Accuracy Enhancement Method of Temporal Visual Media Semantic Indexing Based on Non-negative Tensor Decomposition

A technology of non-negative tensor decomposition and precision enhancement, which is applied in the field of visual media processing, can solve problems such as the inability to make better use of time features, and achieve good precision enhancement effects, strong flexibility and adaptability, and enhanced accuracy.

Active Publication Date: 2020-04-24
TSINGHUA UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the process of global enhancement, the weighted matrix decomposition method used in this patent application cannot make better use of the temporal characteristics of the appearance of semantic concepts in time-series visual media, so there are still problems in the process of enhancing the accuracy of semantic indexing of time-series visual media. room for improvement

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
  • Accuracy Enhancement Method of Temporal Visual Media Semantic Indexing Based on Non-negative Tensor Decomposition
  • Accuracy Enhancement Method of Temporal Visual Media Semantic Indexing Based on Non-negative Tensor Decomposition
  • Accuracy Enhancement Method of Temporal Visual Media Semantic Indexing Based on Non-negative Tensor Decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The non-negative tensor decomposition-based time-series visual media semantic index precision enhancement method proposed by the present invention comprises the following steps:

[0028] (1) Perform semantic indexing on the objects and scenes contained in the initial time-series visual media respectively, obtain the initial detection confidence value of the time-series visual media semantic index, and obtain a tensor T(T ijk ) N×M×L , wherein, L represents the total number of segments that the time-series visual media is divided into segments by a fixed time interval, N represents the number of consecutive pictures contained in each time interval, and M represents the concepts in the time-sequence visual media (i.e. objects or The number of scenes), each element T in the tensor T ijk Indicates the detection confidence value of the i-th picture for the j-th concept (ie object or scene) in the k-th time interval, 1≤k≤L;

[0029] (2) Set a detection confidence threshold,...

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 relates to a nonnegative tensor decomposition-based time sequence visual media semantic index precision enhancement method, and belongs to the technical field of visual media processing.The method comprises the following steps of: firstly carrying out semantic indexing on objects and scenes in a time sequence visual media; constructing confidence coefficient tensors; screening partial elements through threshold value judgement; and re-estimating screened tensors by applying a weighted nonnegative tensor decomposition method so as to complete precision enhancement. The method hasthe advantage of enhancing the correctness of time sequence visual media semantic indexing by utilizing a time sequence semantic relationship. The method does not depend on mass annotation data setsand knowledge bases, and has strong flexibility and adaptability. By adoption of weighted nonnegative tensor decomposition, the flexibility and effect of the method are improved. The method is low incalculation complexity, strong in extensibility and suitable for practical industrial application.

Description

technical field [0001] The invention relates to a time-series visual media semantic index precision enhancement method based on non-negative tensor decomposition, which belongs to the technical field of visual media processing. Background technique [0002] Accuracy enhancement of semantic indexing of visual media is a key technology to further improve indexing results by using concept correlation. The function of this index enhancement technology is to give the result of concept detection of visual media, adjust and improve the quantitative relationship of concepts applied to the result of concept detection, so as to achieve the purpose of effectively indexing a large number of visual media. The patent application titled "A Accuracy Enhancement Method for Visual Media Semantic Indexing" (Application No.: 201610108055.3) discloses a combination of global enhancement and local improve. However, in the process of global enhancement, the weighted matrix decomposition method u...

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 Patents(China)
IPC IPC(8): G06F16/71
CPCG06F16/71
Inventor 王鹏孙立峰杨士强晏晨
Owner TSINGHUA UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap