Image multi-subtitle automatic generation method based on multiscale hierarchical residual network
An automatic generation, multi-scale technology, applied in the field of multi-subtitle acquisition, can solve problems such as easy to ignore image details, achieve the effect of solving gradient disappearance and gradient explosion problems, reducing parameters, and increasing funnel structure
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0052] In order to describe the present invention in more detail, the technical solution of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
[0053] The multi-subtitle acquisition method provided in this embodiment can obtain a non-fixed number of categorical target descriptors in an image, and can be applied to semantic image search, the visual intelligence of chat robots, and the acquisition of subtitles of images and videos shared by social media.
[0054] The process of using the method for automatically generating image multiple captions based on the multi-scale hierarchical residual network in this embodiment to describe the target in the image semantically includes two parts: training and testing. Before describing these two parts, the following will focus on the multi-caption generation model adopted in this embodiment.
[0055] figure 1 It is a schematic diagram of the framework of a multi-subtitl...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap