The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Jul. 21, 2020

Filed:

Dec. 01, 2016
Applicant:

Peking University Shenzhen Graduate School, Shenzhen, CN;

Inventors:

Wenmin Wang, Shenzhen, CN;

Liang Han, Shenzhen, CN;

Mengdi Fan, Shenzhen, CN;

Ronggang Wang, Shenzhen, CN;

Ge Li, Shenzhen, CN;

Shengfu Dong, Shenzhen, CN;

Zhenyu Wang, Shenzhen, CN;

Ying Li, Shenzhen, CN;

Hui Zhao, Shenzhen, CN;

Wen Gao, Shenzhen, CN;

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06F 16/00 (2019.01); G06T 11/60 (2006.01); G06F 40/30 (2020.01); G06F 40/216 (2020.01); G06F 40/284 (2020.01); G06N 20/00 (2019.01); G06K 9/00 (2006.01); G06K 9/62 (2006.01); G06N 3/08 (2006.01); G06N 7/00 (2006.01);
U.S. Cl.
CPC ...
G06F 40/30 (2020.01); G06F 16/00 (2019.01); G06F 40/216 (2020.01); G06F 40/284 (2020.01); G06K 9/00523 (2013.01); G06K 9/00536 (2013.01); G06K 9/628 (2013.01); G06K 9/6277 (2013.01); G06N 3/08 (2013.01); G06N 7/005 (2013.01); G06N 20/00 (2019.01); G06T 11/60 (2013.01);
Abstract

A cross-media search method using a VGG convolutional neural network (VGG net) to extract image features. The 4096-dimensional feature of a seventh fully-connected layer (fc7) in the VGG net, after processing by a ReLU activation function, serves as image features. A Fisher Vector based on Word2vec is utilized to extract text features. Semantic matching is performed on heterogeneous images and the text features by means of logistic regression. A correlation between the two heterogeneous features, which are images and text, is found by means of semantic matching based on logistic regression, and thus cross-media search is achieved. The feature extraction method can effectively indicate deep semantics of image and text, improve cross-media search accuracy, and thus greatly improve the cross-media search effect.


Find Patent Forward Citations

Loading…