BOX DETECTION FOR OBJECT ATTACHMENT
    282.
    发明公开

    公开(公告)号:US20230252752A1

    公开(公告)日:2023-08-10

    申请号:US17666045

    申请日:2022-02-07

    Applicant: Lemon Inc.

    Abstract: The present disclosure describes techniques for determining a bounding box. An image may be received. An X-frame, a Y-frame, and a normal frame may be estimated based on the image using a first neural network. At least one planar region may be detected from the image using a second neural network. A vanishing point detection may be performed on each of the at least one planar region. Output of the first neural network may be fused with results of the vanishing point detection. A depth value of each pixel in at least one plane corresponding to the at least one planar region may be determined based at least in part on a result of the fusing. A location of a bounding box may be determined based at least in part on the depth value of each pixel in the at least one plane.

    FLEXIBLE LOAD BALANCING ON MULTIPATH NETWORKS
    283.
    发明公开

    公开(公告)号:US20230246966A1

    公开(公告)日:2023-08-03

    申请号:US18295783

    申请日:2023-04-04

    Applicant: Lemon Inc.

    CPC classification number: H04L47/125 H04L45/24

    Abstract: A computer system for flexible load balancing on a multipath network includes a processor that implements a multipath transport protocol as a transport layer of a network stack, a load balancer that distributes network traffic across a plurality of paths, and a congestion controller in communication with the load balancer. The congestion controller determines parameters for a message based on information received from the load balancer. A scheduler included in the load balancer selects a load balancing algorithm from a plurality of load balancing algorithms based on the parameters of the message received from the congestion controller and, based on the selected load balancing algorithm, determines a timing and a path for the message to be sent to the transport layer.

    IMPLEMENTATION OF INSTANT CORRUPTION DETECTION AND RECOVERY

    公开(公告)号:US20230237046A1

    公开(公告)日:2023-07-27

    申请号:US18130670

    申请日:2023-04-04

    CPC classification number: G06F16/2365 G06F16/24568

    Abstract: The present disclosure describes techniques for implementing instant corruption detection and recovery. A plurality of streams may be created in a storage device. Each of the plurality of streams may contain a sequence of metadata nodes of a same type. Each of the plurality of streams may maintain an initial state, a sequence of delta modifications to the initial state, and an actual state for each of the sequence of metadata nodes. A checking and recovery function associated with a particular stream among the plurality of streams may be determined. The checking and recovery function may comprise checking logic configured to detect corruptions by checking modification operations associated with metadata nodes in the particular stream. The checking and recovery function may further comprise recovery logic configured to perform recoveries from the corruptions. The checking and recovery function associated with the particular stream may be implemented in the storage device.

    EMBEDDING OPTIMIZATION FOR A MACHINE LEARNING MODEL

    公开(公告)号:US20230229736A1

    公开(公告)日:2023-07-20

    申请号:US17579566

    申请日:2022-01-19

    Applicant: Lemon Inc.

    CPC classification number: G06K9/6257 G06F17/16 G06N20/00

    Abstract: Embodiments of the present disclosure relate to feature selection via an ensemble of gating layers. According to embodiments of the present disclosure, a set of model parameter values for a machine learning model and a set of embedding vectors are determined for an input field of the machine learning model. The machine learning model is constructed to map an input sample in the input field to an embedding vector in the embedding vectors and process the embedding vector with the model parameter values to generate a model output. The machine learning model is trained by updating the model parameter values and the embedding vectors according to at least a first training objective function, the first training objective function being based on an orthogonality metric between embedding vectors in the embedding vectors and based on a difference between the model output and a ground-truth model output.

    Accessing user accounts and data from any computing device

    公开(公告)号:US11693986B1

    公开(公告)日:2023-07-04

    申请号:US17877662

    申请日:2022-07-29

    Abstract: The present disclosure describes techniques for accessing user accounts and data from any computing device. It may be determined whether an account of a user exists in a cloud service in response to receiving information associated with the user from any computing device. Data associated with the account may be stored by the cloud service. There may be a plurality of types of data associated with a plurality of security levels. The plurality of security levels may correspond to different security requirements. The data associated with the account may belong to at least one of the plurality of types of data. An instance of the account may be deployed to the computing device in response to determining that the account exists in the cloud service. The instance of the account may enable the user to access services via the computing device.

    OFFLOADING COMPUTATION BASED ON EXTENDED INSTRUCTION SET ARCHITECTURE

    公开(公告)号:US20230205532A1

    公开(公告)日:2023-06-29

    申请号:US18118367

    申请日:2023-03-07

    CPC classification number: G06F9/30189 G06F9/30145

    Abstract: The present disclosure describes techniques for offloading computation based on an extended instruction set architecture (ISA). The extended ISA may be created based on identifying functions executed multiple times by a central processing unit (CPU). The extended ISA may comprise hashes corresponding to the functions and identifiers of extended operations associated with the functions. The extended operations may be converted from original operations of the functions. The extended operations may be executable by a storage device. The storage device may be associated with at least one computational core. Code may be synthesized based at least in part on the extended ISA. Computation of the synthesized code may be offloaded into the storage device.

    Operational point sample group in coded video

    公开(公告)号:US11683529B2

    公开(公告)日:2023-06-20

    申请号:US17473425

    申请日:2021-09-13

    Applicant: Lemon Inc.

    Inventor: Ye-Kui Wang

    CPC classification number: H04N19/70 H04N19/172 H04N19/188 H04N19/30

    Abstract: Systems, methods and apparatus for visual media data processing are described. One method includes performing a conversion between a visual media data and a visual media file that stores a bitstream of the visual media data in multiple tracks according to a format rule that specifies that the file-level information includes a syntax element that identifies one or more tracks from the multiple tracks that contain a specific type of sample group that includes operation point information.

Patent Agency Ranking