Event detection model training method and device and event detection method

Abstract

The invention provides an event detection model training method and device and an event detection method. The event detection model training method comprises the steps that training image frames in anumber of training videos with tags are acquired; a target neural network is used to extract feature vectors for the training image frame in each training video; in the unit of each training video, aself-attention mechanism processing network is used to carry out at least two rounds of weight assignment on a feature vector matrix formed by the feature vectors of each training video; the weight-assigned feature vector matrix is input into a class prediction network for class prediction to acquire a probability vector of the event classification result of the training video; and an event detection model is trained according to the probability vector of the event classification result and the result of the comparison between tag vectors formed by the tags of the training videos. According tothe method, computational resources and training time consumption are reduced without affecting the accuracy of the model.

Description

technical field [0001] The present invention relates to the technical field of deep learning, in particular to an event detection model training method, device and event detection method. Background technique [0002] With the rapid development of neural networks in the fields of image, video, voice, and text, a series of intelligent products have been promoted, and users have higher and higher requirements for the accuracy of various models based on neural networks. When building an event detection model based on a neural network, in order for the neural network to fully learn the features of the images in the video to improve the classification of the event detection model, it is necessary to input a large number of training videos into the neural network to train the neural network. [0003] However, a lot of images are usually included in the training video, and the amount of data is very large. When using these training videos to train the neural network, although the ...

AI Technical Summary

Problems solved by technology

[0003] However, a lot of images are usually included in the training video, and the amount of data is very large

When using these training videos to train the neural network, although the accuracy of the trained model can be improved, it is precisely because of the large amount of data that the calculation required in the model training process is huge and consumes too much calculation. resources and training time

Images