公开(公告)号：US20230206564A1

公开(公告)日：2023-06-29

申请号：US17940183

申请日：2022-09-08

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Hao DONG ,  Peng LIU ,  Haowen LI

IPC: G06T19/00 ,  G10L13/02

CPC classification number: G06T19/006 ,  G10L13/02

Abstract: Provided are a video processing method, an electronic device and a non-transitory computer-readable storage medium, relates to the field of data processing, and in particular to the field of video generation. The specific implementation solution is text content and a selection instruction are received, wherein the selection instruction is configured to indicate a model for generating a virtual object; the text content is converted into voice; a mixed deformation parameter set is generated according to the text content and the voice; and the model of the virtual object is rendered with the mixed deformation parameter set, so as to obtain a picture set of the virtual object, and generating, according to the picture set, a video that includes the virtual object for broadcasting the text content. By means of the present disclosure, it is possible to simplify a large number of complicated operations for video production.

公开(公告)号：US20230177326A1

公开(公告)日：2023-06-08

申请号：US17968688

申请日：2022-10-18

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Guibin WANG ,  Shijun CONG ,  Hao DONG ,  Lei JIA

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06N3/0454

Abstract: A technical solution for compressing a neural network model which relates to the field of artificial intelligence technologies, such as deep learning technologies, cloud service technologies, is disclosed. The method for compressing a neural network model includes: acquiring a to-be-compressed neural network model; determining a first bit width, a second bit width and a target thinning rate corresponding to the to-be-compressed neural network model; obtaining a target value according to the first bit width, the second bit width and the target thinning rate; and compressing the to-be-compressed neural network model using the target value, the first bit width and the second bit width to obtain a compression result of the to-be-compressed neural network model.