Abstract: A method includes obtaining image frames capturing one or more people in at least one scene and identifying features of the image frames. The method also includes providing the identified features to a trained spatiotemporal transformer machine learning model configured to generate a set of features for each of the one or more people. The set of features for each person includes facial features of the person and pose features of the person over time. The method further includes performing face identification using the facial features to generate one or more first embeddings representing at least one face of at least one person and performing gait identification using the pose features to generate one or more second embeddings representing at least one gait of at least one person. In addition, the method includes identifying at least one of the one or more people based on the first and second embeddings.

Abstract: In one embodiment, a method includes receiving, at an autonomous mobile robot, a request for the robot to remotely control a function of an electronic device comprising a display screen; and determining, by the autonomous mobile robot and based on one or more images of the display screen captured by a camera of the robot, whether a current location of the robot is an optimal location to remotely control the function of the electronic device. The method then includes one or more of: in response to a determination that the robot's location is not an optimal location, then adjusting, by the autonomous mobile robot, a position of the robot; and in response to a determination that the robot's location is an optimal location, then processing the request.

Abstract: A method includes obtaining one or more inputs at a first electronic device. The first electronic device includes a multi-task dynamic machine learning model that includes multiple sub-models configured to perform different machine learning functions. The method also includes dynamically controlling the sub-models used to process the one or more inputs based on at least one of: (i) the one or more inputs that are available for use or (ii) one or more outputs to be generated. The method further includes generating a set of contextual information associated with the first electronic device. At least a portion of the set of contextual information is associated with at least one user of the first electronic device. The method may additionally include sharing the set of contextual information with at least a second electronic device in a specified environment.

Abstract: A method includes obtaining image frames capturing one or more people in at least one scene and identifying features of the image frames. The method also includes providing the identified features to a trained spatiotemporal transformer machine learning model configured to generate a set of features for each of the one or more people. The set of features for each person includes facial features of the person and pose features of the person over time. The method further includes performing face identification using the facial features to generate one or more first embeddings representing at least one face of at least one person and performing gait identification using the pose features to generate one or more second embeddings representing at least one gait of at least one person. In addition, the method includes identifying at least one of the one or more people based on the first and second embeddings.

Abstract: One embodiment provides a method comprising acquiring, via one or more microphones of a device in a spatial area, a signal representing at least one echo of an ultrasound emitted via one or more loudspeakers of the device. The method further comprises applying digital signal processing to the signal to determine a signal-to-noise ratio (SNR) of the signal, and estimating one or more properties of a moving reflector in the spatial area based on the SNR of the signal.

Abstract: A method includes obtaining one or more inputs at a first electronic device. The first electronic device includes a multi-task dynamic machine learning model that includes multiple sub-models configured to perform different machine learning functions. The method also includes dynamically controlling the sub-models used to process the one or more inputs based on at least one of: (i) the one or more inputs that are available for use or (ii) one or more outputs to be generated. The method further includes generating a set of contextual information associated with the first electronic device. At least a portion of the set of contextual information is associated with at least one user of the first electronic device. The method may additionally include sharing the set of contextual information with at least a second electronic device in a specified environment.

Abstract: One embodiment provides a method comprising acquiring, via one or more microphones of a device in a spatial area, a signal representing at least one echo of an ultrasound emitted via one or more loudspeakers of the device. The method further comprises applying digital signal processing to the signal to determine a signal-to-noise ratio (SNR) of the signal, and estimating one or more properties of a moving reflector in the spatial area based on the SNR of the signal.

Abstract: A method includes generating one or more graphs representing automatic content recognition (ACR) data associated with a computing device; identifying one or more paths representing at least a portion of the one or more graphs; training one or more models based on inputting the one or more paths into one or more machine-learning algorithms; producing one or more embeddings from the one or more models; and clustering the one or more embeddings to provide at least one cluster corresponding to a behavioral profile associated with the computing device.

Abstract: Technologies are generally described for automatically reconnecting a security principal to cloud services through correlation of security principal identifier attributes. A new security principal for a user may be detected and automatically reconnected to the user's cloud based services. An administrator for the security domains may specify a value of a unique security principal metadata attribute for the original security principal in a customizable security principal metadata attribute in the new security principal in the same or new security domain. A secondary verification metadata attribute may optionally be specified to ensure the correct security principal is reconnected to the user's cloud based resources. The correlation between the original security principal for the user and the new security principal may be used to reconnect the user's cloud resources.

Abstract: Technologies are generally described for automatically reconnecting a security principal to cloud services through correlation of security principal identifier attributes. A new security principal for a user may be detected and automatically reconnected to the user's cloud based services. An administrator for the security domains may specify a value of a unique security principal metadata attribute for the original security principal in a customizable security principal metadata attribute in the new security principal in the same or new security domain. A secondary verification metadata attribute may optionally be specified to ensure the correct security principal is reconnected to the user's cloud based resources. The correlation between the original security principal for the user and the new security principal may be used to reconnect the user's cloud resources.