Abstract: A crowd motion simulation method is provided based on real crowd motion videos. The method includes framing the videos and storing the framed videos into continuous high-definition images, generating a crowd density map of each image, and accurately positioning an individual in each density map to obtain the accurate position of each individual. The method also includes correlating the positions of each individual in different images to form a complete motion trajectory, and extracting motion trajectory data; and quantifying motion trajectory data, defining training data and data labels, and calculating data correlation. The method further includes building a deep convolutional neural network, and inputting the motion trajectory data for training to learn crowd motion behaviors; and randomly placing a plurality of simulation individuals in a two-dimensional space, testing a prediction effect of the deep convolutional neural network, adjusting parameters for simulation, and drawing a crowd motion trajectory.

Abstract: According to one embodiment, a method, computer system, and computer program product for screen sharing latency detection is provided. The embodiment may include detecting an initiation of a screen sharing session during a web conference. The embodiment may further include adding a timestamp to one or more frames of a shared screen during the screen sharing session. The embodiment may also include transmitting the one or more frames from a sharing participant to a viewing participant during the screen sharing session. The embodiment may further include calculating a time delay between the transmission and a display of the one or more frames on a graphical user interface of the viewing participant. The embodiment may also include displaying the time delay and a frame of the one or more frames corresponding to the time delay on a graphical user interface of the sharing participant.

Abstract: A resource dependency system displays two dynamically interactive interfaces in a resource dependency user interface, a hierarchical resource repository and a dependency graph user interface. User interactions on each interface can dynamically update either interface. For example, a selection of a particular resource in the dependency graph user interface causes the system to update the dependency graph user interface to indicate the selection and also updates the hierarchical resource repository to navigate to the appropriate folder corresponding to the stored location of the selected resource. In another example, a selection of a particular resource in the hierarchical resource repository causes the system to update the hierarchical resource repository to indicate the selection and also updates the dependency graph user interface to display an updated graph, indicate the selection and, in some embodiments, focus on the selected resource by zooming into a portion of the graph.

Abstract: In one embodiment, a method includes rendering a first output image of an XR assistant avatar within a first environment associated with a first XR application for displays of a first extended-reality (XR) display device, wherein the XR assistant avatar has a first form according to a first rendering specification associated with the first XR application and the XR assistant avatar is interactable by a first user to access an assistant system, receiving an indication that the first user is switching from the first XR application to a second XR application, accessing a second rendering specification associated with the second XR application, and rendering a second output image of the XR assistant avatar within a second environment associated with the second XR application for displays of a second XR display device, wherein the XR assistant avatar is rendered to have a second form according to the second rendering specification.

Abstract: Techniques for animatronic design are provided. A plurality of simulated meshes is generated using a physics simulation model, where the plurality of simulated meshes corresponds to a plurality of actuator configurations for an animatronic mechanical design. A machine learning model is trained based on the plurality of simulated meshes and the plurality of actuator configurations. A plurality of predicted meshes is generated for the animatronic mechanical design, using the machine learning model, based on a second plurality of actuator configurations. Virtual animation of the animatronic mechanical design is facilitated based on the plurality of predicted meshes.

Abstract: In an information processing method, a first key frame is obtained. The first key frame includes initial posture data of a target virtual character. The initial posture data corresponds to an initial posture. Target posture data of the target virtual character is determined by inputting the initial posture data and a target task to a policy network trained by reinforcement learning. The target task is set for the target virtual character to perform. An output of the policy network indicates the target posture data that corresponds to a target posture of the target virtual character. At least one force to be acted on at least one first joint of the target virtual character is determined according to the initial posture data and the target posture data. The initial posture of the target virtual character is adjusted to the target posture by applying the at least one force.

Abstract: The present disclosure is an apparatus and a method for providing a precise motion estimation learning model including, a database unit which stores a standard dataset labeled according to a first number of key points, an animation dataset labeled according to a second number of key points which is larger than the first number, and a photorealistic dataset having the second number of key points, a standard learning unit which learns the standard dataset for motion estimation to generate a standard learning model, an animation learning unit which retrains the animation dataset based on a weight of the standard learning model to generate an animation learning model, and a motion estimation learning unit which trains the photorealistic dataset based on the weight of the animation learning model to finely tune to generate a precise motion estimation learning model.

Abstract: Data characterization techniques in an information processing system environment are disclosed. In one example, at least one processing device is configured to obtain data associated with execution of at least one of a plurality of applications in an information processing system. The processing device extracts features from the obtained data, and then selects a reduced subset of features from the extracted features for use in a machine learning classification process configured to determine an intent of the obtained data.

Abstract: A query session system and method is operable to determine a current location of a consumer conversation acquisition system when the consumer conversation acquisition system is a mobile electronic device or determine a current operation of the consumer conversation acquisition system when the consumer conversation acquisition system is stationary. Stored state information corresponding to the determined location or operation is accessed that identifies one of a receptive state of the consumer, an unreceptive state of the consumer, or optionally an indeterminate state of the consumer. The query session is presented to the consumer when the consumer is the receptive state. A query session presents a series of audible questions to the consumer that pertain to a subject media content event that the consumer has previously consumed. Responses of the consumer to each one of the presented audible questions of the query session are acquired and are saved.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing at least one program, and a method for performing operations comprising: receiving, by a client device associated with a first user, a communication from a second user; retrieving, from the communication, a movement vector representing three-dimensional (3D) movement of a set of skeletal joints of the second user; receiving, by the client device associated with the first user, input that selects a 3D avatar; and animating, based on the movement vector, the 3D avatar to mimic the 3D movement of the set of skeletal joints of the second user.

Abstract: An image display method includes displaying, on a display surface, a first image based on first image data from a first input source; and establishing a correspondence between a feature of a first marker and the first input source when it is detected that the first marker is placed in a detection area included in the display surface while the first image is displayed on the display surface.

Abstract: This disclosure generally relate to a method and system for mapping application dependency information. The present technology relates techniques that enable user-adjustable application dependency mapping of a network system. By collecting internal network data using various sensors in conjunction with external user inputs, the present technology can provide optimized application dependency mapping using user inputs.

Abstract: This application provides a display method and an electronic device. When the electronic device switches from a screen-off mode to a lock-screen mode, the electronic device may perform gradual expansion from a last image frame displayed in a screen-off interface, and in a gradual expansion process, successively play a transition animation during switching from the screen-off interface to a lock-screen interface.

Abstract: Implementations relate to dynamically adapting a given assistant output based on a given persona, from among a plurality of disparate personas, assigned to an automated assistant. In some implementations, the given assistant output can be generated and subsequently adapted based on the given persona assigned to the automated assistant. In other implementations, the given assistant output can be generated specific to the given persona and without having to subsequently adapt the given assistant output to the given persona. Notably, the given assistant output can include a stream of textual content to be synthesized for audible presentation to the user, and a stream of visual cues utilized in controlling a display of a client device and/or in controlling a visualized representation of the automated assistant. Various implementations utilize large language models (LLMs), or output previously generated utilizing LLMs, to reflect the given persona in the given assistant output.

Abstract: A system associated with a telecommunications network is in communication with a wireless device and an HMD device. The system obtains image data that depicts the wireless device while a user is wearing the HMD device. The wireless device and the HMD device are co-located in an area of the telecommunications network. The system can receive parameter data generated by one or more sensors of the wireless device. The system can generate mixed reality data based on the image data and the parameter data. The mixed reality data includes an immersive view of a computer-generated virtual environment including a virtual image of the wireless device and the virtual image depicts a real-world view of the wireless device and simulates the wireless device based on the parameter data. The system can also cause the HMD device to display the immersive view to the user wearing the HMD device.

Abstract: A wearing simulation device includes a first animation generation unit that generates a first animation indicating a change in a movement of a body and a surface shape of the body from a second posture to a first posture, a second animation generation unit that generates a second animation indicating a change in a movement of the body and a surface shape of the body in a continuous movement, a third animation generation unit that generates a third animation by connecting the first animation and the second animation, and a simulation execution unit that makes the body wear a clothing model in at least one frame from beginning of the third animation, deforms the clothing model so as to follow the change in the movement of the body and the surface shape of the body in the frame after wearing, and simulates a shape change of the clothing model.

Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for generating insights for video games. The method includes gathering information regarding a player for a plurality of video games, the information comprising at least one of in-world state data, player action data, player progression data, and/or real-world events relevant to each video game. The method also includes tracking events in at least one video game of the plurality of video games, the events comprising an action event or a standby event. The method also includes determining that an event of the tracked events is an action event. The method also includes generating insights regarding the action event based on the information gathered regarding the player, the insights for improving the player's performance in the video game. The method also includes relaying the insights to the player to improve the player's performance in the video game.

Abstract: File system manipulation using machine learning is described. Access to a machine learning system is obtained. A connection between a file system and an application is structured. The connection is managed through an application programming interface (API). The connection provides two-way data transfer through the API between the application and the file system. The connection provides distribution of one or more data files through the API. The connection provides enablement of processing of the one or more data files. The processing uses classifiers running on the machine learning system. Data files are retrieved from the file system connected through the interface. The file system is network-connected to the application through the interface. The data files comprise image data of one or more people. Cognitive state analysis is performed by the machine learning system. The application programming interface is generated by a software development kit (SDK).

Abstract: A non-transitory computer readable medium storing computer executable instructions which, when executed by processing circuitry, cause the processing circuitry to acquire, from a first sensor, data related to a face of a performer; provide first data, that is generated based on the data, to a classifier; receive, from the classifier, specific facial expression data indicating one specific facial expression among a plurality of predetermined specific facial expressions on the basis of the first data; and select, for display output, a specific facial expression corresponding to the specific facial expression data received from the classifier.

Abstract: Disclosed is a system that streams true three-dimensional (“3D”) image data over a data network in a manner that preserves the dimensionality and detail of a dynamic and changing 3D scene. The system generates the 3D image data to represent the 3D scene, and streams different set of the 3D image data that are within different viewing frustums requested by different devices. The system generates updates to the 3D image data based on changes occurring at different parts of the 3D scene. The system streams a first update to the first device in response to image data updated by the first update being within the first device's viewing frustum, and streams a second update to the second device in response to image data updated by the second update being within the second device's viewing frustum.

Abstract: Methods and systems are disclosed for performing operations for transferring motion from one real-world object to another in real-time. The operations comprise receiving a first video that includes a depiction of a first real-world object and extracting an appearance of the first real-world object from the video. The operations comprise obtaining a second video that includes a depiction of a second real-world object and extracting motion of the second real-world object from the second video. The operations comprise applying the motion of the second real-world object extracted from the second video to the appearance of the first real-world object extracted from the first video. The operations comprise generating a third video that includes a depiction of the first real-world object having the appearance of the first real-world object and the motion of the second real-world object.

Abstract: Methods and apparatus are disclosed for video transmission. In one example, computer-readable storage media store instructions cause a processor to: generate first motion data; distribute, toward terminal devices of a plurality of viewers via a communication line, the first motion data; receive a web page; receive first operation data from a user interface; generate a second video related to a computer-implemented game on the basis of the first operation data by using the received web page; distribute the second video toward the terminal devices of the plurality of viewer; receive viewer data regarding a plurality of viewers; extract a selected game object out of a plurality of game objects to be used in the game; calculate a control parameter related to the selected game object on the basis of the viewer data; generate the second video including the selected game object; and distribute the second video toward the terminal devices.

Abstract: Techniques are disclosed for systems and methods to provide dynamically adjusted instrumentation for improved user convenience. In one example, the dynamically adjusted instrumentation provides a virtual gauge comprising a plurality of segments, wherein each segment is associated with a corresponding range of values for a monitored condition; receives a first value within a first one of the range of values; renders on a user display the first value with a first one of the segments associated the first range while excluding from the user display at least a portion of a second one of the segments associated with a second one of the range of values; receives a second value associated with the second range of values; and renders on the user display the second value with the second segment while excluding from the user display at least a portion of the first segment.

Abstract: A method including defining, in a buffer, particles having initial positions in an absolute coordinate system independent of a graphical user interface (GUI) in which the particles are renderable. The method also includes assigning memory ranges within the buffer to corresponding ones of the particles. The method also includes generating, in the memory ranges, updated positions for the particles. The method also includes determining, in the memory ranges and from a combination of the initial positions and the updated positions, corresponding vertices for each of the particles. The method also includes creating, from the corresponding vertices, corresponding particle trails for the particles. The method also includes storing the corresponding particle trails in the memory ranges associated with the particles.

Abstract: A mechanical computer-aided design (MCAD) model representing an object is received. The MCAD model contains a surface with a face defined therein. Deformation of the face is obtained in a simulation based on the MCAD model. The surface is defined by Non-Uniform Rational Basis Spline patches and mapped to a two-dimensional (2-D) parametric grid. The 2-D grid contains a first group of grid points representing the face and a second group of grid points representing outside of the face. The deformation of the face is applied to the first group of grid points. The deformation is extrapolated to the second group of grid points. An updated MCAD model representing a deformed object is generated using the 2-D grid associated with the applied deformation and the extrapolated deformation.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for updating an avatar status for a user of a messaging system. The program and method provide for receiving, by a messaging application running on a device of a user, a request to identify at least one object depicted in an image captured by a device camera; determining, in response to receiving the request, an attribute of an object depicted in the image; selecting, from plural candidate avatar poses for an avatar of the user, an avatar pose corresponding to an activity that relates to the attribute of the object; and displaying the selected avatar pose for the user.

Abstract: The present invention relates to a joint automatic audio visual driven facial animation system that in some example embodiments includes a full scale state of the art Large Vocabulary Continuous Speech Recognition (LVCSR) with a strong language model for speech recognition and obtained phoneme alignment from the word lattice.

Abstract: A method or system for 3D rendering of map features on a client device. The client device receives a map tile and associated non-flat terrain data from a mapping server. The map tile represents a geographic area and features an object with a geometric base and height value. The terrain data gives elevation values for ground points. Using this data, the device's processors select a sample point on the map feature, determine its ground elevation, and calculate the feature's top surface elevation by adding the height value. Vertex ground elevations for the map tile's vertices are also determined, considering terrain variations. Vertex height values are calculated using these ground elevations and the top surface elevation. The map feature is then rendered in 3D, complete with vertical edges and a top surface, and displayed on the device's screen.

Abstract: The systems and processes described herein can provide dynamic and realistic route generation based on actual route data within the game environment. The system provides for generating a route database for use with a sports simulation game application. The present disclosure also provides for generation of routes during runtime of the game application. The route generation system can help address the problem of generating realistic and lifelike routes based on real life movements of athletes.

Abstract: A skeleton model update apparatus, a skeleton model update method, and a program capable of making natural a motion of a skeleton model at a time of occurrence of a collision, compared with an existing technology are provided. An initial position determination section identifies a position to which one or each of a plurality of given nodes included in a skeleton model is to move. A posture update section updates a posture of the skeleton model by executing inverse kinematics computing on the basis of the position to which the one or each of the plurality of given nodes is to move. At a time of occurrence of a collision to one or a plurality of nodes included in the skeleton model, the posture update section updates the posture of the skeleton model by executing the inverse kinematics computing taking into account of an influence of the collision on the one or the plurality of nodes.

Abstract: Methods and systems are provided for selecting a viewport into a video game for a spectator viewing a video game played by a player. The method includes identifying a plurality of virtual cameras for providing a plurality of viewports into scenes of the video game. The method includes accessing a spectator playbook, the spectator playbook is stored in association with a profile of the spectator. The spectator playbook identifies viewing history of the spectator for types of video games viewed by the spectator. The method includes accessing a player playbook, the player playbook is stored in association with a profile of the player. The player playbook identifies performance of the player for types of video games played by the player. The method includes accessing gameplay data for the video game played by the player. The method includes selecting a viewport from the plurality of viewports into the video game.

Abstract: A talking head digital identity immutable dual authentication method for use over a distributed network, comprising: downloading talking head and talking head show files from nodes of a distributed network; downloading hash values of a talking head and talking head show from a blockchain; sending a hash of a publisher's identification from the blockchain to a name lookup service; retrieving and confirming the identity of the publisher; recalculating hash values of the talking head and talking head show; comparing the recalculated hash values of the talking head and talking head show with the hash values of the talking head and talking head show retrieved from the blockchain; incorporating a watermark into the talking head show; starting playback of the talking head show if the hash values received from the blockchain match the recalculated hash values of the talking head and talking head show retrieved from nodes of the distributed network.

Abstract: A method for locating a center of rotation of an articulated joint connecting two bones or set of bones of an upper or lower limb of a user, including performing a series of repetitive movements of sweeping one of the bones or set of bones around the joint, and simultaneously acquiring 3D positions of the bone or set of bones during said series, thereby obtaining a 3D cloud of points, computing a point referred to as center point, said center point being a searching point of the 3D searching space for which the standard deviation is the lowest considering the set of distances between the searching point and each point of the 3D cloud of points, transforming the 3D cloud of points into a plane, projecting the center point on said plane, thereby obtaining the center of rotation of the joint.

Abstract: A graphical user interface renders a display on a display screen that include a preview image described by contents of an input file. When the user is satisfied with the preview image, the input file is automatically converted into a single output scalable vector graphic (SVG) compliant file. Various actions can be performed with the single output SVG compliant file.

Abstract: An autonomic method for the comprehensive profiling of near or real time representations of time sequenced, synchronized, characterized business activity by any entity within a group of commercially related subscribing business partners, for the purpose of creating a near or real time universal business activity mosaic. An autonomic method within a group of commercially interrelated businesses to utilize a universal business activity mosaic to render a virtual customer storefront, whereby a business may discretely witness in time and character the sale of its own assets and services either fully or partially comprising those sold to anybody of related intermediate or end customers for the purpose of purchasing, selling, financing, warehousing or physically transporting assets on demand.

Abstract: Systems and methods for archetype-based generation of Artificial Intelligence (AI) characters are provided. An example method includes receiving at least one keyword describing an AI character, where the AI character is generated by an AI character model in a virtual environment; selecting, based on the at least one keyword, an archetype from a plurality of archetypes; acquiring at least one parameter of the AI character model, where the at least one parameter corresponds to at least one feature of the AI character; determining, based on the archetype, at least one value for the at least one parameter; and assigning the at least one value to the at least one parameter.

Abstract: Imaging devices may capture images of a user premises. The images may be analyzed and processed by a television receiver to determine a scene associated with the user premises. Information indicative of the scene may be transmitted to a service provider system. A content item is received by the television receiver from the service provider system, where the content item is determined based on the information indicative of the scene. The television receiver outputs the content item for presentation to a user device.

Abstract: Systems and methods for providing a network for generating, sharing, and viewing artificial intelligence (AI) characters are provided. An example method includes providing a web-based interface enabling a user to generate and modify a template associated with an AI character generated by an AI character model, where the template includes parameters of the AI character model; receiving at least one value for at least one parameter of the AI character model; receiving a first request to store the template in a data store; storing the template in the data store and attributing the template to an account associated with the user; receiving, from the user, a second request to allow access to the template by at least one further user; and providing the access to the template to the at least one further user to enable the at least one further user to view and interact with the AI character.

Abstract: A computer-implemented method for representing operator control information in the context of operator control and monitoring of a technical installation is proposed, which has at least one operator station server and one operator station client, wherein at least one measurement value of at least one technical object of the technical installation is received via the operator station server, a trend progression of the measurement value is generated in the event that an alarm, which relates to the measurement value, occurs in the operator station server, the trend progression from the operator station server is transferred to the operator station client, and the trend progression is visually presented to an operator of the technical installation in a trend progression diagram.

Abstract: Techniques are described herein for multi-modal interaction between users, automated assistants, and other computing services. In various implementations, a user may engage with the automated assistant in order to further engage with a third party computing service. In some implementations, the user may advance through dialog state machines associated with third party computing service using both verbal input modalities and input modalities other than verbal modalities, such as visual/tactile modalities.

Abstract: Aspects of the subject technology relate to providing frame rate arbitration for electronic devices. Frame rate arbitration can include determining a global frame rate based on frame rate parameters from one or more animation sources, and providing the global frame rate to the animation sources. The frame rate parameters for various animations sources can have differing preferred, minimum, and/or maximum frame rates, and the global frame rate may be determined for concurrent display of multiple animations from the multiple animation sources. In one or more implementations, frame rate arbitration can also be performed based on frame rate parameters from an input source.

Abstract: Sensor data indicating a user's response to an avatar experience in which the user experiences a rendered avatar model is obtained. A perceptual quality metric value corresponding to the rendered avatar model is determined based on the sensor data and a determined relationship between the sensor data and the perceptual quality metric value. The avatar model is re-rendered for display based on the perceptual quality metric value.

Abstract: A method for autonomous navigation of a movable robotic unit, in particular at least as part of a SLAM method. A plurality of virtual points from the surroundings around the detection unit is detected using a detection unit. An optimization problem of graph theory is solved using a control and/or regulation unit for ascertaining a position and/or a movement of the robotic unit and/or for detecting the surroundings as a function of the detected virtual points. At least one virtual plane is ascertained, using the control and/or regulation unit, as a function of at least one group of virtual points of the plurality of virtual points. For ascertaining a position and/or a movement of the robotic unit and/or for representing the surroundings, the ascertained virtual plane is used for solving the optimization problem of graph theory using the control and/or regulation unit.

Abstract: The present disclosure provides a method for topography simulation of a physical structure under a topography-changing process. The method includes initializing a voxel mesh as a three-dimensional (3D) representation of the physical structure, generating a batch of particles, simulating a flight path of one of the particles with a ray-tracing method by a parallel processing thread in a hardware accelerator, identifying a surface normal of a voxel unit in the voxel mesh that intersects the flight path by the parallel processing thread, determining a surface reaction between the one of the particles and the voxel unit by a central processing unit (CPU), and updating the voxel mesh based on the determining of the surface reaction.

Abstract: An electronic device is provided which displays an object (body) on a flexible display screen in accordance with a three-dimensional shape of the display screen by utilizing the flexibility of the display screen. An electronic device including a display portion which includes a flexible display device displaying an object on a display screen; a detection portion detecting positional data of a given part of the display screen; and an arithmetic portion calculating a three-dimensional shape of the display screen on the basis of the positional data and computing motion of the object to make the object move according to a given law in accordance with the calculated three-dimensional shape of the display screen.

Abstract: A method and system for transforming simple user input into customizable animated images for use in text-messaging applications.

Abstract: In a real-time data processing device (1), when a camera video is inputted as video data in a raster format and a hand-drawing input is inputted as drawing data in a vector format, inverted video data in the raster format and inverted drawing data in the vector format are generated, a display of the drawing data in the vector format is made in a drawing area (A1) of a touch panel unit, and a superimposed display of the inverted video data in the raster format and the inverted drawing data in the vector format is made in a preview area (A2). Drawing data in the raster format is generated by performing encoding processing of the drawing data in the vector format, and composite data to be stored is generated by performing rendering processing of the video data in the raster format and the drawing data in the raster format.

Abstract: The technology disclosed relates to automatically interpreting motion of a control object in a three dimensional (3D) sensor space by sensing a movement of the control object in the (3D) sensor space, interpreting movement of the control object, and presenting the interpreted movement as a path on a display. The path may be displayed once the speed of the movement exceeds a pre-determined threshold measured in cm per second. Once the path is displayed, the technology duplicates a display object that intersects the path on the display. In some implementations, the control object may be a device, a hand, or a portion of a hand (such as a finger).

Abstract: A client device of a game streaming system generates an overlay that identifies discontinuities and other changes in features between streamed frames. The client device receives a stream of frames, representing game content for display, from a server via a network. The client device analyzes the received frames to identify discontinuities and other changes in features of the plurality of frames, such as a particular feature changing one or more of position, size, texture, or other visual characteristic between successively received frames. The client device generates the overlay to indicate the identified features and displays the overlay with at least one of the received frames.

Abstract: Systems and methods for recognition of intent of a character are provided. The character is an Artificial Intelligence (AI) character generated by an AI character model for interacting with users in the virtual environment or is controlled by a human user. An example method includes monitoring interactions between a plurality of characters in a virtual environment; recognizing, based on environmental parameters associated with the interactions, an intent of a character selected from the plurality of characters: selecting a plurality of possible behaviors for the character based on the intent; and triggering a behavior selected from the plurality of possible behaviors based on predetermined criteria.