Patent · US Active

Complementary learning for multi-modal saliency detection

US12026930B2 · kind B2 · utility

0Cited by
0References
21Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 14, 2021
Grant dateJul 2, 2024
Priority date
Expiry dateOct 29, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V10/82
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A saliency detection explicitly models complementary information between appearance, or color, and depth information in images. A mutual-information minimization is used as a regularizer to reduce the redundancy between appearance features from RGB and geometric features from depth in the latent space. Then the latent features of each of the appearance and geometric modalities are fused to achieve multi-modal feature fusion for saliency detection.

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