A system is provided that includes a mobile user device (300) that executes an application and determines and transmits a recipe for generating a target cosmetic material that is based on a combination of a plurality of separate ingredients that are associated with the user. The system includes a dispensing device (100) configured to receive the transmitted recipe from the mobile user device 300) and dispense each of the plurality of separate ingredients onto a common dispensing surface such that when the dispensed amounts of each of the plurality of separate ingredients is blended on the dispensing surface, the target cosmetic material is achieved.

The present disclosure provides a photo album management method. The method includes obtaining voice search information from a user, performing intent recognition on the voice search information to obtain an intent recognition result which indicates an intent of the user for a photo album, obtaining a voiceprint feature from the voice search information to determine identity information of the user, sending the intent recognition result and the identity information of the user, and opening the photo album according to the intent recognition result and the identity information.

A face authentication apparatus (50) includes an image generation unit (102) that generates a first image by capturing an image of a person, a control unit (104) that, when the first image does not satisfy a criterion for face collation, controls lighting and causes the image generation unit (102) to generate a second image by capturing an image of the person again, and a face authentication unit (52) that executes face authentication by using the second image.

The present disclosure relates to systems and methods for selecting a best facial image of a target human face. The methods may include determining whether a candidate facial image is obtained before a time point in a time period threshold, wherein the candidate facial image has a greatest quality score of the target human face among a plurality of facial images of the target human face; in response to a determination that the candidate facial image is obtained before the time point, determining the candidate facial image as the best facial image of the target human face; and storing the best facial image together with a face ID and the greatest quality score of the target human face in a face log.

A neural network system is configured to receive an input image and to generate a classification output for the input image. The neural network system includes: a separable convolution subnetwork comprising a plurality of separable convolutional neural network layers arranged in a stack one after the other, in which each separable convolutional neural network layer is configured to: separately apply both a depthwise convolution and a pointwise convolution during processing of an input to the separable convolutional neural network layer to generate a layer output.

A system receives input from a user to initiate a process of generating a holodouble of the user. The system obtains image data of the user and deconstructs the image data to obtain a set of sparse data that identifies one or more attributes associated with the image data the user. The system uses a holodouble training model to generate and train the holodouble of the user based on the set of sparse data and obtained image data. The system renders a representation of the holodouble to the user concurrently while capturing new image data of the user, receives input from the user comprising approval of the holodouble, and completes training of the holodouble by saving the holodouble for subsequent use. The subsequent use includes one or more remote visual communication sessions.

A neural network system is configured to receive an input image and to generate a classification output for the input image. The neural network system includes: a separable convolution subnetwork comprising a plurality of separable convolutional neural network layers arranged in a stack one after the other, in which each separable convolutional neural network layer is configured to: separately apply both a depthwise convolution and a pointwise convolution during processing of an input to the separable convolutional neural network layer to generate a layer output.

The present embodiment provides an image restoration method and apparatus which generate independent different restoration models by performing learning for each of different resolutions, receive a distorted image, and apply a restoration model corresponding to the resolution of the distorted image among the independent different restoration models to restore the distorted image into an improved upscaled image centering on a restoration target object within the distorted image.

Provided are an image capturing method and apparatus, a device and a storage medium. The method includes: at a new acquisition moment, predicting a predicted projection area position of a target object in a current captured image on an image sensor and estimated exposure brightness information of the target object in the predicted projection area position; adjusting, according to a type of the target object and the estimated exposure brightness information, an exposure parameter of the target object in the predicted projection area position when the new acquisition moment arrives; and acquiring a new captured image at the new acquisition moment according to the adjusted exposure parameter, where both the new captured image and the current captured image include the target object.

An electronic device and a controlling method thereof are provided. A controlling method of an electronic device according to the disclosure includes: performing first learning for a neural network model for acquiring a video sequence including a talking head of a random user based on a plurality of learning video sequences including talking heads of a plurality of users, performing second learning for fine-tuning the neural network model based on at least one image including a talking head of a first user different from the plurality of users and first landmark information included in the at least one image, and acquiring a first video sequence including the talking head of the first user based on the at least one image and pre-stored second landmark information using the neural network model for which the first learning and the second learning were performed.