Image content automatic description method constructed by Chinese visual vocabulary
A technology of visual vocabulary and image content, applied in the field of image semantic understanding, which can solve the problems of less image description data, complex sentence structure, and poor quality.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0021] Below at first the present situation of the image automatic generation description technology involved in the present invention is analyzed:
[0022] The current image automatic description generation methods can be summarized into three categories, namely template-based methods, similarity retrieval-based methods, and deep learning-based methods.
[0023] Thanks to the development of image object recognition technology, researchers have proposed template-based image description generation methods. Specifically, the object and its attribute information in the image are detected through target recognition, and then the information is embedded in a pre-designed template in an appropriate manner. In 2010, Farhadi et al. used detectors to detect objects in images to infer triples, and used templates to convert them into descriptive text. In 2011, Yang et al. used Hidden Markov Model to select possible objects, verbs, prepositions and scene types to fill sentence tem...
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