Deep feature fusion video copy detection method based on attention mechanism

Abstract

The invention discloses a deep feature fusion video copy detection method based on an attention mechanism, and the method comprises the steps: (1) extracting a frame image from video data, and constructing an image pyramid through employing different scales; (2) taking the deep convolutional neural network model as a basic network, and adding an attention mechanism into a middle convolutional layer of the deep convolutional neural network model; (3) inputting the frame image and the image pyramid into a deep convolutional neural network model of an attention mechanism, and obtaining fusion features through splicing and fusion; (4) training a deep convolutional neural network model in a metric learning mode; and (5) obtaining source video data through similarity calculation by utilizing thetrained deep convolutional neural network model. According to the method, an attention mechanism and fusion of global features and local features are utilized, the problems that a traditional image processing method is low in efficiency and low in precision can be solved, and the problem that the global features cannot adapt to various complex changes can also be solved.

Description

technical field [0001] The invention relates to the technical field of multimedia information processing, in particular to an attention mechanism-based deep feature fusion video copy detection method. Background technique [0002] In today's mobile Internet era, due to the complexity of multimedia video data, the emergence of various video editing software, and a wide range of sources, it is more difficult to prevent the indiscriminate dissemination of tampered video data. Relevant network supervision departments want to effectively supervise online multimedia video data, and cannot rely solely on human supervision and user reports. [0003] The current solution is to use traditional image processing or global feature extraction methods. Traditional algorithms have low processing efficiency and low accuracy, while global feature extraction methods are good for general editing video processing, but for various complex transformations The edited video processing effect is dif...

AI Technical Summary

Problems solved by technology

[0003] The current solution is to use traditional image processing or global feature extraction methods. Traditional algorithms have low processing efficiency and low accuracy, while global feature extraction methods are good for general editing video processing, but for various complex transformations The edited video processing effect is difficult to meet expectations

Both traditional image processing and global feature extraction methods have certain defects for multimedia videos on the Internet.

Images