Invention Grant
- Patent Title: System and a method for learning features on geometric domains
-
Application No.: US15006694Application Date: 2016-01-26
-
Publication No.: US10013653B2Publication Date: 2018-07-03
- Inventor: Michael Bronstein , Davide Boscaini , Jonatan Masci , Pierre Vandergheynst
- Applicant: Università della Svizzera italiana
- Applicant Address: CH Lugano
- Assignee: UNIVERSITÀ DELLA SVIZZERA ITALIANA
- Current Assignee: UNIVERSITÀ DELLA SVIZZERA ITALIANA
- Current Assignee Address: CH Lugano
- Agency: Saliwanchik, Lloyd & Eisenschenk
- Main IPC: G06T15/00
- IPC: G06T15/00 ; G06N3/08 ; G06F17/10 ; G06T19/00

Abstract:
A method for extracting hierarchical features from data defined on a geometric domain is provided. The method includes applying on said data at least an intrinsic convolution layer, including the steps of applying a patch operator to extract a local representation of the input data around a point on the geometric domain and outputting the correlation of a patch resulting from the extraction with a plurality of templates. A system to implement the method is also described.
Public/Granted literature
- US20170213381A1 SYSTEM AND A METHOD FOR LEARNING FEATURES ON GEOMETRIC DOMAINS Public/Granted day:2017-07-27
Information query
IPC分类:
G | 物理 |
G06 | 计算;推算或计数 |
G06T | 一般的图像数据处理或产生 |
G06T15/00 | 3D〔三维〕图像的加工 |