NEURAL NETWORK METHOD AND APPARATUS

    公开(公告)号:US20230021306A9

    公开(公告)日:2023-01-19

    申请号:US17574408

    申请日:2022-01-12

    Abstract: A lightened neural network method and apparatus. The neural network apparatus includes a processor configured to generate a neural network with a plurality of layers including plural nodes by applying lightened weighted connections between neighboring nodes in neighboring layers of the neural network to interpret input data applied to the neural network, wherein lightened weighted connections of at least one of the plurality of layers includes weighted connections that have values equal to zero for respective non-zero values whose absolute values are less than an absolute value of a non-zero value. The lightened weighted connections also include weighted connections that have values whose absolute values are no greater than an absolute value of another non-zero value, the lightened weighted connections being lightened weighted connections of trained final weighted connections of a trained neural network whose absolute maximum values are greater than the absolute value of the other non-zero value.

    METHOD AND APPARATUS WITH ADAPTIVE OBJECT TRACKING

    公开(公告)号:US20220138493A1

    公开(公告)日:2022-05-05

    申请号:US17246803

    申请日:2021-05-03

    Abstract: Disclosed is a method and apparatus for adaptive tracking of a target object. The method includes method of tracking an object, the method including estimating a dynamic characteristic of an object in an input image based on frames of the input image, determining a size of a crop region for a current frame of the input image based on the dynamic characteristic of the object, generating a cropped image by cropping the current frame based on the size of the crop region, and generating a result of tracking the object for the current frame using the cropped image.

    METHOD AND APPARATUS WITH NEURAL NETWORK OPERATION PROCESSING

    公开(公告)号:US20220019895A1

    公开(公告)日:2022-01-20

    申请号:US17124791

    申请日:2020-12-17

    Abstract: A processor-implemented neural network method includes: obtaining a first weight kernel of a weight model and pruning information of the first weight kernel; determining, based on the pruning information, a processing range of an input feature map for each weight element vector of the first weight kernel; performing a convolution operation between the input feature map and the first weight kernel based on the determined processing range; and generating an output feature map of a neural network layer based on an operation result of the convolution operation.

    FACE VERIFICATION METHOD AND APPARATUS
    26.
    发明申请

    公开(公告)号:US20200320280A1

    公开(公告)日:2020-10-08

    申请号:US16904635

    申请日:2020-06-18

    Abstract: Disclosed is a face verification method and apparatus. The method including analyzing a current frame of a verification image, determining a current frame state score of the verification image indicating whether the current frame is in a state predetermined as being appropriate for verification, determining whether the current frame state score satisfies a predetermined validity condition, and selectively, based on a result of the determining of whether the current frame state score satisfies the predetermined validity condition, extracting a feature from the current frame and performing verification by comparing a determined similarity between the extracted feature and a registered feature to a set verification threshold.

    APPARATUS AND METHOD WITH IMAGE RECOGNITION-BASED SECURITY

    公开(公告)号:US20230049715A1

    公开(公告)日:2023-02-16

    申请号:US17675015

    申请日:2022-02-18

    Abstract: An apparatus and a method with image recognition-based security are disclosed. The method includes, for an unlocked terminal, tracking a face detected in a previous frame, detecting a background region change between the previous frame and a current frame based on a region of the tracked face, when the background region change is not detected, determining whether a state maintenance time fails to meet a preset time, in response to the state maintenance time failing to meet the preset time, determining an operation mode to be a first operation mode for determining whether recognition succeeds for the current frame, performing the first operation mode, including performing face detection with respect to the current frame, and maintaining the unlocked state of the terminal for the current frame when the face is detected as a result of the performing of the face detection, representing that the recognition succeeded for the current frame.

Patent Agency Ranking