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

Action positioning model training method and device and action positioning method

A training method and action technology, applied in character and pattern recognition, instruments, calculations, etc., can solve problems such as wrong positioning, incomplete action positioning, unstable model training, etc., achieve robust action positioning, and realize the effect of action positioning

Active Publication Date: 2022-05-27
UNIV OF SCI & TECH OF CHINA
View PDF12 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this training process cannot guarantee the continuity of pseudo-labels in different clustering processes, making the model training unstable, resulting in incomplete or wrong positioning of actions

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
  • Action positioning model training method and device and action positioning method
  • Action positioning model training method and device and action positioning method
  • Action positioning model training method and device and action positioning method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] Hereinafter, embodiments of the present invention will be described with reference to the drawings. It should be understood, however, that these descriptions are exemplary only and are not intended to limit the scope of the present invention. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the invention. It may be evident, however, that one or more embodiments may be practiced without these specific details. Also, in the following description, descriptions of well-known structures and techniques are omitted to avoid unnecessarily obscuring the concept of the present invention.

[0056] The terminology used herein is for the purpose of describing particular embodiments only, and is not intended to be limiting of the invention. The terms "comprising", "comprising", etc. used herein indicate the presence of stated features, steps, operations and / ...

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 method for training an action positioning model, which comprises the following steps of: 1, performing clustering analysis on sample feature data of sample videos in a sample video set to obtain a first pseudo label set; 2, training the initial action positioning model by using the sample video set and the first pseudo label set to obtain a first action positioning model; operation 3, updating the first pseudo-label set according to the first action positioning model and the current foreground features to obtain a second pseudo-label set; operation 4, when it is determined that the second pseudo-label set does not meet the preset condition, training the first action positioning model by using the sample video set and the second pseudo-label set to obtain a second action positioning model; and 5, circularly executing the operation 3 and the operation 4 to circularly update the pseudo-tag set, and ending training until the obtained ith pseudo-tag set meets a preset condition to obtain a final action positioning model. The invention further provides a training device of the action positioning model and an action positioning method.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to intelligent behavior analysis, and more specifically to a training method and device for an action positioning model, and an action positioning method. Background technique [0002] Time-domain action localization can locate the start time and end time of an action from a large number of given videos, and has a wide range of applications in the fields of intelligent monitoring, video description, and video summary. [0003] Traditional action localization methods are usually based on predetermined categories or fully supervised learning, using predefined action types to classify and boundary label video data, and then use the labeled data to train the model. This process requires pre-defining action types and labeling a large amount of data, which limits the applicability of action localization. [0004] In order to alleviate the reliance on data annotati...

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): G06V40/20G06V10/774G06V10/762G06V10/764G06K9/62
CPCG06F18/2321G06F18/24G06F18/214
Inventor 张天柱张哲张勇东杨文飞吴枫
Owner UNIV OF SCI & TECH OF CHINA
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