Event detection model training method, device and event detection method

Abstract

The present invention provides an event detection model training method, device and event detection method. The event detection model training method includes: obtaining training image frames in a plurality of training videos with labels; using a target neural network model for each training video The training image frame extracts the feature vector; Taking the training video as a unit, the feature vector of the training image frame of each training video is distributed and matched, so that each training video corresponds to at least one training image frame set; for each training video, according to In at least one training image frame set corresponding to the training image frame, the training difficulty of the training image frame in descending order, sort at least one training image frame set; Perform training to obtain an event detection model. The embodiment of the present application can implement more accurate classification for training videos.

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, in practice, in the process of using a large number of training videos to train the neural network, due to individual differences between videos, the difficulty of learning d...

AI Technical Summary

Problems solved by technology

[0003] However, in practice, in the process of using a large number of training videos to train the neural network, due to individual differences between videos, the difficulty of learning different videos for the neural network is usually different.

For videos with complex pictures, the neural network is often unable to learn some features that are different from other videos, which leads to low accuracy of the final generated event detection model for video motion detection and poor classification results.

Images