Unlock instant, AI-driven research and patent intelligence for your innovation.

Video emotion positioning method and system

A positioning method and technology of positioning system, applied in the computer field, can solve the problems of small amount of emotional video data, difficulty in classifier training, unsatisfactory classification effect, etc., and achieve the effect of clear boundary

Active Publication Date: 2019-09-20
ZHONGAN INFORMATION TECH SERVICES CO LTD
View PDF6 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Some researchers apply the algorithm for the entire video to the emotional analysis of each frame. However, due to the small amount of emotional video data generated by users, it is difficult to train the classifier, and the classification effect only for each frame is not ideal.

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Video emotion positioning method and system
  • Video emotion positioning method and system
  • Video emotion positioning method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056]This embodiment provides a video emotion positioning method, which belongs to the field of computer technology and is applicable to various video emotion positioning business scenarios such as video retrieval, monitoring analysis, and advertisement delivery.

[0057] figure 1 A flow chart of a video emotion localization method provided in Embodiment 1, such as figure 1 As shown, the video emotion localization method specifically includes the following steps:

[0058] S1. Perform fragment positioning on the video to be processed, and extract several candidate fragments.

[0059] Step S1 is the preprocessing of the video to be processed, which is used to extract video candidate segments. The video to be processed can be an input video, or a pre-stored video in the database. For the video to be processed, a segment screening algorithm can be used to screen candidate segments.

[0060] Specifically, the video to be processed is positioned into n candidate segments throug...

Embodiment 2

[0106] In order to implement the video emotion localization method in the first embodiment above, this embodiment provides a video emotion localization system.

[0107] figure 2 It is a schematic structural diagram of a video emotion localization system provided by Embodiment 2 of the present invention. Such as figure 2 As shown, the video emotion localization system 100 at least includes:

[0108] Preprocessing module 1: used for segment positioning of the video to be processed, and extracting several candidate segments;

[0109] Feature extraction module 2: used to extract the feature representation of each frame of the candidate segment through the pre-trained first neural network model;

[0110] Classification and sorting module 3: used to perform emotional classification, boundary regression, emotional sorting and integrity classification on candidate segments based on the feature representation of each frame of the candidate segment through the pre-trained second ne...

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

No PUM Login to View More

Abstract

The invention discloses a video emotion positioning method and system and. A computer belongs to the technical field of computers, the video emotion positioning method comprises the following steps: extracting candidate fragments of a to-be-processed video; extracting feature representation of each frame of the candidate segment by using a first neural network model; and then carrying out the emotion classification, boundary regression, emotion sorting and integrity classification are carried out through the second neural network model, and finally filtering candidate fragments which do not meet requirements are filtered out and outputting emotion positioning fragments of the to-be-processed video are output, so that the fragments reflecting the emotion of the whole video in the video can be quickly and accurately positioned, and the boundaries of the positioned fragments are clear and complete.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a video emotion positioning method and system. Background technique [0002] With the development of the Internet and mobile devices, the identification of video content has attracted more and more attention from scientific researchers in recent years. There have been many studies on video classification and detection. However, video sentiment analysis has many difficulties due to the complexity of video content. Early research on emotional content mainly focused on image emotion recognition. In addition to overall image features, texture, location, face and other features also play a certain role in image emotion recognition tasks. In the field of video, early work mainly focused on sentiment analysis of movies, and the combination of the underlying visual and audio features achieved good results on some standard movie datasets. [0003] In recent years, convolutional neural...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/75G06F16/73
CPCG06F16/73G06F16/75
Inventor 徐宝函郑莹斌叶浩王恒孙谷飞
Owner ZHONGAN INFORMATION TECH SERVICES CO LTD