Cross-modal hash retrieval method based on supervision graph embedding
A graph embedding, cross-modal technology, applied in digital data information retrieval, instrumentation, computing and other directions, can solve the problems of reduced hash code effectiveness, unsatisfactory retrieval results, quantization errors, etc., to enhance the ability to distinguish, The effect of improving retrieval performance and improving representation ability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0054] Detailed description of the specific embodiments of the present invention will be described in conjunction with the accompanying drawings:
[0055] Although the present invention specifies two modalities of images and text, the algorithm is easily extended to other modalities and more than two modalities. For convenience, the present invention considers only two modes of image and text.
[0056] Such as figure 1 As shown, a cross-mode hash retrieval method embedded based on the supervision chart, includes the following steps:
[0057] 1) Step S1, climb the graphic sample pair on the webpage that can be developed from the image and text mode, build a graphic data set, and randomly divided the data set as a training set and test set;
[0058] 2) Step S2, extract 512-dimensional Gist features and the 1000-dimensional Bow feature of all images in the training set and test concentration, respectively;
[0059] 3) Step S3, design the overall target function of the cross-mode hash...
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