Visual content retrieval

摘要

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating image search results. One of the methods includes receiving first image search results responsive to a text query, each first image search result associated with a respective first score indicating a relevance of an image represented by the first image search result to the text query. Second image search results responsive to a query image are received, each second image search result associated with a respective second score indicating a measure of similarity between an image represented by the second image search result and the query image. A set of final image search results is selected including combining first scores and second scores of the selected first image search results. The final image search results are ordered by similarity to the query image.

主权项

1. A computer-implemented method, the method comprising:
receiving first image search results responsive to a text query, each first image search result associated with a respective first score indicating a relevance of an image represented by the first image search result to the text query; receiving second image search results responsive to a query image, each second image search result associated with a respective second score indicating a measure of similarity between an image represented by the second image search result and the query image, wherein the measure of similarity is calculated based in part on a distance between a content descriptor associated with the query image and a content descriptor associated with the image; selecting one or more of the first image search results that also occur in the second image search results and whose respective first scores satisfy a first threshold; selecting a set of final image search results from only the selected one or more first image search results, including combining first scores and second scores of the selected first image search results; and ordering each of the final image search results by a score derived from a distance between the content descriptor associated with the query image and the content descriptor associated with the respective image represented by the final image search result.