an optical sensor at a time, detecting a set of humans in the image, detecting a second set of human effects in the image, predicting a second set of humans occupying but absent the work area based on the second set of human effects, and estimating a total occupancy in the work area at the time based on the set of humans and the second set of humans; and transmitting the total occupancy to a remote computer system for update of a scheduler for the work area.

Abstract: A computer-implemented method for ascertaining a need for predictive maintenance for a microscope system. A microscope system, which an image sensor for recording digital images of a sample, recording digital images during regular operation of the microscope system, and providing a digital image as an input data set to an image analysis system, is provided. At least one feature relating to a malfunction of the microscope system during regular operation is determined, a status signal is produced, and a component group of the microscope system for which a maintenance procedure is necessary is determined.

Abstract: A device control apparatus includes an imaging unit configured to capture an image of an occupant in a vehicle, a first recognition unit configured to recognize a posture of the occupant based on the image captured by the imaging unit, a second recognition unit configured to recognize a state of a hand including at least a shape of the hand of the occupant based on the image captured by the imaging unit, a discrimination processing unit configured to specify a device to be controlled and an operation to be executed based on the posture of the occupant recognized by the first recognition unit and the state of the hand recognized by the second recognition unit, and a controller configured to issue a control command corresponding to the specified device to be controlled and the specified operation to be executed.

Abstract: A method includes training a prediction model to forecast a likelihood of curtailment for at least one wind turbine. The prediction model is trained, by a processor system, using historical information and historical instances of curtailment. The method also includes forecasting the likelihood of curtailment for the at least one wind turbine using the trained prediction model. The method also includes outputting the forecasted likelihood.

Abstract: A pattern finding device of embodiments includes a pattern generator, a pattern storage, a pattern selector, a pattern deleter. The pattern generator generates a group of patterns from data including a plurality of items. The pattern storage stores the group of patterns generated by the pattern generator. The pattern selector selects at least one pattern to be deleted from the group of patterns with reference to an evaluated value indicating a change of an item distribution condition in the group of patterns when at least one pattern which is selected as a candidate is excluded from the group of patterns stored in the pattern storage. The pattern deleter deletes the at least one pattern that is selected by the pattern selector from the pattern storage.

Abstract: The present disclosure is directed toward systems and methods that provide users with efficient and effective user experiences when browsing, selecting, or inspecting content items. More specifically, systems and methods described herein provide users the ability to easily and effectively select multiple content items via a single touch gesture (e.g., swipe gesture). Additionally, systems and methods disclosed herein can allow users to select various content items in a selection interface, preview a content item, and return to the selection interface with the previous selections remaining intact. Still further, systems and methods described herein allow users to transition between a content graphical user interface and a selection interface based on touch gestures with content items. Embodiments of the present invention further provide improved navigability by collapsing views of content items.

Abstract: A method for unsupervised image segmentation based on a background likelihood estimation is described herein. The method includes calculating a distance for each pixel in an input image and transforming each distance into a probability of the distance of belonging to a background of an input image or a foreground of the input image. The method also includes transforming each probability into a log likelihood value to form a unary term and minimizing an energy function including the unary term to obtain a set of foreground labels and a set of background labels.

Abstract: The invention discloses a sentence similarity judgment method, which belongs to the technical field of natural language processing.

Abstract: One variation of a method for monitoring occupancy in a work area includes, at a sensor block: transitioning from an inactive state into an active state when an output of a motion sensor indicates motion in a work area; during a scan cycle in the active state, recording an image through an optical sensor at a time, detecting a set of humans in the image, detecting a second set of human effects in the image, predicting a second set of humans occupying but absent the work area based on the second set of human effects, and estimating a total occupancy in the work area at the time based on the set of humans and the second set of humans; and transmitting the total occupancy to a remote computer system for update of a scheduler for the work area.

Abstract: A method for testing includes capturing a sequence of video images of a sample comprising semen. The sequence of video images is analyzed by a processor so as to compute and output a motile sperm concentration of the sample.

Abstract: A recognition method of pattern feature is provided, where a recognition result thereof is applied to optical proximity correction, the method includes: providing a plurality of reference images with a reference pattern feature; recognizing and classifying the reference images by an image recognition device, and storing the recognition result; comparing the image with the actual pattern feature with the stored recognition result by the image recognition device to recognize and classify the image with the actual pattern feature; and calculating an angle feature value and/or a distance feature value of the actual pattern feature by the image recognition device according to a classification result to obtain the recognition result of the pattern feature.

Abstract: Embodiments of the present disclosure relate to a method, a device and a computer readable medium for generating an image tag. According to the embodiments of the present disclosure, an index value of an image is determined based on contents of the image, similarities between a plurality of images is determined based on index values of the plurality of images, and thereby tags are generated for images. According to the embodiments of the present disclosure, images is further grouped depending on similarities between them.

Abstract: Aspects of the disclosure provide for mechanisms for character recognition using neural networks. A method of the disclosure includes assigning, using a first-level classifier of a grapheme classifier, an input grapheme image to a first grapheme cluster of a plurality of grapheme clusters, wherein the first grapheme cluster comprises a first plurality of graphemes; selecting, by a processing device, a classifier from a plurality of second-level classifiers of the grapheme classifier based on the first grapheme cluster, wherein the selected classifier is trained to recognize the first plurality of graphemes; and processing the input grapheme image using the selected classifier to recognize at least one character in the input grapheme image.

Abstract: A method that incorporates teachings of the subject disclosure may include, for example, determining, by a system comprising a processor, more common features of a plurality of images according to similarity matrices indicating relative similarities between instances of common features occurring within multiple images of the plurality of images, defining, by the system, cluster groups associated with the more common features, where each cluster group comprises cluster images of the plurality of images, and where the more common features are present in each the cluster images, and performing, by the system, quality-based filtering on the cluster images to identify a target cluster image to represent the cluster images for each of the cluster groups. Other embodiments are disclosed.

Abstract: Techniques are disclosed for generating a low-dimensional representation of an image. An image driver receives an image captured by a camera. The image includes features based on pixel values in the image, and each feature describes the image in one or more image regions. The image driver generates, for each of the plurality of features, a feature vector that includes values for that feature corresponding to at least one of the image regions. Each value indicates a degree that the feature is present in the image region. The image driver generates a sample vector from each of the feature vectors. The sample vector includes each of the values included in the generated feature vectors.

Abstract: Implementations of the disclosure provide a method comprising generating, by a processing device, a group repository in view of a plurality of image repositories comprising image manifests. An image manifest comprising an application image and an image platform specifier specifying platform resources for executing the application image from the image repositories is identified. The image manifest is clustered into one or more group members of the group repository in view of the image platform specifier. Each group member references at least a key and a value associated with the key. The key references the image manifest and the value references a manifest list describing a plurality of platforms to execute the application image associated with the image manifest. Thereupon, a data object to redirect a client device to a location comprising the one or more group members of the group repository is published.

Abstract: Users desiring to generate videos from video clips may want to locate moments of interest within the video clips. A system and method described herein may be configured to provide recommendations of moments of interest within video clips post capture of the video clips. User accounts associated with users of the system may include preference information that defines user preferences with respect to values of attributes of video clips. Moments of interest may be identified within individual video clips when the individual video clips have at least one value of at least one attribute specified by the user preferences. Recommendations of identified moments of interest may be provide to users.

Abstract: Feature information characterize features of video clips may be obtained. A given video clip may be selected as a segment of a video edit. Other video clips may be iteratively selected as other segments of the video edit based on the feature information of the video clips and recommended feature information of the segments. Recommended feature information of a particular segment may be obtained by processing feature information of a previously selected video clip through a trained recurrent neural network. Video edit information defining the video edit may be generated. The video edit may include the selected video clips as the segments of the video edit.

Abstract: A method for determining a longest common subsequence in a plurality of text strings. The method comprises: separately converting a plurality of text strings into word sequences (S100); classifying the word sequences (S400); and performing longest common subsequence computation on every class (S500). The time needed by LCS computation can be saved by classifying text strings.

Abstract: A method for retrieving an image-text block from a web page is provided, which comprises: retrieving an image node; filtering the image node to obtain candidate image nodes; traversing, for each of the candidate image nodes, a node in sequence toward an ancestor node of the candidate image node in a preset maximum traversal depth until an ancestor node with a text is visited, using the ancestor node with the text as a candidate image-text block; clustering the candidate image-text blocks based on hash values of the path information of the candidate image-text blocks; and determining, for each image-text block cluster, a common ancestor node of the candidate image-text blocks within the image-text block cluster based on the path information of the candidate image-text blocks, and determining path information of the image-text block cluster based on the common ancestor node.

Abstract: A method includes: receiving training data comprising a plurality of training data items, each training data item labelled under a respective class and comprising a elements arranged in conformity with a structured representation having an associated coordinate system; determining patches of the training data, each patch comprising a subset of the elements of a respective training data item and being associated with a location within the co-ordinate system of the structured representation; and initialising a set of parameters for a Gaussian process. The method further includes iteratively: processing pairs of the determined patches, using a patch response kernel to determine patch response data; determining, using the patch response data, entries of a covariance matrix; and updating the set of parameters in dependence on the determined entries of the covariance matrix.

Abstract: The present disclosure relates to systems and methods for generating headshots from a plurality of still images. In one implementation, the system may include a memory storing instructions and a processor configured to execute the instructions. The instructions may include instructions to receive a plurality of still images from one or more video feeds, score the plurality of images along a plurality of dimensions based on a scale, rank the plurality of images using at least one of a composite score or at least one of the dimensions, select a subset of the plurality of images using the ranking, and construct at least one headshot of the user from the subset of the plurality of images.

Abstract: In an embodiment, a user equipment (UE) recognizes a set of faces within a set of media files stored on the UE using facial recognition. The UE identifies a set of prevalent faces based on a set of criteria including a prevalence of one or more faces among the set of media files. The UE scans real-time media using facial recognition to determine whether any prevalent faces from the set of prevalent faces are present in the real-time media. The UE performs an action based on whether the scanning detects any prevalent faces from the set of prevalent faces in the real-time media. By way of example, the action may include adding one or more enhancement effects to the real-time media, authorizing a communicative operation to proceed, authorizing access to the UE, or any combination thereof.