Search International and National Patent Collections

1. (WO2018121690) OBJECT ATTRIBUTE DETECTION METHOD AND DEVICE, NEURAL NETWORK TRAINING METHOD AND DEVICE, AND REGIONAL DETECTION METHOD AND DEVICE

Pub. No.:    WO/2018/121690    International Application No.:    PCT/CN2017/119535
Publication Date: Fri Jul 06 01:59:59 CEST 2018 International Filing Date: Fri Dec 29 00:59:59 CET 2017
IPC: G06K 9/00
Applicants: BEIJING SENSETIME TECHNOLOGY DEVELOPMENT CO., LTD
北京市商汤科技开发有限公司
Inventors: SHAO, Jing
邵婧
YAN, Junjie
闫俊杰
Title: OBJECT ATTRIBUTE DETECTION METHOD AND DEVICE, NEURAL NETWORK TRAINING METHOD AND DEVICE, AND REGIONAL DETECTION METHOD AND DEVICE
Abstract:
An object attribute detection method and device, a neural network training method and device, and a region detection method and device. The object attribute detection method comprises: inputting an image to be detected to an attention neural network for region detection to obtain at least one target region, in the image to be detected, associated with an object attribute of a target (S102); and inputting the image to be detected and the at least one target region to an attribute classification neural network for attribute detection to obtain object attribute information of the image to be detected (S104).