A method for generating video summaries and related devices
A technology for video summarization and video frames, applied in the computer field, can solve the problems of time-consuming and labor-intensive, labeling errors, affecting the efficiency and accuracy of video summarization, and achieve the effect of improving efficiency and accuracy and ensuring quality.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0108] The embodiment of the present application provides a method for generating a video summary and a related device, which can be applied to a system or program including a video summary generation function in a terminal device. By acquiring a target video, wherein the target video includes a sequence of video frames, the video The frame sequence contains multiple video frames; then extract the image features of each video frame to generate an image feature sequence; and divide the video frame sequence into multiple target segment sequences to generate a paragraph feature sequence; further image feature sequence It is fused with the paragraph feature sequence to obtain the fusion feature; and then the reinforcement learning training is performed based on the fusion feature to generate a video summary. In this way, the unsupervised video summary generation process is realized. Due to the combination of image-level image features and depth-level paragraph features, the quality...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com