Digital object animation techniques are described. In a first example, translation-based animation of the digital object operates using control points of the digital object. In another example, the animation system is configured to minimize an amount of feature positions that are used to generate the animation. In a further example, an input pose is normalized through use of a global scale factor to address changes in a z-position of a subject in different digital images. Yet further, a body tracking module is used to computing initial feature positions. The initial feature positions are then used to initialize a face tracker module to generate feature positions of the face. The animation system also supports a plurality of modes used to generate the digital object, techniques to define a base of the digital object, and a friction term limiting movement of features positions based on contact with a ground plane.

Multifactor authentication techniques described herein may allow a user to submit a recent proof of purchase as a part of a multifactor authentication process to access an account associated with a financial institution. As part of the login process, the user may submit a proof of purchase associated with a transaction. The financial institution may determine information associated with the transaction, such as a merchant associated with the proof of purchase, a time of the transaction, the last four numbers of the transaction card used, a dollar amount, or any combination thereof. If the information matches one or more records in the transaction history of the user's account, the financial institution may authenticate the user and provide access to the account. In this way, the financial institution may leverage transaction history known to the financial institution and the user to authenticate the user.

Systems and methods are provided for receiving a plurality of images corresponding to a listing in an online marketplace, generating a scene type for each image of the plurality of images, and grouping each image into a scene type group of a set of predefined scene types. Each group of images are input into a respective machine learning model specific to the scene type of the group of images to generate a visual score for each image in each group of images, and an attractiveness score is generated for the listing in the online marketplace based on the visual scores for each image in each group of images.

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.

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.

The present invention provides a gesture recognition apparatus in which a gesture intended to be used for an interface operation is performed at the closest mode of the camera, thus allowing the gesture to achieve interface control. A gesture recognition apparatus according to the present invention includes: an image capturer that sequentially captures distance image data taken by an imaging apparatus; a closest point detector that detects, from the distance image data, a closest point from the imaging apparatus; a gesture measurer that calculates an input switching border for switching ON and OFF of interface input, based on a trajectory of the closest point that is the gesture of the user detected from a plurality of distance image data items; a gesture recognizer that determines whether the input is ON or OFF, in accordance with the input switching border; and an interface controller that performs the interface control associated with the gesture if it is determined that the input has been turned on.

A system for remote identification of users. The system uses deep learning techniques for authenticating a user from an identification document and using automated verification of identification documents. Identification documents may be authenticated by validating security features. The system may determine features expected in a valid identification document and determine whether those features are present, employing techniques, such as determining whether direction-sensitive features are present. Liveness of a user indicated by the identification document may be determined with a deep learning model trained for identification of facial spoofing attacks.

Methods and systems for interacting with a user to build a customer profile include: receiving, by a processor, an identifier of the user; retrieving, by the processor, personal information of the user from a database system based on the identifier; recognizing, by the processor, preference information of the user from an image of the user; obtaining, by the processor, additional preference information of the user by managing a dialog between the user and a mirror display system; and storing, by the processor, the customer profile based on the personal information, the preference information, and the additional dialog information.

A controlled access entrance gate, comprising a frame or structure (11) that defines an entry area (I1), an exit area (I2) and a transit area (P) of a user (U), a actuation unit (13), which allows the passage of one or more subjects (U), an electronic control unit (14) and a plurality of sensors or cameras (15, 16). The sensors or cameras (15, 16), which can also be used as an independent kit and can be associated with any type of passage or area to be controlled, are suitable for detecting the data relating to the distance (DT) between each sensor (15, 16) and each subject (U) present in the entry area (11) or in the exit area (I2) or in the passage area (P) and the speed, trajectory and tracking parameters of the subject (U). An electronic control unit (14) receives and processes data through interpolation processes and machine-learning and/or deep-learning algorithms, so as to autonomously learn the characteristics of the passage and predict the forms and probabilistic directions of each subject (U) inside the volume corresponding to the entry (I1) and exit (I2) areas and to the transit area (P) of the passage.

Multifactor authentication techniques described herein may allow a user to submit a recent proof of purchase as a part of a multifactor authentication process to access an account associated with a financial institution. As part of the login process, the user may submit a proof of purchase associated with a transaction. The financial institution may determine information associated with the transaction, such as a merchant associated with the proof of purchase, a time of the transaction, the last four numbers of the transaction card used, a dollar amount, or any combination thereof. If the information matches one or more records in the transaction history of the user's account, the financial institution may authenticate the user and provide access to the account. In this way, the financial institution may leverage transaction history known to the financial institution and the user to authenticate the user.