Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Video hash retrieval method based on attention mechanism

A technology of attention and video, applied in the field of video and multimedia signal processing, to achieve the effect of low computational complexity, high retrieval accuracy, and reduced quantity

Active Publication Date: 2020-05-05
SHANDONG JIANZHU UNIV
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the past, we mainly retrieved pictures and videos through keywords, but this often retrieved unwanted results

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 hash retrieval method based on attention mechanism
  • Video hash retrieval method based on attention mechanism
  • Video hash retrieval method based on attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention will be described in detail below in conjunction with the accompanying drawings.

[0041] The method of the present invention presses figure 1 The flow shown includes the following specific steps:

[0042] (1) Video preprocessing

[0043] ④ Uniform sampling of video frames, each video uniformly extracts a specific number of video frames;

[0044] ⑤ Adjust each frame to a frame of the same size, for example, adjust each frame to a size of 224*224;

[0045] ⑥Construct video pairs, including similar sample pairs and different sample pairs, and the ratio of similar video pairs to different video pairs is 1:1. When constructing a video pair, randomly select a video, then randomly select a video of the same type from the remaining videos, and randomly select a video of a different type, so that a positive sample video pair and a negative sample video pair can be constructed.

[0046] (2) Video frame feature extraction

[0047] Such as figure 1 , use ...

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 video hash retrieval method of an attention mechanism. The method comprises the following steps: (1) video preprocessing: sampling video frames, and constructing video pairs;(2) video frame feature extraction: performing feature extraction on each frame by using a convolutional neural network; (3) video feature learning: learning the video by using a twin network, a long-term and short-term memory (LSTM) neural network and an attention mechanism; (4) dimension reduction and training: performing dimension reduction on the video features by using a full connection layerto obtain a hash code with a desired length, and learning network parameters by using a gradient descent algorithm; and (5) retrieval: obtaining the hash code of each video by using one path of network of the twin network, calculating the Hamming distance with other videos, and performing sorting to obtain the nearest video. Compared with the prior art, the method has the advantages that the spatial information and the time information of the video are learned at the same time, the calculation cost is greatly reduced through sampling and other technologies, and the accuracy of video retrievalis also improved.

Description

technical field [0001] The invention relates to a video hash retrieval method, which belongs to the technical field of video and multimedia signal processing. Background technique [0002] With the development of network and mobile social media, massive multimedia information is constantly generated, especially pictures and videos. Flickr, a famous photo-sharing website, uploads 3,000 pictures every minute; YouTube, a video-sharing website, uploads up to 100 hours of videos every minute. Therefore, how to retrieve massive multimedia information is a hot topic. In the past, we mainly retrieved pictures and videos through keywords, but this often retrieved unwanted results. For this reason, content-based retrieval was proposed. The hash method has become a hot research direction in recent years because of its advantages, namely fast retrieval and space saving. The hash method maps pictures or videos into compact and discrete binary codes (usually 0 and 1 or -1 and 1), that...

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): G06F16/783G06F16/71G06F16/738G06N3/04
CPCG06F16/783G06F16/71G06F16/738G06N3/044G06N3/045Y02D10/00
Inventor 聂秀山尹义龙王迎新
Owner SHANDONG JIANZHU UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com