An image description method of multi-level connection recurrent neural network
A cyclic neural network and image description technology, applied in the field of image description with multi-level connection cyclic neural network, can solve the problem of ignoring the attention information of deep semantic concepts of images and so on.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0030] Such as figure 1 As shown, an image description method of a multi-level connection recurrent neural network includes the following steps:
[0031] (1) Semantic attributes are extracted from the training set of tagged sentences, and an attribute vocabulary is constructed.
[0032] (2) The VGGNet model is used as the initial model of CNN, the single-label ImageNet dataset is used for pre-training of CNN parameters, and then the multi-label dataset MS COCO is used for fine-tuning of CNN parameters.
[0033] (3) Input the image to be described, divide it into different regions, input it into the trained CNN, express the image information into high-level semantic information, and obtain the prediction probability of semantic attributes.
[0034] (4) Send the image into the CNN network to extract the paraphrase vectors describing different regions.
[0035] (5) Calculate the weight corresponding to each interpretation according to the hidden variable information of the prev...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 
