A method for authenticating a user includes: an application frontend of a face recognition application, upon receipt of a face recognition request from an application backend of the face recognition application, causes a terminal device to activate a camera of the terminal device; the application frontend receives a video stream of a face of the user captured by the camera of the terminal device; the application frontend transmits the received video stream to the application backend; the application backend, upon receipt of the video stream, extracts a face characteristic of the user from the received video stream in real-time; and the application backend compares the extracted face characteristic with a stored reference face characteristic of the user and authenticates the user based on the extracted face characteristic matching the stored reference face characteristic.

A content selection device includes: an image acquisition unit configured to acquire an image captured by an image capture device configured to capture a person; a human detection unit configured to detect one or more persons included in the image; and a selection unit configured to select a first person who has a slower moving speed than at least one other person from among the one or more persons, and select a first content according to an attribute of the first person as a content to be displayed on a display device.

Embodiments of the present disclosure provide a quantitative method and system for attention based on a line-of-sight estimation neural network, which improves the stability and training efficiency of the line-of-sight estimation neural network. A few-sample learning method is applied to training of the line-of-sight estimation neural network, which improves generalization performance of the line-of-sight estimation neural network. A nonlinear division method for small intervals of angles of the line of sight is provided, which reduces an estimation error of the line-of-sight estimation neural network. Eye opening and closing detection is added to avoid the line-of-sight estimation error caused by an eye closing state. A method for solving a landing point of the line of sight is provided, which has high environmental adaptability and can be quickly used in actual deployment.

An apparatus includes an extraction unit configured to extract an N-dimensional feature vector (N is an integer that is greater than M) in a second format including an M-dimensional feature vector (M is an integer of 2 or greater) in a first format from input data, and an identification unit configured to identify a target in the input data based on the feature vector in the first format and the feature vector in the second format.

In some examples an electronic device includes an image sensor and a processor. The processor is to determine an angle of an eye gaze of a user in relation to an optical axis of the image sensor and adjust, responsive to a determination that the angle exceeds a threshold angle, an active area of a display device.

Methods, systems, and apparatus, including medium-encoded computer program products, for a secure edge platform that uses image classification machine learning models. An edge platform can include at least one camera and can identify image classification models that generate classification output data from image data generated by the cameras. The edge platform can receive image data generated by the camera, and provide the image data to the models. In response to providing the image data classification models, the edge platform can receive classification output data. In response to receiving the classification output data from the image classification models, the edge platform can generate augmentation data that is associated with the image data, then transmit detection data to a central server platform. The detection data can include (i) the classification output data and (ii) the augmentation data associated with the image data. Data can be made recordable, reportable, searchable, and alarmable.

Hot word free adaptation, of one or more function(s) of an automated assistant, responsive to determining, based on gaze measure(s) and/or active speech measure(s), that a user is engaging with the automated assistant. Implementations relate to various techniques for mitigating false positive occurrences of and/or false negative occurrences, of hot word free adaptation, through utilization of personalized parameter(s) for at least some user(s) of an assistant device. The personalized parameter(s) are utilized in determining whether condition(s) are satisfied, where those condition(s), if satisfied, indicate that the user is engaging in hot word free interaction with the automated assistant and result in adaptation of function(s) of the automated assistant.

The present disclosure provides a laser projection component and a detection method thereof, and an electronic device. The laser projection component is applicable to the depth camera component and is configured to project a laser pattern. The detection method includes: obtaining the laser pattern; determining whether a preset identifier exists in the laser pattern; and determining that the depth camera component is abnormal when the preset identifier does not exist in the laser pattern.

A driver monitor includes a processor configured to: detect the posture of a driver of a vehicle from an image of the interior of the vehicle generated by a camera provided on the vehicle, determine that the driver's condition is abnormal, when the detected posture satisfies an abnormality determining condition, detect an unusual sound made by the driver of the vehicle, based on a voice signal of the interior of the vehicle obtained by a microphone provided on the vehicle, and make the abnormality determining condition for the case where the unusual sound is detected less strict than an abnormality determining condition for the case where the unusual sound is not detected.

Some embodiments enable distributing data (e.g., recorded video, photographs, recorded audio, etc.) to a plurality of users in a manner which preserves the privacy of the respective users. Some embodiments leverage homomorphic encryption and proxy re-encryption techniques to manipulate the respective data so that selected portions of it are revealed according to an identity of the user currently accessing the respective data.