公开(公告)号：US20240007639A1

公开(公告)日：2024-01-04

申请号：US18075867

申请日：2022-12-06

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

Inventor： Xu Zhang ,  Le Shi

IPC: H04N19/132 ,  H04N19/105 ,  H04N19/172 ,  H04N19/177

CPC classification number: H04N19/132 ,  H04N19/105 ,  H04N19/172 ,  H04N19/177

Abstract: Provided are a video frame processing method, a model training method, a device and a storage medium, relates to a field of artificial intelligence, and in particular, to cloud computing, video processing, and medium cloud technology, and may be applied in an intelligent cloud scenario. The video frame processing method includes: acquiring a target characteristic corresponding to a current video frame in a video frame sequence to be encoded, in the case of the video frame sequence to be encoded satisfies a preset condition; inputting the target characteristic corresponding to the current video frame to a first target model, to obtain a first output result corresponding to the current video frame; and determining a first target group of pictures (GOP) length corresponding to the current video frame, based on the first output result corresponding to the current video frame.

公开(公告)号：US20250142049A1

公开(公告)日：2025-05-01

申请号：US18749192

申请日：2024-06-20

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

Inventor： Xu Zhang

IPC: H04N19/105 ,  H04N19/172

Abstract: A method for reference frame selection, an apparatus for reference frame selection, an electronic device and a storage medium are provided, which relates to the field of data processing technology, in particular to the fields of video coding technology and unsupervised learning technology. The method includes: acquiring a current frame to be processed and determining attribute information of the current frame; selecting candidate reference frames from a reference frame set according to the attribute information; clustering the selected candidate reference frames to obtain at least one cluster; and selecting one candidate reference frame from each of the at least one cluster and adding the one selected candidate reference frame from each of the at least one cluster to a reference frame list associated with the current frame. The technical solution herein provided can improve the accuracy of reference frame selection.