A visual scene graph generation system and method based on relation regularization
A technology of scene graph and relationship, applied in the field of visual scene graph generation
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0064] The present invention aims to propose a system and method for generating a visual scene graph based on relational regularization, which can quickly and effectively judge whether there is a relation between objects, and is conducive to enhancing the detection effect of an object detection model.
[0065] In order to achieve the above purpose, the present invention designs a network based on relational regularization to generate a visual scene graph. Since previous work has proved that the label of the object has a great influence on the final scene graph, we propose the object label refinement module to improve the object label generated by Faster R-CNN. A relation generation module is then used to generate the final visual scene graph. Each module is composed of two-way long-short-term memory model (Bi-LSTMs) and graph convolutional network (GCNs). Bi-LSTMs are used to obtain features containing global context information, and then use this feature to obtain a relations...
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