公开(公告)号：WO2023080841A2

公开(公告)日：2023-05-11

申请号：PCT/SG2022/050757

申请日：2022-10-25

Applicant: LEMON INC.

Inventor： SCHAGER, Nathanael ,  CRICHTON, Maryyann ,  GALLIPOLI, Jefrain

Abstract: Systems and methods directed to rendering a dynamic eyelash attachment to an eye identified in a video are described. In examples, a dynamic eyelash template may be applied to a video, where the dynamic eyelash template configures an eyelash skeleton that includes eyelash skeleton branches. Further, the video with one or more video frames may be received such that eye keypoints associated with a shape of the eye in the video frames can be identified. Accordingly, the eyelash skeleton branches may be attached to areas corresponding to eye keypoints based on the dynamic eyelash template. A three-dimensional rotation of the eyelash skeleton branches may be configured to conform to the shape of the eye defined by the eye keypoints during an eye movement. Thus, a dynamic effect can be added to the eyelash skeleton to allow the eyelash skeleton branches to rotate and bounce during the eye movement.

公开(公告)号：WO2023063879A2

公开(公告)日：2023-04-20

申请号：PCT/SG2022/050703

申请日：2022-09-29

Applicant: LEMON INC.

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

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.

公开(公告)号：WO2023063878A2

公开(公告)日：2023-04-20

申请号：PCT/SG2022/050698

申请日：2022-09-28

Applicant: LEMON INC.

Inventor： NOSKIN, Dan ,  YANG, Jiacheng ,  HU, Bo ,  GAO, Shouhan ,  TANGUTURI, Vishnuvardhan ,  LI, Yunjiu ,  GAO, Yaxi ,  CHEN, Zhili ,  ZHU, Yiheng ,  ZHANG, Yuxi ,  HUANG, Chaoran

Abstract: Systems and methods for managing a presentation of a dynamic profile photo are provided. In particular, a server may receive contextual information associated with one or more users. The server may determine that the contextual information is consistent with a predetermined contextual action. In some examples, the server may identify a dynamic profile photo associated with the predetermined contextual information; and present, in response to the determination that the contextual information is consistent with the predetermined contextual action, the dynamic profile photo to the one or more users.

公开(公告)号：WO2023038573A2

公开(公告)日：2023-03-16

申请号：PCT/SG2022/050605

申请日：2022-08-25

Applicant: LEMON INC.

Inventor： PRIVITELLI, Anthony ,  WEIGELE, Chris ,  BUZINOVER, Michael

IPC: G06F3/048 ,  G06Q30/0251 ,  H04N21/20

Abstract: The present disclosure describes techniques for presenting information associated with content creators. The techniques comprise receiving information about a first subset of users selected based on information about a first users, displaying information about a second user among the first subset of users in a first area of a user interface, displaying information about a plurality of users among a second subset of users in a second area of the user interface while displaying the information about the second user in the first area, determining that the first user has a desire to review information about a third user among the first subset of users based on user input, displaying information about the third user in the first area, and displaying information about a plurality of users among a third subset of users in the second area while displaying the information about the third user in the first area.

公开(公告)号：WO2023033721A2

公开(公告)日：2023-03-09

申请号：PCT/SG2022/050550

申请日：2022-08-02

Applicant: LEMON INC.

Inventor： CHEN, Jianjun ,  DING, Yonghua ,  LIU, Ye ,  LI, Fangshi ,  ZHANG, Li ,  ZHANG, Mingyi ,  WEI, Kui ,  DING, Wei ,  WU, Kai ,  SUN, Jason Yang

IPC: G06F16/27 ,  G06F16/21

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.

公开(公告)号：WO2023033720A2

公开(公告)日：2023-03-09

申请号：PCT/SG2022/050549

申请日：2022-08-02

Applicant: LEMON INC.

Inventor： CHEN, Jianjun ,  DING, Yonghua ,  LIU, Ye ,  LI, Fangshi ,  CAO, Lixun ,  LIU, Yang ,  ZHANG, Li ,  ZHANG, Mingyi ,  MENG, Xiangrui ,  ZHAO, Junda ,  ZHANG, Lei ,  SHI, Rui

IPC: G06F16/23 ,  G06F16/27 ,  G06F16/28 ,  G06F16/22 ,  G06F16/901 ,  G06F16/2358 ,  G06F16/2365 ,  G06F16/278 ,  G06F16/283

Abstract: The present disclosure describes techniques of providing data consistency for hybrid transactional and analytical processing. Logical logs and log serial numbers (LSNs) associated with the logical logs may be generated based on data captured by a first processing engine. The logical logs and the LSNs may be propagated to a storage subsystem configured to be in communication with the first processing engine and a second processing engine. The LSNs and information indicative of LSN schema versions may be stored and distributed by a metadata service. The first processing engine, the second processing engine, the storage subsystem and the metadata service are modularized, and support a LSN mechanism for maintaining data consistency.

公开(公告)号：WO2023009060A1

公开(公告)日：2023-02-02

申请号：PCT/SG2022/050345

申请日：2022-05-24

Applicant: LEMON INC.

Inventor： MA, Wanchun ,  CHENG, Shuo ,  WANG, Chao ,  TAY, Michael Leong Hou ,  LUO, Linjie

IPC: G06V10/82 ,  G06V40/16 ,  G06N3/0464

Abstract: The present disclosure describes techniques for face tracking. The techniques comprise receiving landmark data associated with a plurality of images indicative of at least one facial part. Representative images corresponding to the plurality of images may be generated based on the landmark data. Each representative image may depict a plurality of segments, and each segment may correspond to a region of the at least one facial part. The plurality of images and corresponding representative images may be input into a neural network to train the neural network to predict a feature associated with a subsequently received image comprising a face. An animation associated with a facial expression may be controlled based on output from the trained neural network.

公开(公告)号：WO2022260591A1

公开(公告)日：2022-12-15

申请号：PCT/SG2022/050296

申请日：2022-05-10

Applicant: LEMON INC.

Inventor： LIAN, Xiaochen ,  YANG, Linjie ,  WANG, Peng ,  JIN, Xiaojie ,  DING, Mingyu

IPC: G06N3/08 ,  G06N3/04

Abstract: Systems and methods for searching a search space, specifically neural architecture search, are disclosed. Some examples may include using a first parallel module including a first plurality of stacked searching blocks and a second plurality of stacked searching blocks to output first feature maps of a first resolution and to output second feature maps of a second resolution. In some examples, a fusion module is configured to generate multiscale feature maps by fusing one or more feature maps of the first resolution received from the first parallel module with one or more feature maps of the second resolution received from the first parallel module, and wherein the fusion module is configured to output the multiscale feature maps and output third feature maps of a third resolution. The searching blocks can comprise a transformer with a projection function for learning self-attention in low-dimensional space.

公开(公告)号：WO2022260590A1

公开(公告)日：2022-12-15

申请号：PCT/SG2022/050295

申请日：2022-05-10

Applicant: LEMON INC.

Inventor： LIAN, Xiaochen ,  DING, Mingyu ,  YANG, Linjie ,  WANG, Peng ,  JIN, Xiaojie

IPC: G06N3/02 ,  G06V10/77 ,  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.

公开(公告)号：WO2022075920A1

公开(公告)日：2022-04-14

申请号：PCT/SG2021/050570

申请日：2021-09-20

Applicant: LEMON INC.

Inventor： LI, Yunjiu ,  YANG, Siyao ,  YE, Xin ,  FAN, Wenjing ,  ZHU, Yiheng

IPC: G06F3/01 ,  G06T19/00 ,  G06K9/00 ,  G06Q50/00 ,  H04W4/029

Abstract: Systems and methods for social networking using augmented reality are disclosed. A network may receive, from a plurality of client devices, a request to connect to a server. The server may be associated with an object, such as a landmark or a product. The server may serialize an AR world including the object and content associated with the objectand send, to the plurality of client devices, data indicative of the AR world. The server via network may receive, from a first client device among the plurality of client devices, an indication of user input associated with the AR world. The indication of user input may comprise text data, digital image data, or user feedback. The indication of user input may be broadcast to the plurality of client devices.