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:
Dec. 06, 2022

Filed:

Aug. 01, 2018
Applicant:

Beijing Sensetime Technology Development Co., Ltd, Beijing, CN;

Inventors:

Xiaogang Wang, Hong Kong, CN;

Lijun Wang, Liaoning, CN;

Wanli Ouyang, Hong Kong, CN;

Huchuan Lu, Liaoning, CN;

Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06N 3/08 (2006.01); G06K 9/62 (2022.01); G06K 9/46 (2006.01); G06T 7/11 (2017.01); G06T 7/73 (2017.01); G06T 7/20 (2017.01); G06N 5/04 (2006.01); G06N 3/04 (2006.01); G06V 10/44 (2022.01); G06V 20/10 (2022.01);
U.S. Cl.
CPC ...
G06N 5/046 (2013.01); G06K 9/6262 (2013.01); G06K 9/6274 (2013.01); G06N 3/0454 (2013.01); G06N 3/084 (2013.01); G06T 7/11 (2017.01); G06T 7/20 (2013.01); G06T 7/73 (2017.01); G06V 10/454 (2022.01); G06V 20/10 (2022.01); G06T 2207/20081 (2013.01);
Abstract

Disclosed are methods, apparatuses and systems for CNN network adaption and object online tracking. The CNN network adaption method comprises: transforming a first feature map into a plurality of sub-feature maps, wherein the first feature map is generated by the pre-trained CNN according to a frame of the target video; convolving each of the sub-feature maps with one of a plurality of adaptive convolution kernels, respectively, to output a plurality of second feature maps with improved adaptability; training, frame by frame, the adaptive convolution kernels.


Find Patent Forward Citations

Loading…