公开(公告)号：US20220385710A1

公开(公告)日：2022-12-01

申请号：US17724122

申请日：2022-04-19

Applicant: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD.

Inventor： Ye CHEN ,  Xinqi XIE ,  Junke PENG ,  Yan WANG

IPC: H04L65/611 ,  H04L65/1093 ,  G06F3/0482 ,  G06F3/04817 ,  H04N21/2187 ,  H04N21/4788

Abstract: The present disclosure relates to a method and a device for displaying a virtual livestream room, a client, a server and a medium. When a user triggers an interactive operation on a livestream page, a client can determine room identifications of one or more virtual livestream rooms to be updated that are bound to the interactive operation, and send the room identifications to a server. The server queries relevant information of virtual livestream rooms corresponding to changes in their room state through the room identifications of the virtual livestream rooms, and sends the relevant information of the virtual livestream rooms to the client, so that the client can quickly locate and modify the relevant information of the virtual livestream rooms, to timely update the virtual livestream rooms on the livestream page, and refresh data of each virtual livestream room.

公开(公告)号：US20210029305A1

公开(公告)日：2021-01-28

申请号：US17021090

申请日：2020-09-15

Applicant: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD.

Inventor： Tang TANG ,  Yu MENG ,  Manyi CHEN ,  Ye LIN ,  Ye CHEN

IPC: H04N5/262 ,  G06K9/00 ,  H04N5/232 ,  H04N5/77

Abstract: Provided is a method for adding a video special effect. The method includes acquiring an image frame in a video, and recognizing a target human joint point of a user in the image frame; when a position of the target human joint point in the image frame satisfies a joint position condition, using the image frame as a target image frame and acquiring at least two consecutive image frames before the target image frame; determining a motion state of the target human joint point according to the target human joint point recognized in the at least two consecutive image frames; when the target human joint point satisfies a joint motion condition, acquiring a video special effect matching the video special effect condition; and adding, at a video position associated with the target image frame in the video, the video special effect matching the video special effect condition.

公开(公告)号：US20230005194A1

公开(公告)日：2023-01-05

申请号：US17782985

申请日：2020-11-03

Applicant: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD.

Inventor： Jingjing ZHUGE ,  Xu FAN ,  Ye CHEN ,  Shupeng ZHANG

IPC: G06T11/00 ,  G06T7/13

Abstract: An image processing method includes: recognizing a target contour of a target object in a target image collected at a current moment determining, in the target contour, a starting contour point corresponding to a starting contour position, a final contour point corresponding to a final contour position, and a split contour point corresponding to the current moment taking a line segment composed of contour points between the starting contour point and the split contour point in the target contour as a first line segment, and taking a line segment except the first line segment in the target contour as a second line segment rendering the first line segment according to a first color, and rendering the second line segment according to a second color.