Abstract: A method of representing a space of handwriting stroke styles includes representing writer-, character- and writer-character-level style variations within a recurrent neural network (RNN) model using decoupled style descriptors (DSD) that model the style variations such that character style variations depend on writer style.

Abstract: Disclosed are method and electronic components for: i) electronically extracting a sequence of values from a measurement signal corresponding to a position of a moving object, wherein the sequence of values indicates the position of the moving object at corresponding time increments; ii) electronically determining at least one of an estimate for a velocity of the moving object and an estimate for an acceleration of the moving the object based on a plurality of the values in the sequence of values; and iii) electronically correcting a value in the sequence of values to substantially reduce the effect of processing and signal delays based on one or both of the velocity and acceleration estimates.

Abstract: A system and method for integrating machine learning algorithms to enrich content items in a content management system. The content management system includes at least one processor, a transformation engine to execute one or more transformations on content items stored in the content management system, and a machine learning services to apply a machine learning algorithm to the content items based on the one or more transformations.

Abstract: A method may include receiving, by a first computing device, a positional message from a second computing device. The positional message may indicate a position and an accumulated error of the indicated position corresponding to the second computing device. The accumulated error of the second computing device may be compared to an accumulated error of the first computing device in which the first and the second accumulated errors respectively represent degrees of uncertainty regarding respective positions and orientations of the first and second computing devices that increase over time. Responsive to the second accumulated error being less than the first accumulated error, a distance and an orientation of the first computing device relative to the second computing device may be assessed and a position of the first computing device in the environment may be updated based on the distance and the orientation.

Abstract: Systems, methods, and software are disclosed herein for automating the editing of documents based on ink gestures via an LLM integration in various implementations. In an implementation, a computing device receives an ink gesture made by a user with respect to a document displayed in the user interface of an application. The ink gesture includes ink strokes made on a portion of the document. The computing device generates a prompt for an LLM to obtain suggested revisions to the document, wherein the prompt includes an image of the ink strokes made on the portion of the document. The prompt also includes a document tree indicative of a structure of the document. The computing device surfaces a suggested revision generated by the LLM in response to the prompt in the user interface.

Abstract: Systems and methods are provided for obtaining characterizations of paths to be traversed, such as foot paths. A scanning tool may be configured to capture information or data characterizing aspects of such a path. The scanning tool may comprise multiple sensors for capturing image/visual data from multiple perspectives, as well as for capturing data reflecting physical features or conditions of the path. Such information can be combined and quantified or otherwise characterized to provide insight into micromobility zones.

Abstract: A document editor is configured to leverage a file format which defines sections of content in a dynamic tree structure. The dynamic tree structure defines sections in an arbitrarily ordered sequence of sibling nodes where each section may be atomic. Using this dynamic tree structure, the document editor can dynamically render the content of the sections and provide a number of enhanced functions to simplify the drafting and management of legal documents.

Abstract: A method in an electronic device includes receiving, by a flexible display carried by a blade assembly that is slidably coupled to a device housing and movable between an extended position and a retracted position, user input. The method then delivers, by a translation mechanism in response to the user input, haptic feedback by causing the blade assembly to translate relative to the device housing with an oscillatory motion.

Abstract: The embodiments herein relate to a system and a method identifying and generating an alert, using a deep learning model, for atypical events during an activity on an electronic whiteboard. The system includes a user device associated with a user, and an atypical event detecting server. The atypical event detecting server (i) receives one or more canvases at concurrent sessions, (ii) annotates the one or more canvases, (iii) detects historical atypical events from the annotated one or more canvases, (iv) trains the deep learning model by correlating the historical atypical events, historical bounding boxes with historical canvases in historical sessions, (v) processes the one or more canvases by determining a bounding box around each atypical event, and (vi) generates an alert for identified atypical events using an event record table.

Abstract: Provided are a control system and a control method for a work machine, by which a bucket shake operation can be performed and a load applied to a vehicular body can be reduced. The control system for a work machine includes: a rear frame; a front frame connected to the rear frame to be bendable with respect to the rear frame; a bucket that is operable with respect to the front frame; an actuator that drives the bucket; a sensor that detects a relative position between the rear frame and the front frame; and a work implement controller that controls the actuator. The work implement controller receives an input of a result of detection by the sensor, and controls an operation of the actuator based on the result of detection by the sensor.

Abstract: Examples of generating a map for an indoor space are described. In one example, a raw digital representation of the indoor space is obtained and preprocessed by at least one of marking a region-of-interest (ROI) in the raw digital representation and classifying the indoor space into a space-category to obtain a preprocessed representation. Using the preprocessed representation, a skeletal map is generated including indicators to identify elements of the indoor space. Revision inputs are received to modify an erroneous indicator from amongst the multiple indicators. The erroneous indicator is revised to a modified indicator and the modified indicator and unmodified indicators are used to create a modified skeletal map which is usable for localizing a mobile device in the indoor space.

Abstract: A unified data library is referred to by a surveillance satellite group to track a flying object, a surveillance ground facility to control the surveillance satellite group, a communication satellite group to transfer flying object information acquired by the surveillance satellite group, a communication ground facility to control the communication satellite group, a coping asset to cope with the flying object, and a coping ground facility to control the coping asset. The unified data library includes a database having stored therein orbit information of the surveillance satellite group, orbit information of the communication satellite group, position information of the coping asset, and a plurality of flying path models having flying paths of the flying object modeled therein.

Abstract: A method of selecting accessibility plugins for disabled users is disclosed. In one example, the method includes determining accessibility requirements of a user to access a website. The method then selects, without user intervention, one of many accessibility plugins to satisfy the accessibility requirements of the user to access the website. Here, each one of the accessibility plugins has an accessibility requirement different from that of another accessibility plugin. The method then installs, without user intervention, the selected accessibility plugin to facilitate use of the website by the user.

Abstract: A map information update method includes: obtaining one or more projection relationships; obtaining, for each projection relationship, reprojection error information; calculating, for each of one or more landmarks, a first sum value based on all items of reprojection error information associated with the landmark; calculating, for each of one or more keyframes, a second sum value based on all items of reprojection error information associated with the keyframe; inferring from the first sum value, for each landmark, a position information update value of an item of position information about the landmark, and updating the item of position information about the landmark using the position information update value; and inferring from the second sum value, for each keyframe, a pose information update value of an item of pose information about the keyframe, and updating the item of pose information about the keyframe using the pose information update value.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that provides a subset of the set of snapping guides that excludes snapping guides. In particular, in some embodiments, the disclosed systems identify a set of objects within a viewport and further determine one or more at least partially obscured objects within the viewport. Furthermore, in some embodiments the disclosed systems receive a user interaction to modify the object and further determine a set of snapping guides to aid in modifying the object based on the user interaction. Moreover, in some embodiments the disclosed systems provide a subset of the set of snapping guides and excludes snapping guides based on the one or more at least partially obscured objects.

Abstract: In some implementations, there is provided a method including identifying, from an electronic drawing, at least one object and at least one object location in at least one user intention for a user interface that is responsive across a plurality of screen sizes, wherein the at least one object and the at least one object location are identified using a machine learning model; creating responsive rules for the at least one object and at least one object location detected in the at last one user intention; and rendering, based on the responsive rules, the user interface, such that the responsive rules configure content layout in the user interface in response to a screen size displaying the user interface. Related systems, methods, and articles of manufacture are also disclosed.

Abstract: Use of a satellite network as a source of image data for detection of off-road obstacles is provided. Image data from a satellite network is received to an OBU of a vehicle via a transceiver of the vehicle. The image data is related to an off-road location to be traversed by the vehicle. A navigation map indicating locations of any obstacles detected as being present based on an analysis of changes in the image data over time is displayed in an HMI of the vehicle.

Abstract: Present invention describes a computer-implemented method for managing content to be rendered in a webpage. A web server receives a request to access a webpage. A user identifier or a device identifier is extracted from the request. The web server transmits a request for a Self Sovereign Identity (SSI) to a gatekeeper server using the identifier. The web server receives the SSI generated based on a propensity score indicating extent to which the user has propensity for releasing user's data to a digital platform. The web server extracts data about content preferences, user characteristics, or browsing history from the SSI based on data related to privacy of a user associated with the user identifier. using the data, a content item is selected to fill a content slot on the webpage. The web server configures the webpage such that the selected content item fills the content slot.

Abstract: The present disclosure provides an autonomous cruising system capable of improving an accuracy of identifying description of a sign. The autonomous cruising system includes processing circuitry. The processing circuitry acquires a first image including a buoy from a camera installed in a ship. The processing circuitry identifies a position of the buoy inside the first image. The processing circuitry acquires a second image corresponding to a partial area of the first image including the position of the buoy, and the second image is higher in resolution than the first image. The processing circuitry identifies description of a sign of the buoy based on the second image.

Abstract: A method of identifying a webpage, a device, and a medium are provided, which relate to a field of an artificial intelligence technology, in particular to fields of deep learning, knowledge graph and other technologies. The method of identifying the webpage includes: acquiring structural data of a target webpage, a first association relationship between the target webpage and a historical webpage, and historical graph data for the historical webpage; determining target graph data for the target webpage and the historical webpage based on the structural data of the target webpage, the first association relationship and the historical graph data; determining a similarity between the target webpage and the historical webpage based on the target graph data; and determining a category of the target webpage based on a category of the historical webpage and the similarity.