NEURAL NETWORK-BASED KEY POINT TRAINING APPARATUS AND METHOD

Title:

NEURAL NETWORK-BASED KEY POINT TRAINING APPARATUS AND METHOD

Document Type and Number:

WIPO Patent Application WO/2022/004970

Kind Code:

A1

Abstract:

Disclosed are neural network-based key point training apparatus and method. The key point training apparatus according to one embodiment disclosed comprises: a key point model trained to extract key points from an input image; and an image reconstruction model trained to reconstruct the input image with the key points outputted by the key point model as the input.

More Like This:

WO/2023/250312	METHODS, SYSTEMS, AND COMPUTER PROGRAM PRODUCT FOR PRE-CATEGORIZING DRUG PRODUCTS BASED ON CHARACTERISTICS THEREOF TO REDUCE ARTIFICIAL INTELLIGENCE MODEL SIZE USED IN VALIDATING THE DRUG PRODUCTS
WO/2022/055795	DAMAGE DETECTION BASED ON IMAGES WITH VARYING RESOLUTIONS
WO/2021/069309	REINFORCEMENT LEARNING SYSTEMS FOR CONTROLLING WIRELESS COMMUNICATION NETWORKS

Inventors:

CHAE GYEONGSU (KR)
HWANG GUEMBUEL (KR)

Application Number:

PCT/KR2020/017404

Publication Date:

January 06, 2022

Filing Date:

December 01, 2020

Export Citation:

Click for automatic bibliography generation Help

Assignee:

DEEPBRAIN AI INC (KR)

International Classes:

G06N3/08; G06N3/04

Foreign References:

KR100368743B1	2003-01-24
JP2010218051A	2010-09-30
US10635917B1	2020-04-28
JP2015026922A	2015-02-05
JPH11213132A	1999-08-06

Attorney, Agent or Firm:

DOOHO IP LAW FIRM (KR)

Download PDF:

View/Download PDF PDF Help

Previous Patent: STEEL SHEET FOR HOT PRESSING AND MANUFACTURING METHOD THEREOF

Next Patent: LEARNING DEVICE AND METHOD FOR GENERATING IMAGE