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

Micro-expression discovery method and system based on attention mechanism and one-dimensional convolution sliding window

A discovery method and attention technology, applied in the field of computer vision, can solve problems such as inaccurate positioning of micro-expressions in long videos, and achieve the effect of improving accuracy

Active Publication Date: 2022-08-02
SHANDONG UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this is still for the analysis of short videos, and a binary classification network is designed only for single short video recognition, which cannot analyze the relationship between frames from the perspective of a long video, resulting in inaccurate positioning of micro-expressions in long videos. exact question

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
  • Micro-expression discovery method and system based on attention mechanism and one-dimensional convolution sliding window
  • Micro-expression discovery method and system based on attention mechanism and one-dimensional convolution sliding window
  • Micro-expression discovery method and system based on attention mechanism and one-dimensional convolution sliding window

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] This embodiment provides a micro-expression discovery method based on an attention mechanism and a one-dimensional convolutional sliding window, including:

[0056] Obtaining continuous frame images of the video stream, preprocessing the continuous frame images, extracting spatial features, and extracting global features and local features for the spatial features;

[0057] According to the correlation between the global features of an image and other images, and the correlation between local features, the global attention weight and the local attention weight are obtained respectively. Attention feature and local attention feature, the global attention feature and local attention feature are fused to obtain the attention feature;

[0058] A one-dimensional convolution sliding window is used to set the step size and detection interval to move in the attention feature to extract the features in each detection interval, and perform micro-expression recognition on the feat...

Embodiment 2

[0113] This embodiment provides a micro-expression discovery system based on an attention mechanism and a one-dimensional convolution sliding window, including:

[0114] The feature extraction module is configured to obtain continuous frame images of the video stream, and after preprocessing the continuous frame images, extract spatial features, and extract global features and local features for the spatial features;

[0115] The attention extraction module is configured to obtain the global attention weight and the local attention weight according to the correlation between the global features of an image and other images, and the correlation between the local features, respectively, according to the global attention weight and the local attention weight to obtain the global attention feature and the local attention feature respectively, and the global attention feature and the local attention feature are fused to obtain the attention feature;

[0116] A micro-expression loca...

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 micro-expression discovery method and system based on an attention mechanism and a one-dimensional convolution sliding window, and the method comprises the steps: obtaining continuous frame images of a video stream, carrying out the extraction of spatial features, and carrying out the extraction of global features and local features of the spatial features; according to the correlation degree between the global features and the correlation degree between the local features of a certain image and other images, a global attention weight and a local attention weight are obtained respectively, and a global attention feature and a local attention feature are obtained respectively according to the global attention weight and the local attention weight. Fusing the global attention features and the local attention features to obtain attention features; a one-dimensional convolution sliding window is adopted to move in attention features according to a set step length and detection intervals so as to extract features in each detection interval, micro-expression recognition is performed on the features in each detection interval, and micro-expression recognition results of the detection intervals are grouped at intervals so as to more accurately position real micro-expression positions.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a method and system for finding micro-expressions based on an attention mechanism and a one-dimensional convolution sliding window. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] Micro-expression discovery refers to finding out the micro-expression interval from the video stream, and marking the start frame, vertex frame and end frame of the micro-expression; the start frame refers to the frame where the micro-expression begins to appear; the vertex frame refers to the movement range of the micro-expression The largest frame; the end frame is the frame where the micro-expression disappears. [0004] At first, almost all methods attempted to discover micro-expressions in videos by computing feature differences between frames and thresh...

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): G06V40/16G06V20/40G06V10/80G06V10/82G06N3/04
CPCG06V40/174G06V20/40G06V20/46G06V40/168G06V10/806G06V40/161G06V10/82G06N3/048G06N3/044G06N3/045Y02D10/00
Inventor 曹叶文周冠群蒋友军袁树森邢红波
Owner SHANDONG UNIV