Semi-supervised cross-media feature learning retrieval method
A feature learning and cross-media technology, applied in the field of retrieval, can solve the problems affecting the computational complexity and large dimensions of the algorithm, and achieve the effects of reducing computational complexity, increasing diversity, and achieving robustness.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0074] The specific implementation manners of the present invention will be described below in conjunction with the accompanying drawings.
[0075] Such as figure 1 Shown is a flow chart of a semi-supervised cross-media feature learning method based on the present invention, combined below figure 1 The present invention is described further, and the concrete realization steps of the inventive method are as follows:
[0076] (1) Establish a multimedia database;
[0077] Described step (1) comprises the steps:
[0078] (1.1) Collect multimedia raw data: you can collect it yourself, or use a public data set. Here, for the accuracy of the data, use a public data set, Wikipedia data set;
[0079] (1.2) extract the feature of multimedia data: adopt appropriate method to extract the feature of every kind of media type data respectively;
[0080] (2) Obtain the projection matrix of different media types;
[0081] Described step (2) comprises the steps:
[0082] (2.1) Define the ...
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