Patent · US Active

Method of bidirectional image-text retrieval based on multi-view joint embedding space

US11106951B2 · kind B2 · utility

0Cited by
0References
8Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJan 29, 2018
Grant dateAug 31, 2021
Priority date
Expiry dateMay 26, 2038

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V30/274
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A bidirectional image-text retrieval method based on a multi-view joint embedding space includes: performing retrieval with reference to a semantic association relationship at a global level and a local level, obtaining the semantic association relationship at the global level and the local level in a frame-sentence view and a region-phrase view, and obtaining semantic association information in a global level subspace of frame and sentence in the frame-sentence view, obtaining semantic association information in a local level subspace of region and phrase in the region-phrase view, processing data by a dual-branch neural network in the two views to obtain an isomorphic feature and embedding the same in a common space, and using a constraint condition to reserve an original semantic relationship of the data during training, and merging the two semantic association relationships using multi-view merging and sorting to obtain a more accurate semantic similarity between data.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.