Lemon Inc.

Beijing Zitiao Network Technology Co., Ltd.

Yufei Wang

Longyin Wen

Ye Yuan

Xinyao Wang

Guang Chen

Xin Gu

Xiaojie Li

Fan Chen

Sijie Zhu

The present disclosure describes techniques for generating representations of editing components using a machine learning model. Images and guidance tokens are input into a first sub-model of the machine learning model. The machine learning model is trained to distinguish the editing components from raw materials and generate the representations of the editing components. Tokens corresponding to the images are generated by the first sub-model based on the images and the guidance tokens. The tokens corresponding to the images and the guidance tokens are input into a second sub-model of the machine learning model. The second sub-model comprises a cross-attention mechanism. An embedding indicative of at least one editing component is generated based on the tokens corresponding to the images and the guidance tokens by the second sub-model.

Generating representations of editing components using a machine learning model

Provided are a processing method and apparatus, an electronic device and a medium. The method includes steps described below. A target video is acquired; video information of the target video is determined; copy information corresponding to the video information is generated by using a video description model, where the copy information is generated by using the video description model and based on a task prompt and a copy keyword. Through this method, the video description model is constrained based on the task prompt and the copy keyword, so that the copy information of the target video is generated more accurately, and the coupling degree between the copy information and the target video is improved.

Processing method and apparatus, electronic device and medium

Provided are a processing method, a terminal device, and a medium. The method includes the steps described below. Basic information of a target video is determined; attribute information of the target video is determined based on the basic information; in a case where the attribute information indicates that the target video is a video capable of being structured, chapter division is performed on the target video based on the basic information to obtain at least two video clips; and chapter description information of the at least two video clips, a key frame of the at least two video clips and video description information of the target video are determined.

Processing method, terminal device, and medium

Provided are a video processing method and apparatus, an electronic device, and a medium. The method includes that a candidate slice information set of an original video is determined based on video information of the original video, the original video is segmented into a plurality of video segments based on each piece of candidate slice information in the candidate slice information set, the plurality of video segments is input into an evaluation model to determine a piece of probability information of each piece of candidate slice information, and target slice information of the original video is determined based on the piece of probability information corresponding to each piece of candidate slice information.

Video processing method, electronic device, and non-transitory computer-readable storage medium

A target video and video description information corresponding to the target video are acquired; salient object information of the target video is determined; a key frame category of the video description information is determined; and the target video, the video description information, the salient object information and the key frame category are input into a processing model to obtain a timestamp of an image corresponding to the video description information in the target video.

Growing community of inventors

Los Angeles, CA, United States of America

Yufei Wang