Abstract: A method for generating a limitless path in a virtual reality environment (VR) for a continuous locomotion within a real physical space using Head-Mounted-Display (HMD) device associated with a user is provided. The method includes determining a line segment between two points that corresponds to an initial path travelled by the user. The method includes detecting a boundary of the VR environment to generate a next line segment. The method includes generating and adding a new line segment to end of the initial path. The method includes generating and adding the new line segment to the end of the next line segment. The method includes generating an updated path by adding the new line segment in a direction at the angle of shift angle to the direction of the next line segment. The method includes, configuring to output updated path as two-dimensional points to render updated path into VR environment.

Abstract: An apparatus detects a plurality of areas from an overall image, determines on each of the plurality of areas whether the area is a candidate for an area including an object as a processing target based on a determination reference value (first determination processing), acquires a zoom-in image of the area determined to be the candidate for the area including the object in the first determination processing, and determines whether the acquired zoom-in image is an image of the object (second determination processing). The apparatus identifies an area, in the overall image, corresponding to the zoom-in image determined not to be the image of the object in the second determination processing, and performs control to update the determination reference value used in the first determination processing based on image information of the identified area in the overall image.

Abstract: An example method includes identifying a need and an emotional state of a user who is participating in an interaction with a support application, retrieving a set of preferences for the user, selecting a set of features for an avatar to be presented to the user, wherein the set of features is selected based at least on the emotional state of the user and the set of preferences, selecting a stored workflow based on the need of the user, and rendering the avatar to exhibit the set of features and to present the stored workflow as part of the interaction.

Abstract: Generating data to provide an animated visual representation is disclosed. A method comprises receiving input data obtained by a first sensor system measuring information about at least one target person. One data unit is selected from a database comprising a plurality of the data units. Each data unit comprises information about a reference person in a reference state measured at a previous time by the first sensor system or by a second sensor system. The information in each data unit allows generation of an animated visual representation of the reference person in the reference state. The reference state is different for each of the data units. The selected data unit and the input data are used to generate output data usable to provide an animated visual representation corresponding to the target person and synchronized with activity of the target person measured by the first sensor system.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed herein to accelerate security threat investigation. An example apparatus includes a model trainer to train a security investigation model, a game engine to determine a source security software product and a destination security software product of a security threat object, an actions database to store at least one of the previous security response action, the source security software product, the destination security software product, and the security threat object, an action generator to generate at least one suggested security response action in response to a user security investigation action, wherein the suggested security response action is based on an execution of the security investigation model, and a software product controller to adjust a display of the destination security software product of the security threat object in response to the security response action.

Abstract: Various implementations disclosed herein include devices, systems, and methods for controlling motion of CGR objects. In various implementations, a device includes a non-transitory memory and one or more processors coupled with the non-transitory memory. In some implementations, a method includes determining, by a first animation controller, values for a first set of animation parameters associated with a first animation for a computer-generated reality (CGR) object. In some implementations, the CGR object is associated with a plurality of joints. In some implementations, the method includes generating, by a motion controller, respective joint movements for the plurality of joints based on the values for the first set of animation parameters. In some implementations, the method includes manipulating the CGR object in accordance with the respective joint movements for the plurality of joints in order to provide an appearance that CGR object is moving within a degree of similarity to the first animation.

Abstract: A method and apparatus for controlling a social robot includes providing a set of quantitative personality trait values, also called a “personality profile” to a decision engine of the social robot. The personality profile is derived from a character portrayal in a fictional work, dramatic performance, or by a real-life person (any one of these sometime referred to herein as a “source character”). The decision engine controls social responses of the social robot to environmental stimuli, based in part on the set of personality trait values. The social robot thereby behaves in a manner consistent with the personality profile for the profiled source character.

Abstract: Techniques for adaptive thresholding are provided. A first data point in a data stream is received, and a first plurality of data points from the data stream is identified, where the first plurality of data points corresponds to a timestamp associated with the first data point. At least a first cluster is generated for the first plurality of data points, and a predicted value for the first data point is generated based at least in part on data points in the first cluster. A deviation is computed between the predicted value for the first data point and an actual value for the first data point. Upon determining that the deviation exceeds a first predefined threshold, the first data point is labeled as anomalous, and reallocation of computing resources is facilitated based on labeling the first data point as anomalous.

Abstract: A virtual reference plane and a virtual camera are updated based on detection of a characteristic portion in a captured image. A virtual object and the virtual camera are updated based on a shooting state. An overlay image in which an image of the virtual object is overlaid on the captured image is generated. The virtual camera and the virtual object are controlled such that the virtual object is in a field-of-view range, before the detection of the characteristic portion. The virtual object, the virtual reference plane, and the virtual camera are updated such that the virtual object is along the virtual reference plane, based on the shooting state, after the detection of the characteristic portion, and such that an appearance of the virtual object is in association with the shooting state, no matter whether or not the characteristic portion has been detected, when a position fixation condition is satisfied.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and a method for detecting a pose of a user. The program and method include receiving a monocular image that includes a depiction of a body of a user; detecting a plurality of skeletal joints of the body depicted in the monocular image; and determining a pose represented by the body depicted in the monocular image based on the detected plurality of skeletal joints of the body. A pose of an avatar is modified to match the pose represented by the body depicted in the monocular image by adjusting a set of skeletal joints of a rig of an avatar based on the detected plurality of skeletal joints of the body; and the avatar having the modified pose that matches the pose represented by the body depicted in the monocular image is generated for display.

Abstract: A method for utilizing human recognition and a method utilizing the same are provided. The method for utilizing human recognition includes updating a moving image database to include information about a moving image in which a cluster subject appears, the information being extracted based on clustering using a face feature; receiving a search condition; and detecting moving image information using the database. According to the present disclosure, a skeleton can be analyzed and a face can be recognized using an artificial intelligence (AI) model performing deep learning through a fifth generation (5G) network, and using the analysis result, a photographing composition can be determined, and moving image information can be constructed at an edge.

Abstract: A method for controlling placement of a virtual character includes: displaying a virtual character at a first position in a virtual reality (VR) scene; receiving a first instruction in the VR scene, the first instruction indicating moving the virtual character from the first position by a designated movement; displaying, in response to receiving the first instruction, third indication information as a preview of the designated movement in the VR scene; determining, according to the first instruction, a second position by the designated movement from the first position in response to the first instruction; removing the virtual character from the first position; and placing the virtual character at the second position, the virtual character not appearing between the first position and the second position after being removed from the first position.

Abstract: This application discloses a video file playing method and apparatus, and a storage medium. The video file playing method includes playing an animation file frame by frame according to a playback time of a video file, the video file comprising at least one displayed object, and the animation file comprising an animation element generated according to the displayed object; determining click/tap position information of a screen clicking/tapping event in response to the screen clicking/tapping event being detected; determining an animation element display area corresponding to the click/tap position information of the screen clicking/tapping event in the animation file according to the click/tap position information; determining, according to the corresponding animation element display area, an animation element triggered by the screen clicking/tapping event; and determining an interactive operation corresponding to the triggered animation element and performing the interactive operation.

Abstract: An augmented reality viewer includes components, assemblies, and executable logic to provide a user with the perception of rich augmented reality experiences, including aspects of the aquatic world.

Abstract: A method for real-time video processing for changing features of an object in a video, the method comprises: providing an object in the video, the object being at least partially and at least occasionally presented in frames of the video; detecting the object in the video; generating a list of at least one element of the object, the list being based on the object's features to be changed according to a request for modification; detecting the at least one element of the object in the video; tracking the at least one element of the object in the video; and transforming the frames of the video such that the at least one element of the object is modified according to the request for modification.

Abstract: An information processing apparatus includes: a first obtaining unit configured to obtain a first three-dimensional model expressing a position and a shape of a first object in a three-dimensional space based on images of the first object captured by a plurality of image-capturing devices at different locations; a second obtaining unit configured to obtain a second three-dimensional model expressing a position and a shape of a second object in the three-dimensional space; an identifying unit configured to identify a plurality of parts of the first object; a determining unit configured to determine a contact between a certain part of the first object and the second object based on the obtained first three-dimensional model and second three-dimensional model and an identification result of the plurality of parts; and an output unit configured to output information according to a determination result of the contact.

Abstract: A system (1) for displaying an optical image (2) by means of unmanned autonomous vehicles. Each vehicle has a display for displaying at least a part of the image (2) by way of stored or transmitted image information as well as a control unit (9). The control unit (9) is configured to control the image information and to move the vehicle using a drive unit (11) by means of stored or transmitted positon information. At least two vehicles are configured as land crafts (5), wherein the displays (3) of the land crafts (5) are oriented in parallel to a substantially horizontal image plane (6) and configured as displays (3) accessible by a human person.

Abstract: There is provided information processing apparatuses, information processing methods, programs, and information processing systems capable of reinforcing the reinforcement target behavior without causing the user's consciousness. A quest is presented for urging a user to execute a reinforcement target behavior, and when the user executes the reinforcement target behavior upon the request, an electroencephalogram is measured, emotion is estimated on the basis of the electroencephalogram, and when the number of times that dominant emotion having the highest emotion score among emotion of the emotion estimation results is detected exceeds a predetermined number of times, an avatar is changed corresponding to the emotion that is detected as the dominant emotion. The present disclosure can be applied to long-term feedback technology.

Abstract: To allow free animation production in virtual space, an animation production method executing: a step of placing a virtual camera for shooting a character in a virtual space; a step of placing a first plate object with a first image attached as a texture under the foot of the character in response to an instruction from a user; a step of placing a second plate object with a second image attached as a texture in response to an instruction from the user; a step of correcting the posture of the second plate object such that the second plate object is perpendicular to the first plate object; and a step of generating an image captured by the camera.

Abstract: A representation of a surface in a three-dimensional space is obtained. A first input representing a starting point and a second input representing a next point are obtained. A representation of a surface-aware spline comprising vertices is generated, with the representation of the surface-aware spline including a starting vertex corresponding to the starting point and a next vertex corresponding to the next point. First and second projection points corresponding to projections of a first vertex and a second vertex onto the surface are determined. New points corresponding to equal distance points for the first and second vertices aligned with the first and second projection points are determined, and a rigid transformation is determined from the new points. The representation of the surface-aware spline is adjusted based on a transformation of the new points using the rigid transformation.

Abstract: Techniques for adaptive thresholding are provided. First and second data points are received. A plurality of data points are identified, where the plurality of data points corresponds to timestamps associated with the first and second data points. At least one cluster is generated for the plurality of data points based on a predefined cluster radius. Upon determining that the first data point is outside of the cluster, the first data point is labeled as anomalous. A predicted value is generated for the second data point, based on processing data points in the cluster using a machine learning model, and a deviation between the predicted value and an actual value for the second data point is computed. Upon determining that the deviation exceeds a threshold, the second data point is labeled as anomalous. Finally, computing resources are reallocated, based on at least one of the anomalous data points.

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: capturing a video that depicts a person; identifying a set of skeletal joints of the person depicted in the video; storing a movement vector representing previously captured three-dimensional (3D) movement of the set of skeletal joints of the person depicted in the video; receiving input that selects a 3D avatar; and animating, based on the movement vector, the 3D avatar to mimic the previously captured 3D movement of the set of skeletal joints of the person depicted in the video.

Abstract: Enhanced techniques applicable to a ray tracing hardware accelerator for traversing a hierarchical acceleration structure and its underlying primitives are disclosed. For example, traversal speed is improved by grouping processing of primitives sharing at least one feature (e.g., a vertex or an edge) during ray-primitive intersection testing. Grouping the primitives for ray intersection testing can reduce processing (e.g., projections and transformations of primitive vertices and/or determining edge function values) because at least a portion of the processing results related to the shared feature in one primitive can be used in determine whether the ray intersects another primitive(s). Processing triangles sharing an edge can double the culling rate of the triangles in the ray/triangle intersection test without replicating the hardware.

Abstract: Systems and methods are described for imparting dynamic, non-linear and realistic movement and look and feel to a player's/virtual character's first-person limbs and hand-held object model, and procedurally animating a first-person virtual camera such that it simulates the movement of a camera handheld by the player/virtual character. To impart chaotic or random motion to the first-person limbs and hand-held object model a first module defines and implements first and second two dimensional mass-spring-damper systems, each of which is linked to the player's/virtual vector's view vector. Procedural animation or rotational shake is implemented by a second module by applying a coherent noise function to each of the six axes of the first-person virtual camera.

Abstract: A digital content package includes first content comprising a video feature such as a motion picture or the like, and a user-selectable application configured to operate as follows. When activated using an icon off of a menu screen, the application records an identifier for scenes (discrete portions) of the first content that are selected by a user to generate a playlist. The user may select the scenes by indicating a start and end of each scene. The application saves the playlist locally, then uploads to a server. Via a user account at the server, a user may publish the playlist to a user-created distribution list, webpage, or other electronic publication, and modify the playlist by deleting or reordering scenes.

Abstract: An information processing apparatus connected to a controller device equipped with proximity sensors that are provided for at least respective fingers of a user, estimating amounts of bending of the fingers of the user using a first method on the basis of detection results from the proximity sensors, estimating a posture and a shape of a hand of the user using a second method different from the first estimation method, and correcting by using information estimated by the first method, information regarding an amount of movement of each finger in a bending direction in information regarding the posture and the shape of the hand of the user estimated by the second method to generate information relating to the posture and the shape of the hand of the user.

Abstract: To enable you to take animations in a virtual space, an animation production method comprising: placing a first and second objects and a virtual camera in a virtual space; controlling an action of the first object in response to an operation from the first user; controlling an action of the second object in response to an operation from the second user; and controlling the camera in response to an operation from the first or second user or the second user to shoot the first and second objects.

Abstract: Ray tracing hardware accelerators supporting motion blur and moving/deforming geometry are disclosed. For example, dynamic objects in an acceleration data structure are encoded with temporal and spatial information. The hardware includes circuitry that test ray intersections against moving/deforming geometry by applying such temporal and spatial information. Such circuitry accelerates the visibility sampling of moving geometry, including rigid body motion and object deformation, and its associated moving bounding volumes to a performance similar to that of the visibility sampling of static geometry.

Abstract: Systems and methods for image-based guidance for facilitating navigation of tubular networks. A region of interest in three-dimensional image data may first be segmented. An endoscopic instrument may be detected in two-dimensional intraoperative image data of the region of interest. A centerline of the detected endoscopic instrument may then be determined. The endoscopic instrument and the centerline may be backprojected to generate a three-dimensional backprojected volume. A device path of the endoscopic instrument may be generated based at least in part on the three-dimensional backprojected volume and the three-dimensional image data.

Abstract: Systems, devices and processes and described herein to improve the generation of video content in video production systems. In general, the systems, devices and processes facilitate the incorporation of remotely generated user telestration inputs into output video streams generated by the video production systems. In one embodiment user telestration inputs are received at a control device. Minimum capture shapes corresponding to the user telestration inputs are then determined and images corresponding to the minimum capture shape are captured. The captured images are then transmitted from the control device to the video access point device. At the video access point device the captured images can then be combined with previously captured and transmitted images and overlaid with a selected input video stream. The video input stream with the overlaid image can then be transmitted as an output video stream.

Abstract: A real-time video exploration (RVE) system that allows users to pause, step into, move through, and explore 2D or 3D modeled worlds of scenes in a video. The RVE system may allow users to discover, select, explore, and manipulate objects within the modeled worlds used to generate video content. The RVE system may implement methods that allow users to view and explore in more detail the features, components, and/or accessories of selected objects that are being manipulated and explored. The RVE system may also implement methods that allow users to interact with interfaces of selected objects or interfaces of components of selected objects.

Abstract: An apparatus for configuring an avatar responsive to a content having at least one of a video and an audio signal includes an authoring unit configured to detect one or more events in a content comprising at least one of a video and an audio signal, categorise one or more of the detected events, and generate an event track for the content, the event track comprising one or more of the categorised events associated with a respective time; a selecting unit configured to select a configuration of an avatar to correspond to a respective categorised event of the event track; and an output generator configured to generate control data to configure an avatar in response to a selected configuration.

Abstract: A method, system, and computer program product to manage a network comprising a plurality of interconnected components are described. The method includes obtaining a set of all the components that are part of the network over time, and identifying one or more repeating patterns of components among the set of all the components as corresponding lower-level definitions to generate a hierarchical set of all the components. The method also includes obtaining time-varying information regarding topology and operational values within the network, and creating a representation of the network at a set of times based on the hierarchical set of all the components and the time-varying information.

Abstract: The present disclosure is directed to systems and methods for providing improved tools (e.g., user interfaces) that can be used for managing access permissions to cloud or other network resources. In general, the systems and methods include providing a user interface that can function in at least two modes which together can provide an improved user experience for intuitively and effectively developing code. As an example, the two interface modes can include a builder mode in which the user interface includes one or more interactive elements that enable a user to modularly build a set of computer-readable code that controls access permissions to one or more computing resources and an editor mode in which the user interface allows the user to directly edit the set of computer-readable code.

Abstract: Various implementations disclosed herein include devices, systems, and methods for selectively applying a tool and/or a rig to a skeleton of an object based on an upcoming motion. In some implementations, a method includes obtaining, from a memory location, a response characteristic to be exhibited by an object while displaying the object in a computer graphics environment. A tool is selected that allows the object to be manipulated to exhibit the response characteristic in the computer graphics environment. The tool is associated with a skeleton of the object. A manipulation of the object is displayed within the computer graphics environment in accordance with the response characteristic after associating the tool with the skeleton of the object.

Abstract: A location-based augmented-reality system to generate and cause display of augmented-reality content that includes three-dimensional typography, based on a perspective, and location of a client device.

Abstract: Techniques described herein take character glyphs as input and generate a text-on-a-path text object that includes the character glyphs arranged in a determined order along a path. For instance, a method described herein includes accessing character glyphs in input data. The method further includes determining an order for the character glyphs based on relative positions and orientations of the character glyphs in the input data. The method further includes generating a path for the character glyphs, based on the order, and associating the path with the character glyphs. Further, the method includes generating a text object that includes the set of character glyphs arranged in the order along the path.

Abstract: An electronic chip, a chip assembly, a computing device, and a method are described. The electronic chip comprises a plurality of processing cores and at least one hardware interface coupled to at least one of the one or more processing cores. At least one processing core implements a game engine and/or a simulation engine and one or more processing cores implements an artificial intelligence engine, whereby implementations are on-chip implementations in hardware by dedicated electronic circuitry. The one or more game and/or simulation engines perform tasks on sensory data, generating data sets that are processed through machine learning algorithms by the hardwired artificial intelligence engine. The data sets processed by the hardwired artificial intelligence engine include at least contextual data and target data, wherein combining both data and processing by dedicated hardware results in enhanced machine learning processing.

Abstract: A method of network-based media processing (NBMP) can include receiving a function description of a media processing function from a function repository at a workflow manager in an NBMP system. The function description can include a configuration descriptor providing configuration information of parameters for the media processing function. The parameters can have logical relationships represented by a parameter representation graph constructed according to a set of rules. The media processing function can be instantiated as a media processing task that is part of a workflow. The media processing task can be configured based on the configuration information of the parameters in the configuration descriptor.

Abstract: Embodiments of the present invention provide a position-based dynamics approach for simulating objects using a set of points and constraints, applied as equations that restrict the relative motion of bodies. Forces are applied to the points to move them, and the constraints ensure that the points will not move in a way that is inconsistent with rules of the simulation. The present invention improves upon existing PBD approaches by using regularized constraints that directly correspond to well-defined energy potentials, and which can advantageously be solved independent of time step and iteration count.

Abstract: The present disclosure provides an image warping method and an image warping device, including: obtaining an image or a video; identifying at least one target portion of a to-be-warped portrait in the image or the video; and performing a warping process on the target portion using a preset warping algorithm, where the warping process includes one or more of the following processes: enlarging, narrowing down, or shifting. In this way, a portrait in the image or the video can be beautified automatically, without a manual beautification of the image from a user, making the beautification more intelligent and simpler, thereby improving the user experience. Moreover, according to the method of the present disclosure, a warping process can be performed on an image or a video online in real time, or performed on a stored image or a stored video offline, allowing the image warping method to be more widely used.

Abstract: A viewing window for a spherical video may define which extents of the spherical video are viewable. Abrupt changes in the extents defined by the viewing window may result in non-smooth views of the spherical video, such as stagger, jitter, and/or other jerky motions being included in the views of the spherical video. Changes in the extents defined by the viewing window may be smoothed to provide smoother views of the spherical video.

Abstract: Systems and methods for reconstructing a motion-compensated magnetic resonance image are presented. In certain implementations, a computer-implemented method is provided. The method may include a plurality of operations, including receiving a set of k-space data from a magnetic resonance imaging device, dividing the set of k-space data into a plurality of groups, performing a plurality of initialization operations, performing a first iterative process until a first criteria for the first iterative process is achieved for a current scale of motion estimation, performing a second iterative process until a second criteria for the second iterative process is achieved, and outputting a motion-compensated magnetic resonance image reconstructed in accordance with a predetermined scale of motion estimation.

Abstract: A retrieval device includes one or more processors. The processors acquire trajectory information indicating a movement trajectory of a target in time-series images. The processors acquire situation information indicating a peripheral situation of the target in the time-series images. The processors acquire a retrieval query containing a movement trajectory and a peripheral situation. The processors retrieve an image matching with the retrieval query among images contained in the time-series images based on the trajectory information and the situation information.

Abstract: A state control method includes detecting an operation execution event used for requesting to operate on a first object in a first application. The method also includes determining whether a next node of a current node of the first object in a hybrid state machine is a first state node or a first behavior-tree node. Nodes in the hybrid state machine includes at least a state node and a behavior-tree node, and a state change relationship exists among the nodes in the hybrid state machine. The method further includes, when it is determined that the next node is the first state node, performing on the first object an operation in a first state corresponding to the first state node; and, when it is determined that the next node is the first behavior-tree node, performing on the first object an operation in a first behavior-tree corresponding to the first behavior-tree node.

Abstract: Systems and methods provide reframing operations in a smart editing system that may generate a focal point within a mask of an object for each frame of a video segment and perform editing effects on the frames of the video segment to quickly provide users with natural video editing effects. A reframing engine may processes video clips using a segmentation and hotspot module to determine a salient region of an object, generate a mask of the object, and track the trajectory of an object in the video clips. The reframing engine may then receive reframing parameters from a crop suggestion module and a user interface. Based on the determined trajectory of an object in a video clip and reframing parameters, the reframing engine may use reframing logic to produce temporally consistent reframing effects relative to an object for the video clip.

Abstract: An analysis system analyzes a state of a person and includes a terminal configured to be worn on the person's body. The terminal includes an acceleration sensor, a storage unit, and a processing unit. The processing unit determines whether each value contained in the time series data is in a first state in which the value is equal to or greater than the threshold or in a second state in which the value is less than the threshold. The processing unit also determines a duration which is a period of time during which the first state continues. The processing unit quantifies a brain state of the person on the basis of the duration.

Abstract: A system to track orientations of parts of a user based on both images and inertial measurement units (IMUs). For example, the system receives images showing a portion of the user wearing sensor modules. The system receives a first set of orientation measurements generated by the sensor modules attached to some parts of the user. The system determines the second set of orientation measurements of one or more features of the portion of the user from the images. The system provides the first set of orientation measurements and the second set of orientation measurements as input to an artificial neural network that is configured to predict orientation measurements of the one or more other parts of the user that would be measured by additional sensor modules if the additional sensor modules were to be attached to the other parts of the user.

Abstract: Motion retargeting with kinematic constraints is implemented in a digital medium environment. Generally, the described techniques provide for retargeting motion data from a source motion sequence to a target visual object. Accordingly, the described techniques position a target visual object in a defined visual environment to identify kinematic constraints of the target object relative to the visual environment. Further, the described techniques utilize an iterative optimization process that fine tunes the conformance of retargeted motion of a target object to the identified kinematic constraints.

Abstract: A method of and system for recreating a real world pose or aligning a real world object in a virtual space, the method including: prompting a user to successively place a device at a plurality of positions/alignments associated with a plurality of physical points associated with a body of the user, a body of another, or an object; capturing the plurality of positions/alignments with respect to a real world frame of reference; translating the plurality of positions/alignments with respect to the real world frame of reference to a frame of reference in virtual space; and recreating a pose of the body of the user, a pose of the body of the other, or an alignment of the object in the virtual space using the translated plurality of positions/alignments.