Video classification method, training method of video classification model and related equipment
A video classification and model technology, applied in the field of image processing, can solve the problem of high cost of video classification, achieve the effect of increasing long-term feature performance, good airspace performance, and reducing costs
Active Publication Date: 2021-07-30
MASHANG CONSUMER FINANCE CO LTD
View PDF19 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The embodiment of the present application provides a video classification method, a video classification model training method and related equipment to solve the problem of high cost of video classification
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
[0035] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of this application.
[0036] see figure 1 , figure 1 is a flow chart of a video classification method provided in the embodiment of the present application, such as figure 1 shown, including the following steps:
[0037] Step 101, input the image frame sequence corresponding to the target video to the 3D convolutional network layer for feature extraction, and obtain the first feature map sequence;
[0038] In the embodiment of the present application, the above-mentioned target video is a vi...
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 present application provides a video classification method, a video classification model training method and related equipment, the method comprising: inputting the image frame sequence corresponding to the target video into the 3D convolutional network layer for feature extraction to obtain the first feature map sequence; using The first hybrid neural network performs short-term feature and spatial feature extraction on the first feature map sequence to obtain the second feature map sequence; uses the second hybrid neural network to perform long-term features, short-term features and spatial features on the second feature map sequence Extracting to obtain a third feature map sequence; using a classification network layer to classify the third feature map sequence to obtain a classification result of the target video. Compared with the prior art that uses a dual-stream method for video classification, the embodiments of the present application only need to train a deep neural network to implement video classification, thus reducing the cost of video classification.
Description
technical field [0001] The present application relates to the technical field of image processing, and in particular to a video classification method, a training method of a video classification model, and related equipment. Background technique [0002] With the development of communication technology, the application of video is more and more extensive. At the same time, the demand for video classification is also more and more extensive. Whether it is sharing video recommendations on social networks or monitoring security, video classification is required. When classifying videos, it is not only necessary to analyze the spatial information of the object in the video, but also to analyze the information in the time dimension. At present, the dual-stream method is usually used for video classification. The dual-stream method includes two channels, one channel is an RGB image channel, which is used to model spatial information, and the other channel is an optical flow channe...
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 Patents(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/41G06N3/047G06N3/045G06F18/2415G06F18/241
Inventor 赵幸福王洪斌周迅溢蒋宁吴海英
Owner MASHANG CONSUMER FINANCE CO LTD