Method and device for determining video annotation information, equipment and computer storage medium

A technology for labeling information and video information, applied in the field of information processing
CN109933688APending Publication Date: 2019-06-25BEIJING BAIDU NETCOM SCI & TECH CO LTD
4 Cites 14 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
BEIJING BAIDU NETCOM SCI & TECH CO LTD
Publication Date
2019-06-25

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The embodiment of the invention relates to a method and device for determining annotation information of a video, equipment and a computer readable storage medium. The method may include determining text information and video information in the video. The method may also include determining a first entity associated with the text information and a second entity associated with the video information. Further, the method may further include determining annotation information of the video based on the first entity and the second entity. According to the technical scheme, multi-mode video annotation can be achieved, and the applicability of the video annotation scheme is remarkably improved. Moreover, the entity information associated with the text information and the entity information associated with the video information can be used for mutual verification, so that the situation that the video annotation has errors is avoided.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] Embodiments of the present disclosure mainly relate to the field of information processing, and more specifically, relate to a method, device, device and computer storage medium for determining video annotation information. Background technique

[0002] In the current information flow, the proportion of short video content is constantly increasing, and its value is also becoming greater and greater. Annotating videos based on video content understanding can present the subject of the video to users in the form of text, thereby helping users to easily understand video information, realize personalized recommendations for users, and improve user stickiness of video-based multimedia products. However, traditional solutions generally perform single-modal entity annotation on videos, for example, annotating videos purely through text information or video information. The biggest problem with single-modal annotation is that it only considers one aspect of v...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More