公开(公告)号：US12094208B2

公开(公告)日：2024-09-17

申请号：US17502173

申请日：2021-10-15

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

Inventor： Hu Yang ,  Feng He ,  Qi Wang ,  Zhifan Feng ,  Chunguang Chai ,  Yong Zhu

IPC: G06K9/62 ,  G06F18/214 ,  G06F18/241 ,  G06F18/25 ,  G06N20/00 ,  G06V10/22 ,  G06V10/40 ,  G06V10/70 ,  G06V10/764 ,  G06V10/80 ,  G06V10/82 ,  G06V20/40 ,  G06V20/62 ,  G06V20/70 ,  G10L15/08 ,  G06N3/08 ,  G06V30/10

CPC classification number: G06V20/46 ,  G06F18/214 ,  G06F18/241 ,  G06F18/253 ,  G06N20/00 ,  G06V10/22 ,  G06V10/40 ,  G06V10/764 ,  G06V10/768 ,  G06V10/806 ,  G06V10/82 ,  G06V20/41 ,  G06V20/635 ,  G06V20/70 ,  G10L15/08 ,  G06N3/08 ,  G06V30/10

Abstract: The present disclosure discloses a video classification method, an electronic device and a storage medium, and relates to the field of computer technologies, and particularly to the field of artificial intelligence technologies, such as knowledge graph technologies, computer vision technologies, deep learning technologies, or the like. The video classification method includes: extracting a keyword in a video according to multi-modal information of the video; acquiring background knowledge corresponding to the keyword, and determining a text to be recognized according to the keyword and the background knowledge; and classifying the text to be recognized to obtain a class of the video.

公开(公告)号：US12112539B2

公开(公告)日：2024-10-08

申请号：US17450158

申请日：2021-10-06

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

Inventor： Qi Wang ,  Zhifan Feng ,  Hu Yang ,  Chunguang Chai

IPC: G06V20/40 ,  G06F18/22 ,  G06F18/25 ,  G06N3/045 ,  G06V10/80

CPC classification number: G06V20/46 ,  G06F18/22 ,  G06F18/25 ,  G06N3/045 ,  G06V10/806 ,  G06V20/48 ,  G06V20/49

Abstract: A video processing method, an electronic device and a storage medium are provided, and relate to the field of artificial intelligence, and particularly relates to the fields of deep learning, model training, knowledge mapping, video processing and the like. The method includes: acquiring a plurality of first video frames, and performing fine-grained splitting on the plurality of first video frames to obtain a plurality of second video frames; performing feature encoding on the plurality of second video frames according to multi-mode information related to the plurality of second video frames, to obtain feature fusion information for characterizing fusion of the multi-mode information; and performing similarity matching on the plurality of second video frames according to the feature fusion information, and obtaining a target video according to a result of the similarity matching.