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

Multi-modal data association method and device

A data association and multi-modal technology, applied in the field of data processing, can solve the problems of inability to determine the data association of different modal data, poor universality of data association methods, etc.

Active Publication Date: 2020-12-01
TSINGHUA UNIV +1
View PDF10 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the purpose of the present invention is to provide a multi-modal data association method and device to alleviate the problem of the poor universality of the data association method in the prior art and the inability to determine data association of different modal data. technical problem

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
  • Multi-modal data association method and device
  • Multi-modal data association method and device
  • Multi-modal data association method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] According to an embodiment of the present invention, an embodiment of a multimodal data association method is provided. It should be noted that the steps shown in the flow chart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, Also, although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that shown or described herein.

[0027] figure 1 is a multimodal data association method according to an embodiment of the present invention, such as figure 1 As shown, the method includes the following steps:

[0028] Step S102, acquiring data to be processed, wherein the types of data to be processed include: video data, picture data and text data;

[0029] Step S104, constructing the semantic graph of the data to be processed;

[0030] Step S106, using the graph convolutional network to calculate the representation vector of the s...

Embodiment 2

[0087] The embodiment of the present invention also provides a multimodal data association device, which is used to execute the multimodal data association method provided in the above content of the embodiment of the present invention, the following is provided by the embodiment of the present invention A detailed introduction to the multimodal data association device.

[0088] Such as image 3 as shown, image 3 It is a schematic diagram of the above-mentioned multimodal data association device, which includes: an acquisition unit 10 , a construction unit 20 , a calculation unit 30 and a determination unit 40 .

[0089] The acquiring unit 10 is configured to acquire data to be processed, wherein the types of the data to be processed include: video data, picture data and text data;

[0090] The construction unit 20 is configured to construct the semantic graph of the data to be processed;

[0091] The calculation unit 30 is configured to calculate the representation vector...

Embodiment 3

[0101] A terminal provided by an embodiment of the present invention includes a memory, a processor, and a computer program stored on the memory and operable on the processor. When the processor executes the computer program, the multimodal data association method in the first embodiment above is implemented. .

[0102] see Figure 4 , the embodiment of the present invention also provides a terminal 100, including: a processor 60, a memory 61, a bus 62 and a communication interface 63, the processor 60, the communication interface 63 and the memory 61 are connected through the bus 62; the processor 60 is used for Executable modules, such as computer programs, stored in the memory 61 are executed.

[0103] Wherein, the memory 61 may include a high-speed random access memory (RAM, Random Access Memory), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory. The communication connection between the system network element and at least...

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 provides a multi-modal data association method and device, and relates to the technical field of data processing, and the method comprises the following steps: obtaining to-be-processeddata, and enabling the types of the to-be-processed data to comprise video data, picture data and text data; constructing a semantic graph of the to-be-processed data; calculating a representation vector of the semantic graph by utilizing a graph convolution network; and based on the representation vector, determining a data association result of the to-be-processed data, thereby solving the technical problems that an existing data association method is relatively poor in universality and cannot determine data association of different modal data.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular to a multimodal data association method and device. Background technique [0002] In the display technology, represented by image annotation technology, the existing multi-modal data processing usually adopts the codec framework, which is basically for two specific modalities. When multiple modalities are involved, it often needs to be combined with The data type is a codec structure with a quadratic relationship, which means that there is basically no simple and direct multi-modal data processing method. [0003] In addition, in data association tasks, even if only two modalities are dealt with, the existing methods do not achieve the optimal results. Take the image and text data association based on the image annotation model as an example. The image annotation model is composed of a convolutional neural network and a recurrent neural network. To train a neural ne...

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): G06F16/901G06N3/04G06K9/62
CPCG06F16/9024G06N3/045G06F18/22
Inventor 陶晓明段一平李明哲徐迈邓欣
Owner TSINGHUA UNIV