Image Determination Model Training Method, Image Determination Method, Device, and Equipment
A training method and image technology, applied in the field of machine learning, can solve problems such as inaccurate determination, achieve the effect of improving recognition accuracy, reducing huge distribution differences and semantic gaps
Active Publication Date: 2021-05-28
长沙海信智能系统研究院有限公司
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0007] The embodiment of the present invention provides a training method, determination method, device, equipment and storage medium for an image determination model, which solves the problem that the image corresponding to the description cannot be accurately determined according to the natural language description in the existing technical solutions problem, improving the recognition accuracy of cross-modal pedestrian re-identification
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0036] The characteristics and exemplary embodiments of various aspects of the present invention will be described in detail below. In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only configured to explain the present invention, not to limit the present invention. It will be apparent to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is only to provide a better understanding of the present invention by showing examples of the present invention.
[0037] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The embodiment of the invention discloses a training method for an image determination model, an image determination method, device and equipment. By first obtaining the text information used to describe the image features; then based on the preset neural network and text information, the first image corresponding to the image features is generated; finally, according to the first image and the image in the preset image database, the neural network The training is performed to obtain an image determination model, which is used to determine the second image corresponding to the image feature according to the text information used to describe the image feature. It solves the problem that the image corresponding to the description cannot be accurately determined according to the natural language description in the existing technical solution, and improves the recognition accuracy rate of cross-modal pedestrian re-identification.
Description
technical field [0001] The invention relates to the field of machine learning, in particular to a training method for an image determination model, an image determination method, device and equipment. Background technique [0002] In recent years, with the construction of smart cities, cities around the world have installed a large number and variety of surveillance cameras, resulting in a lot of valuable surveillance video data. [0003] In response to the expectations of the police and other agencies to quickly obtain clues of suspects or find missing children and the elderly, pedestrian re-identification technology based on surveillance video data has attracted much attention. [0004] In practical application scenarios, descriptions of suspects or missing persons are often verbal, that is, descriptions in natural language are used to determine images, and thus cross-modal person re-identification based on natural language to determine images has begun to appear. [0005...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06N3/08
CPCG06N3/08G06F18/214
Inventor 闾凡兵曾雅文曹达秦拯姚胜曾海文
Owner 长沙海信智能系统研究院有限公司