公开(公告)号：WO2023038576A2

公开(公告)日：2023-03-16

申请号：PCT/SG2022/050641

申请日：2022-09-06

Applicant: LEMON INC.

Inventor： WANG, Jialin ,  CHEN, Fangfei ,  GUO, Kaitong ,  CAO, Yi ,  CHU, Pangyang

IPC: H04L67/563 ,  H04L69/16 ,  H04L12/66 ,  H04L63/0272 ,  H04L63/0281

Abstract: Systems and methods directed to a third-party gateway that controls egress traffic from Internet Data Centers (IDC) and/or Virtual Private Clouds (VPC) are described. When egress traffic reaches the third-party gateway, a forward proxy may obtain a service identified or otherwise associated with the source IP address and port. Once, the service is identified, the third-party gateway may obtain a configuration rule specified by a rule manager to determine if the service is allowed to access the destination host(s). If the destination host is approved for the service, the forward proxy may send the traffic to the internet. If the destination host is not approved for the service, the forward proxy may block or otherwise drop the respective communication. In some examples, one or more auditors or auditing agencies may access essential information from the third-party gateway to view egress traffic logs and verify egress traffic approved destinations.

公开(公告)号：WO2023033724A2

公开(公告)日：2023-03-09

申请号：PCT/SG2022/050608

申请日：2022-08-25

Applicant: LEMON INC.

Inventor： LI, Qingkun ,  CHEN, Fangfei ,  YANG, Yang

IPC: H04L67/289 ,  H04L67/10 ,  H04W12/02 ,  H04L61/256

Abstract: Systems and method directed to providing a framework for a trustworthy and security compliant edge computing infrastructure are described. Such framework allows self-built edge datacenters to continue providing enhanced service quality in regions where user data and user privacy are of top concerns. In examples, the systems and methods may include an edge router configured to route a communication received from a mobile device to a network address translation appliance, the network address translation appliance associates an anonymous internet protocol address with an internet protocol address associated with the mobile device, and provides the request to an edge datacenter. The edge data center may request content and/or services from a technology partner datacenter via an application gateway for security and privacy that is configured to receive the request for content from the edge datacenter and determine if the request for content is associated with user protected information.

公开(公告)号：WO2023014292A2

公开(公告)日：2023-02-09

申请号：PCT/SG2022/050530

申请日：2022-07-26

Applicant: LEMON INC.

Inventor： YANG, Linjie ,  LIN, Peter ,  SALEEMI, Imran

IPC: G06T7/194 ,  H04N19/20 ,  G06N3/044 ,  G06N3/0455 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/30196 ,  G06T3/40 ,  G06T7/11 ,  G06V10/454 ,  G06V10/82 ,  G06V20/46 ,  G06V20/695

Abstract: The present disclosure describes techniques of improving video matting. The techniques comprise extracting features from each frame of a video by an encoder of a model, wherein the video comprises a plurality of frames; incorporating, by a decoder of the model, into any particular frame temporal information extracted from one or more frames previous to the particular frame, wherein the particular frame and the one or more previous frames are among the plurality of frames of the video, and the decoder is a recurrent decoder; and generating a representation of a foreground object included in the particular frame by the model, wherein the model is trained using segmentation dataset and matting dataset.

公开(公告)号：WO2023014284A2

公开(公告)日：2023-02-09

申请号：PCT/SG2022/050479

申请日：2022-07-08

Applicant: LEMON INC.

Inventor： NOSKIN, Dan ,  GUBMAN, Mike ,  GAO, Yaxi ,  SHI, Shengchuan ,  LIAO, Jie ,  CHEN, Yiling ,  WEIGELE, Chris ,  AN, Esther ,  NORTHWAY, Ryan ,  MCCLURE, Ray ,  LEWANDOWSKI, David ,  PAN, Keting ,  FAWLEY, Blake ,  CHEN, Yi ,  WANG, Yong ,  GORE, Mehul ,  LEE, Christine ,  BROWN, Vanessa ,  TIAN, Guangqian

IPC: G06T19/00 ,  G06V20/20 ,  G06F3/01

Abstract: Systems and methods for generating a video including a plurality of graphic objects provided in a shared environment is described. The method includes acquiring, at a first computing device, a shared session identifier from a shared session manager, the shared session identifier being associated with a first user identifier, receiving a selection of a second user identifier, causing the shared session identifier and the first user identifier to be provided to a second computing device associated with the second user identifier, receiving as input, a first graphic object for rendering to a display associated with the first computing device, the first graphic object being associated with the first user identifier, receiving from a data synchronizer, a second graphic object associated with the second user identifier and the shared session identifier for rendering to the display associated with the second computing device, and generating a video including graphic objects.

公开(公告)号：WO2022255941A2

公开(公告)日：2022-12-08

申请号：PCT/SG2022/050342

申请日：2022-05-23

Applicant: LEMON INC.

Inventor： RASHID, Imran ,  SMITH, Jordan ,  SMITH, Fraser ,  HAWKINS, Will ,  NEWTON-REX, Edmund Philip

IPC: H04N5/265 ,  G11B27/06 ,  G10L25/57 ,  G11B27/007 ,  G11B27/031

Abstract: The present invention relates to method for generating a video remix, the method comprising: receiving an input video (101); selecting at least one excerpt from the input video (103), wherein an audio signal of the selected excerpt includes at least one onset; determining a plurality of sub-sequences of the at least one excerpt (104); and rearranging the plurality of sub-sequences according to a predetermined pattern (105) to form the video remix.

公开(公告)号：WO2022235207A1

公开(公告)日：2022-11-10

申请号：PCT/SG2022/050214

申请日：2022-04-13

Applicant: LEMON INC.

Inventor： HAMILTON, Frank ,  KIM, Hwankyoo Shawn ,  LU, Zhixiong ,  LV, Qingyang ,  YU, Weishan ,  MA, Ben

IPC: G06T19/00 ,  G06F3/01 ,  G06V20/20 ,  G06F3/04817

Abstract: Systems and methods directed to placing user are described. More specifically, content is received and depth information corresponding to an external environment of the computing device is obtained. An indication to associate the content with a location based on the depth image is received from a user. Information for at least one plane associated with the depth information at the location is obtained; and a portion of the selected content is warped to match the at least one plane.

公开(公告)号：WO2022186780A1

公开(公告)日：2022-09-09

申请号：PCT/SG2022/050111

申请日：2022-03-03

Applicant: LEMON INC.

Inventor： YANG, Linjie ,  JIANG, Ziyu ,  LIU, Ding ,  WEN, Longyin

IPC: G06T7/194 ,  G06T7/33 ,  G06V10/26 ,  G06N3/02

Abstract: Systems and method directed to performing video object segmentation are provided. In examples, video data representing a sequence of image frames and video data representing an object mask may be received at a video object segmentation server. Image features may be generated based on a first image frame of the sequence of image frames, image features may be generated based on a second image frame of the sequence of image frames; and object features may be generated based on the object mask. A transform matrix may be computed based on the image features of the first image frame and image features of the second image frame; the transform matrix may be applied to the object features resulting in transformed object features. A predicted object mask associated with the second image frame may be obtained by decoding the transformed object features.

公开(公告)号：WO2022169414A1

公开(公告)日：2022-08-11

申请号：PCT/SG2022/050041

申请日：2022-01-28

Applicant: LEMON INC.

Inventor： WANG, Fernando ,  BUZINOVER, Michael ,  ZHANG, Jialiang ,  LI, Ning

IPC: G06F16/438 ,  G06F16/483 ,  G06F16/738 ,  G06F16/783

Abstract: A plurality of music samples and a plurality of images corresponding to the music samples may be stored in a database. The plurality of music samples may be sorted in an order of priority. Information associated with the plurality music samples may be sent to a user device. The user device may display the plurality of images corresponding to the plurality of music samples in the order of priority. The user device may receive information indicative of at least one video associated with a music sample in response to receiving user input indicative of a selection of an image among the plurality of images. The user device may display at least one sample video image corresponding to the at least one video associated with the music sample.

公开(公告)号：WO2023091080A2

公开(公告)日：2023-05-25

申请号：PCT/SG2022/050796

申请日：2022-11-03

Applicant: LEMON INC.

Inventor： SCHAGER, Nathan ,  ZHAO, Yixin

Abstract: Methods, systems and storage media for applying a pattern application effect to one or more frames of video are disclosed. Some examples may include: obtaining video data including one or more video frames, determining one or more segments in each of the one or more video frames, determining one or more object masks based on the one or more segments in each of the one or more video frames, combining, the one or more object masks into a single mask, obtaining pattern information, the pattern information representing one or more graphical effects to be applied to at least one layer of the one or more video frames, applying the pattern information to the single mask to generate masked pattern information and generating, by the computing device, a rendered video by adding the masked pattern information to the one or more video frames.

公开(公告)号：WO2023080845A2

公开(公告)日：2023-05-11

申请号：PCT/SG2022/050801

申请日：2022-11-04

Applicant: LEMON INC.

Inventor： LIU, Jing ,  LAI, Chunpong ,  SONG, Guoxian ,  LUO, Linjie

Abstract: Systems and methods directed to controlling the similarity between stylized portraits and an original photo are described. In examples, an input image is received and encoded using a variational autoencoder to generate a latent vector. The latent vector may be blended with latent vectors that best represent a face in the original user portrait image. The resulting blended latent vector may be provided to a generative adversarial network (GAN) generator to generate a controlled stylized image. In examples, one or more layers of the stylized GAN generator may be swapped with one or more layers of the original GAN generator. Accordingly, a user can interactively determine how much stylization vs. personalization should be included in a resulting stylized portrait.