An information processing apparatus of the present invention acquires, from a communication device of a user, at least one of utterance information by the user and position information of the communication device, specifies a predetermined region according to a mark included in the utterance information; acquires a movement direction of the user from at least one of the utterance information and the position information acquired from the communication device of the user, and setting a probability distribution that the user exists to a divided region of the predetermined region based on the acquired movement direction of the user; and presumes the user based on the set probability distribution.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for agent behavior prediction using keypoint data. One of the methods includes obtaining data characterizing a scene in an environment, the data comprising: (i) context data comprising data characterizing historical trajectories of a plurality of agents up to the current time point; and (ii) keypoint data for a target agent; processing the context data using a context data encoder neural network to generate a context embedding for the target agent; processing the keypoint data using a keypoint encoder neural network to generate a keypoint embedding for the target agent; generating a combined embedding for the target agent from the context embedding and the keypoint embedding; and processing the combined embedding using a decoder neural network to generate a behavior prediction output for the target agent that characterizes predicted behavior of the target agent after the current time point.

An in-vehicle apparatus (1) according to the present disclosure includes: estimated walking path acquisition means (21) for acquiring an estimated walking path, which is a path in which it is estimated that a driver will walk; and drinking determination means (22) for determining whether or not the driver is drunk based on a walking pattern of the driver in the estimated walking path.

The disclosure is inputting a first image captured an image of an authentication target; inputting a second image captured an image of a right eye or a left eye of the target; determining whether the second image is of a left eye or a right eye of the target based on information including the first image, and outputting a determination result as left/right information in association with the second image; detecting an overlap between a region including the second image and a predetermined region in the first image; calculating a verification score by comparing characteristic information that are related to the left/right information with iris characteristic information calculated from the second image, and calculating a first weighted verification score obtained by weighting the verification score with a detection result; and authenticating a target in the second image based on the first weighted verification score, and outputting an authentication result.

Systems, methods, and non-transitory computer readable media for selectively controlling display of virtual objects are provided. Virtual objects may be virtually presented in an environment via a wearable extended reality appliance operable in a first and second display modes. In the first display mode, positions of the virtual objects are maintained in the environment regardless of detected movements of the wearable extended reality appliance, and in the second display mode, the virtual objects move in the environment in response to detected movements of the wearable extended reality appliance. Movement of the wearable extended reality appliance may be detected. A selection of the first or second display mode may be received. Display signals configured to present the virtual objects in a manner consistent with the selected display mode may be outputted for presentation via the wearable extended reality appliance in response to the selected display mode.

The present disclosure is directed to providing digital health services. In some embodiments, systems and methods for conducting virtual or remote sessions between patients and clinicians are disclosed. During the sessions, media content (e.g., images, video content, audio content, etc.) may be captured as the patient performs one or more tasks. The media content may be presented to the clinician and used to evaluate a condition of the patient or a state of the condition, adjust treatment parameters, provide therapy, or other operations to treat the patient. The analysis of the media content may be aided by one or more machine learning/artificial intelligence models that analyze various aspects of the media content, augment the media content, or other functionality to aid in the treatment of the patient.

A system includes one or more antennas; and a processor to control a directionality of the antennas in communication with a predetermined target using 5G protocols.

A system and method for a machine learning-based automated electronic time recording for personnel includes identifying, via a scene capturing device, a representation of a time recording space; identifying a body having a time recording pose within the time recording space based on an assessment of the representation of the time recording space; extracting a plurality of distinct features from the representation of the time recording space based on identifying the body having the time recording pose; executing automated user-recognition based on the extracting of the plurality of distinct features; executing automated time recording recognition based on the extracting of the plurality of distinct features; and executing automated electronic time recording, via a time recording application based on the automated user-recognition and the automated time recording recognition.

A system includes one or more antennas and a processor to communicate with a predetermined target using 5G or 6G protocols.

A computer alters at least one recognizable metric or text in a digitally encoded photographic image by operating an alteration algorithm in response to user input data while preserving an overall aesthetic quality of the image and obscuring an identity of at least one individual or geographic location appearing in the image. An altered digitally-encoded photographic image prepared by the altering of the at least one recognizable metric or text in the image is stored in a computer memory. User feedback and/or automatic analysis may be performed to define parameter values of the alteration algorithm such that the alteration process achieves preservation of aesthetic qualities while obscuring an identity of interest.