Title:
METHOD AND DEVICE FOR GENERATING MODEL
Document Type and Number:
WIPO Patent Application WO/2019/237657
Kind Code:
A1
Abstract:
A method and device for generating a model. The method comprises: obtaining a training sample set, and dividing the training sample set into a preset number of training sample groups (201), wherein the training samples comprise sample videos and sample recognition results annotated in advance for the sample videos, and the sample recognition results are used for indicating whether the sample videos are videos obtained by photographing a screen that displays sample objects; for each of the preset number of training sample groups, using the sample videos of the training samples in the training sample group as input, using the sample recognition results corresponding to the input sample videos as expected output, and training by using a machine learning method to obtain an initial video recognition model corresponding to the training sample group (202); and generating a video recognition model based on the obtained initial video recognition model (203). By means of the method, a model for video recognition can be obtained, and the generation mode of the model is enriched.
Inventors:
LI WEIJIAN (CN)
WANG CHANGHU (CN)
WANG CHANGHU (CN)
Application Number:
PCT/CN2018/116339
Publication Date:
December 19, 2019
Filing Date:
November 20, 2018
Export Citation:
Assignee:
BEIJING BYTEDANCE NETWORK TECH CO LTD (CN)
International Classes:
G06K9/00
Foreign References:
| CN108805091A | 2018-11-13 | |||
| CN107766940A | 2018-03-06 | |||
| CN105354543A | 2016-02-24 | |||
| CN101833569A | 2010-09-15 |
Attorney, Agent or Firm:
INSIGHT INTELLECTUAL PROPERTY LIMITED (CN)
Download PDF: