Image-text matching method and device and storage medium
By encoding images and performing vector matching using a pre-trained image-text encoding model, the matching text can be determined directly from the stored text vectors, solving the problem of low efficiency of image-text matching servers and achieving a faster image-text matching process.
CN112148839BActive Publication Date: 2026-05-29BEIJING XIAOMI PINECONE ELECTRONICS CO LTD
1 Cites 0 Cited by
Patent Information
- Application Number
- CN202011052223.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-09-29
- Publication Date
- 2026-05-29
- Estimated Expiration
- 2040-09-29
AI Technical Summary
Technical Problem
In existing technologies, image-text matching servers are inefficient, requiring multiple steps to achieve image-text matching, resulting in severe system delays.
Method used
The image is encoded using a pre-trained image-text encoding model to obtain an image vector. Then, the text vectors that are similar to the image vectors are determined from the pre-stored text vectors, and the matching text is directly determined without the need to search for candidate texts in the text library and encode them in real time.
Benefits of technology
It improved the processing efficiency of the image and text matching server, reduced system latency, and increased the speed of image and text matching.
✦ Generated by Eureka AI based on patent content.
Abstract
The present disclosure relates to a method and device for image-text matching and a storage medium. The method for image-text matching comprises: obtaining an image to be matched; inputting the image into a pre-trained image-text encoding model to encode the image and obtain an image vector; determining a text vector similar to the image vector from pre-stored text vectors; wherein the image-text encoding model comprises a text encoding sub-network for encoding text during training, and the pre-stored text vectors are determined by encoding pre-set texts using the text encoding sub-network; and determining the texts corresponding to a preset number of text vectors similar to the image vector as the texts matched with the image. The present disclosure can improve the efficiency of image-text matching of a server and reduce the system delay of the server.
Need to check novelty before this filing date? Find Prior Art