FEDERATED LEARNING FOR MEDIA CONTENT RECOMMENDATION

    公开(公告)号:US20240193468A1

    公开(公告)日:2024-06-13

    申请号:US18077410

    申请日:2022-12-08

    Applicant: Lemon Inc.

    Inventor: Haipeng GAO

    CPC classification number: G06N20/00

    Abstract: A method is proposed for media content recommendation. In the method, a client device obtains a first version of a machine learning model for media content recommendation from a server. A first set of media contents is recommended based on local information of the client device according to the first version of the machine learning model. An update to the machine learning model is determined based on respective interactions of the user with the first set of media contents. The client device provides the update to the server.

    Display screen or portion thereof with a graphical user interface

    公开(公告)号:USD1029854S1

    公开(公告)日:2024-06-04

    申请号:US29815606

    申请日:2021-11-15

    Applicant: Lemon Inc.

    Abstract: FIG. 1 is a front view of a first embodiment of a display screen or portion thereof with a graphical user interface showing our new design; and,
    FIG. 2 is a front view of a second embodiment thereof.
    The outermost broken line rectangle illustrates a display screen or portion thereof and forms no part of the claimed design. The remaining broken lines illustrate portions of the graphical user interface that form no part of the claimed design.

    Techniques for zoned namespace (ZNS) storage using multiple zones

    公开(公告)号:US11989423B2

    公开(公告)日:2024-05-21

    申请号:US18056083

    申请日:2022-11-16

    Applicant: Lemon Inc.

    CPC classification number: G06F3/0619 G06F3/064 G06F3/0679 G06F12/0802

    Abstract: Described are examples for storing, in a first zone cache, one or more logical blocks (LBs) corresponding to a data chunk, writing, for each LB in the data chunk, a cache element of a cache entry that points to the LB in the first zone cache, where the cache entry includes multiple cache elements corresponding to the multiple LBs of the data chunk, writing, for the cache entry, a table entry in a mapping table that points to the cache entry, and when a storage policy is triggered for the cache entry, writing the multiple LBs, pointed to by each cache element of the cache entry, as contiguous LBs in an isolation block for the data chunk in a second zone stream, and updating the table entry to point to the isolation block in the second zone stream.

    Lightweight transformer for high resolution images

    公开(公告)号:US11983239B2

    公开(公告)日:2024-05-14

    申请号:US17342483

    申请日:2021-06-08

    Applicant: Lemon Inc.

    CPC classification number: G06F18/213 G06F18/24 G06N3/04 G06N3/08 G06V10/82

    Abstract: Systems and methods for obtaining attention features are described. Some examples may include: receiving, at a projector of a transformer, a plurality of tokens associated with image features of a first dimensional space; generating, at the projector of the transformer, projected features by concatenating the plurality of tokens with a positional map, the projected features having a second dimensional space that is less than the first dimensional space; receiving, at an encoder of the transformer, the projected features and generating encoded representations of the projected features using self-attention; decoding, at a decoder of the transformer, the encoded representations and obtaining a decoded output; and projecting the decoded output to the first dimensional space and adding the image features of the first dimensional space to obtain attention features associated with the image features.

    ON-CHIP INTEGRATED CIRCUIT, DATA PROCESSING DEVICE, AND DATA PROCESSING METHOD

    公开(公告)号:US20240152474A1

    公开(公告)日:2024-05-09

    申请号:US18414920

    申请日:2024-01-17

    Applicant: Lemon Inc.

    CPC classification number: G06F13/4027 G06F2213/40

    Abstract: An on-chip integrated circuit, a data processing device and a method are provided. The on-chip integrated circuit includes: a processor circuit and an accelerator circuit. The processor circuit includes a processor and a data storage area, the processor is connected to the data storage area through a first bus in the processor circuit. The accelerator circuit includes an accelerator and a second bus, the accelerator is connected to the second bus, and the second bus is bridged with the first bus corresponding to the data storage area, to perform data interaction between the accelerator and the data storage area, which can reduce the congestion on a bus of the processor and improve the quality of service of the application.

    Creation of videos using virtual characters

    公开(公告)号:US11978143B2

    公开(公告)日:2024-05-07

    申请号:US17751222

    申请日:2022-05-23

    Applicant: Lemon Inc.

    CPC classification number: G06T13/40 G06T15/005 G06T15/04 G06V40/10

    Abstract: The present disclosure describes techniques for creating videos using virtual characters. Creation of a video may be initiated by a user. Camera input comprising a human body of the user may be received. The camera input may be split into a first stream for removing the human body and a second stream for animating a virtual character in the video. An inpainting filter may be applied to remove the human body in real time from the camera input. The inpainting filter may be configured to accelerate texture sampling. Output of the inpainting filter may be blended with images comprised in the camera input to generate camera input backgrounds.

    VIDEO GENERATION METHOD AND APPARATUS, DEVICE AND MEDIUM

    公开(公告)号:US20240135501A1

    公开(公告)日:2024-04-25

    申请号:US18543969

    申请日:2023-12-18

    Applicant: Lemon Inc.

    Abstract: The present disclosure provides a video generation method, an apparatus, a device and a medium, and the method includes: acquiring background images; acquiring an image to be segmented comprising a target object; performing image segmentation for the target object on the image to be segmented to obtain a contour image corresponding to the target object; using the contour image as a foreground image of a target display video; and cyclically flipping the background images, and generating the target display video by fusing the foreground image and the background images, in which the background images are being cyclically flipped in the target display video.

Patent Agency Ranking