Image description generation method, model training method, equipment and storage medium
A technology of image description and description information, applied in the field of machine learning, can solve the problem of inaccurate image description information, achieve the effect of accurate target image description information and improve accuracy
Active Publication Date: 2019-12-20
SHENZHEN TENCENT COMP SYST CO LTD
View PDF4 Cites 23 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] In the image description generation method provided by the related art, the input parameters of the decoder only include the global feature vector and the label vector set of the target image, that is, the input parameters of the decoder only include the image information of the target image, which may easily lead to the generation of image description information Not accurate enough
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
[0039] In order to make the objectives, technical solutions and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below in conjunction with the accompanying drawings.
[0040] This solution has broad application prospects in artificial intelligence (AI) scenarios such as intelligent image recognition. For ease of description, the following briefly introduces the terms involved in each embodiment.
[0041] CNN (Convolution Neural Network, convolutional neural network) is a feedforward neural network that directly starts from the pixel features of the bottom layer of the image and extracts features from the image layer by layer. It is the most commonly used implementation model for encoders and is responsible for image encoding Into a vector.
[0042] RNN (Recurrent Neural Network, recurrent neural network), is a neural network with fixed weights, external inputs and internal states. It can be regarded as the beha...
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 invention discloses an image description generation method, a model training method, equipment and a storage medium, and belongs to the technical field of machine learning. The method comprises the following steps: acquiring a target image; generating a first global feature vector and a first annotation vector set of the target image; inputting the target image to the matching model, and generating a first multi-modal feature vector of the target image through the matching model, wherein the matching model is a model obtained by training according to the training image and the reference image description information of the training image; generating target image description information of the target image according to the first multi-modal feature vector, the first global feature vector and the first annotation vector set; and generating the multi-modal feature vector of the target image through the matching model obtained through training, and then inputting the multi-modal feature vector into the calculation model to obtain the description information of the target image, so the effect of improving the accuracy of the generated image description information is achieved in artificial intelligence scenes such as image recognition.
Description
[0001] This application is a divisional application of the invention patent application filed on August 30, 2017, with the application number 201710763735.3, and the invention title "Image description generation method, model training method, equipment and storage medium". Technical field [0002] The embodiments of the present invention relate to the field of machine learning technology, and in particular to an image description generation method, model training method, equipment, and storage medium. Background technique [0003] With the development of image recognition technology, the content information of the image can be transformed into the text description of the image through the algorithm. [0004] A related image description generation method includes: first encoding the acquired target image through an encoder, such as a feature extraction model, generating the global feature vector and label vector set of the target image, and then inputting the global feature vector and...
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 Applications(China)
IPC IPC(8): G06T9/00G06N3/04G06V10/776
CPCG06N3/049G06T9/002G06N3/045G06N3/084G06V10/454G06V10/82G06V10/776G06N3/044G06F18/214G06F18/217
Inventor 姜文浩马林刘威
Owner SHENZHEN TENCENT COMP SYST CO LTD