FACILITATING COLLABORATION IN A WORK ENVIRONMENT

    公开(公告)号:US20230153758A1

    公开(公告)日:2023-05-18

    申请号:US17859988

    申请日:2022-07-07

    Applicant: Lemon Inc.

    CPC classification number: G06Q10/103

    Abstract: The present disclosure describes techniques for facilitating a collaborative environment. The techniques may comprise aggregating data shared by at least a subset of a plurality of users via a plurality of message threads and a plurality of virtual rooms in the collaborative environment. The data may be categorized into a plurality of categories based on determining relatedness of the data. Data associated with any category among the plurality of categories may be classified based on a plurality of types of the data associated with the category. One of the plurality of types of the data associated with the category may be displayed on a first computing device associated with a first user among the plurality of users.

    LABEL INFERENCE IN SPLIT LEARNING DEFENSES
    122.
    发明公开

    公开(公告)号:US20230143789A1

    公开(公告)日:2023-05-11

    申请号:US18149462

    申请日:2023-01-03

    Applicant: Lemon Inc.

    CPC classification number: G06N3/084 G06N3/045

    Abstract: Split learning is provided to train a composite neural network (CNN) model that is split into first and second submodels, including receiving a noise-laden backpropagation gradient, training the surrogate submodel by optimizing a gradient distance loss, and computing an updated dummy label using the first submodel and the trained surrogate submodel to infer label information of the second submodel. Noise can be added to a label of the second submodel or a shared backpropagation gradient to protect the label information.

    METHOD AND APPARATUS FOR CONVERTING PICTURE INTO VIDEO, AND DEVICE AND STORAGE MEDIUM

    公开(公告)号:US20230132137A1

    公开(公告)日:2023-04-27

    申请号:US18089348

    申请日:2022-12-27

    Applicant: Lemon Inc.

    Abstract: A method and apparatus for converting a picture into a video, and a device and a storage medium. The method for converting a picture into a video includes: partitioning an original picture to obtain a foreground region and a background region; performing an iterative transformation for visual depth on the background region, and storing an image obtained through each transformation as a picture frame to obtain multiple frames of images; and splicing the multiple frames of images to obtain a target video. The iterative transformation includes at least two transformations for visual depth.

    MUSIC PLAYING METHOD AND APPARATUS BASED ON USER INTERACTION, AND DEVICE AND STORAGE MEDIUM

    公开(公告)号:US20230131975A1

    公开(公告)日:2023-04-27

    申请号:US18087576

    申请日:2022-12-22

    Applicant: Lemon Inc.

    Abstract: A music playing method and apparatus based on user interaction, a device and a storage medium, which relate to the technical field of music videos. The method includes: capturing a target video through a video capturing apparatus; determining an audio processing mode corresponding to a target action when it is identified in the target video that a target object presents the target action; and playing music according to the audio processing mode. The target video is captured by the video capturing apparatus, and when the target object in the target video is identified to generate the target action, the corresponding audio processing mode is determined based on the target action, and music is played according to the audio processing mode.

    VIDEO CAPTURING METHOD, APPARATUS, DEVICE AND STORAGE MEDIUM

    公开(公告)号:US20230131151A1

    公开(公告)日:2023-04-27

    申请号:US18088167

    申请日:2022-12-23

    Applicant: Lemon Inc.

    Abstract: A video capturing method, an apparatus, a device and a storage medium are provided. The method is applied to a terminal device, the terminal device includes a camera, and the method includes: segmenting a to-be-segmented target object to obtain a target segmentation result in response to an input event of selecting the to-be-segmented target object among a plurality of objects presented in an acquisition image of the camera; displaying the target segmentation result; and fusing the target segmentation result, that is adjusted, with a to-be-fused video scene to generate a video in response to a triggering operation for adjusting the target segmentation result.

    PORTRAIT STYLIZATION FRAMEWORK USING A TWO-PATH IMAGE STYLIZATION AND BLENDING

    公开(公告)号:US20230124252A1

    公开(公告)日:2023-04-20

    申请号:US17501990

    申请日:2021-10-14

    Applicant: Lemon Inc.

    Abstract: Systems and method directed to generating a stylized image are disclosed. In particular, the method includes, in a first data path, (a) applying first stylization to an input image and (b) applying enlargement to the stylized image from (a). The method also includes, in a second data path, (c) applying segmentation to the input image to identify a face region of the input image and generate a mask image, and (d) applying second stylization to an entirety of the input image and inpainting to the identified face region of the stylized image. Machine-assisted blending is performed based on (1) the stylized image after the enlargement from the first data path, (2) the inpainted image from the second data path, and (3) the mask image, in order to obtain a final stylized image.

    Adaptation parameter set storage in video coding

    公开(公告)号:US11611752B2

    公开(公告)日:2023-03-21

    申请号:US17475826

    申请日:2021-09-15

    Applicant: Lemon Inc.

    Inventor: Ye-Kui Wang

    Abstract: Systems, methods and apparatus for encoding or decoding a file format that stores one or more images are described. One example method includes performing a conversion between a visual media file and a bitstream of a visual media data according to a format rule, where the format rule specifies that first adaptation parameter set network abstraction layer units are disallowed from being simultaneously stored in in the visual media file in (1) any one or both of samples of video coding layer tracks or sample entries of the video coding layer tracks, and (2) samples of non-video coding layer tracks, where the video coding layer tracks are tracks containing video coding layer network abstraction layer units, and where the first adaptation parameter set network abstraction layer units includes luma mapping with chroma scaling parameters for a video stream and scaling list parameters for the video stream.

    WEB AUTHENTICATION FOR NATIVE APPLICATION

    公开(公告)号:US20230076454A1

    公开(公告)日:2023-03-09

    申请号:US18056001

    申请日:2022-11-16

    Applicant: Lemon Inc.

    Inventor: Eugene Pivovarov

    Abstract: A web authentication system includes a native application to generate at least one safety parameter, a user agent instructed to perform web authentication with safety controls, and a relying party to generate an authentication result. The native application is to deliver the at least one safety parameter to the user agent, obtain the authentication result from the relying party via the user agent, and validate the authentication result with the relying party.

    STORAGE ENGINE FOR HYBRID DATA PROCESSING

    公开(公告)号:US20230063730A1

    公开(公告)日:2023-03-02

    申请号:US17462853

    申请日:2021-08-31

    Applicant: LEMON INC.

    Abstract: The present disclosure describes storage techniques for hybrid transactional and analytical processing. Data captured by a first processing engine may be received. The first processing engine may be configured to perform online transactional processing). Multiple replicas of logical logs generated based on the data may be distributed to a Delta Store by applying a quorum protocol on the multiple replicas. Data in the Delta Store are stored in a row format and are visible to a query for online analytical processing performed by a second processing engine. Data may be flushed from the Delta Store to a Base Store based on one or more predetermined rules. Data in the Base Store are stored in a columnar format and may be accessible by the second processing engine.

Patent Agency Ranking