Placing unobtrusive overlays in video content
A video content, obvious technology, applied in the superimposed field of inconspicuous positions, can solve the problems of not allowing, lacking automatic or interactive selection of advertising positions, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
other Embodiment approach
[0127] Other embodiments may employ user attention models for video summarization. According to these embodiments, there are two types of video summarization: static video abstraction and dynamic video scraping. Static video abstraction attempts to obtain keyframe collections from representative video content. Dynamic video scraping seeks to find a collection of video clips (video and audio) within indoor content that represent the entire video asset (with a much smaller total frame length or duration). These embodiments use a framework for video summarization (both static and dynamic) that considers video content as containing three types of information: visual, audio, and linguistic. Different saliency maps are generated from one or more of these different sources and combined to generate an attention curve for the video content. The attention curve can be smoothed and the portion of the video asset around the local maximum can be used as a generalization.
[0128] exempl...
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