Multimedia document summarization

A technology for multimedia documents and documents, which is applied in multimedia data retrieval, file management systems, dynamic trees, etc., and can solve problems such as not including image summarization

Active Publication Date: 2017-05-31
ADOBE INC
View PDF8 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, general aspects about images are not actually included

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
  • Multimedia document summarization
  • Multimedia document summarization
  • Multimedia document summarization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] review

[0017] Multimedia document summarization techniques are described. That is, given a document that includes different content types (e.g., text and a set of images), various embodiments generate summaries by extracting relevant segments of text in the document and related segments of images, where the Amount of text and number / dimensions of images.

[0018] In one or more implementations, the model is utilized to generate document summaries that take into account different content types, such as text and images. For both text and image contexts, the model produces multimodal summaries with high cohesion between summarized image segments and text segments, while maximizing the amount of information in the summaries (in terms of the coverage of document content and by the summarization both in terms of the diversity of information provided).

[0019] In the context of this document, "degree of cohesion" refers to the correlation between different content type...

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

Multimedia document summarization techniques are described. That is, given a document that includes text and a set of images, various implementations generate a summary by extracting relevant text segments in the document and relevant segments of images with constraints on the amount of text and number/size of images in the summary.

Description

technical field [0001] The present disclosure relates to multimedia document summarization. Background technique [0002] Summarizing documents (such as articles, etc.) that include multimedia content (such as text and images) often involves providing excerpts of text and images that are assumed to provide an overview of the document. However, many current approaches tend to tackle the summarization task only with respect to the textual part of the document. For image parts, these methods use the first or top full-size image as a thumbnail, regardless of the context of the image part and how it can be related to the text part. Therefore, general aspects about images are not actually included. This ignores the fact that other images or parts may be more relevant to the text part, so that collectively the other image parts and the text part will provide better, more relevant information content. Contents of the invention [0003] Multimedia document summarization techniqu...

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): G06F17/30
CPCG06F16/435G06F16/4393G06F16/94G06F16/345G06N3/088G06N5/022G06F40/30G06N5/01G06N3/044G06N3/045G06F16/40G06F16/93G06F40/166
Inventor N·莫达尼V·苏布拉马尼安尤特帕尔S·古普塔P·R·马内里克G·希拉南达尼A·R·辛哈
Owner ADOBE INC
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