公开(公告)号：US20240104808A1

公开(公告)日：2024-03-28

申请号：US17954098

申请日：2022-09-27

Applicant: Lemon Inc. ,  Douyin Vision Co., Ltd.

Inventor： Thomas OEFVERSTROEM ,  Kin Chung WONG ,  Yuyang TIAN ,  Long JIANG ,  Christopher JUNEJA

IPC: G06T11/60 ,  H04L51/046 ,  H04L51/52

CPC classification number: G06T11/60 ,  H04L51/046 ,  H04L51/52

Abstract: Example aspects include techniques for creating video stickers from user-generated content. These techniques may include receiving selection of a video content item previously uploaded to a SMP server application corresponding to the SMP client application, and presenting a graphical user interface (GUI) for receiving one or more derivative attributes for generating a derivative video sticker from the video content item. In addition, the techniques may include adding the derivative video sticker to a library of stickers provided by the SMP server application to a plurality of SMP client applications, and presenting the derivative video sticker within a communication interface associated with the SMP server application.

公开(公告)号：US20240346820A1

公开(公告)日：2024-10-17

申请号：US18301165

申请日：2023-04-14

Applicant: Lemon Inc.

Inventor： Siqi TAN ,  Longyin WEN ,  Xinyao WANG ,  Erica Lynne RUZIC ,  Kin Chung WONG ,  Yi DUAN ,  Thomas OEFVERSTROEM

IPC: G06V20/40 ,  G06F40/40 ,  G06V10/70 ,  G06V20/62 ,  G10L15/26 ,  G10L25/57

CPC classification number: G06V20/41 ,  G06F40/40 ,  G06V10/70 ,  G06V20/62 ,  G10L15/26 ,  G10L25/57 ,  G06F3/0482

Abstract: The present disclosure provides systems and methods for generating comments corresponding to an input video. Given an input video, comments with content relevant to the input video can be generated. One aspect includes a computing system comprising a processor and memory. The processor can be configured to execute a program using portions of the memory to receive an input video in a social networking system, generate at least one predicted comment corresponding to the input video based on video frames of the input video and a user profile of a target user, and present the at least one predicted comment to the target user.