Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 6, 2026

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

8.6K

Multi-scale locality-constrained spatiotemporal coding for local feature based human action recognition.

Bin Wang1, Yu Liu, Wei Wang

  • 1College of Information System and Manage, National University of Defense Technology, 109 Deya Road, Changsha, Hunan 410073, China.

Thescientificworldjournal
|November 7, 2013
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

[Study of electroreflectance spectrum and Franz-Keldysh effect at metal-GaAs interfaces].

Guang pu xue yu guang pu fen xi = Guang pu·2008
Same author

[Study on electro-degradation of new conjugated polymer PFO-BT15 light emitting diodes].

Guang pu xue yu guang pu fen xi = Guang pu·2008
Same author

Comparison of the curative effects of video assisted thoracoscopic anterior correction and small incision, thoracotomic anterior correction for idiopathic thoracic scoliosis.

Chinese medical journal·2008
Same author

Distribution and sources of mercury in soils from former industrialized urban areas of Beijing, China.

Environmental monitoring and assessment·2008
Same author

[Main flavonoids from Sophora flavescenes].

Yao xue xue bao = Acta pharmaceutica Sinica·2008
Same author

External validation and prediction employing the predictive squared correlation coefficient test set activity mean vs training set activity mean.

Journal of chemical information and modeling·2008

This study introduces a Multiscale Locality-Constrained Spatiotemporal Coding (MLSC) method for human action recognition. MLSC improves upon traditional methods by incorporating spatiotemporal information, leading to enhanced video classification accuracy.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Artificial Intelligence

Background:

  • Traditional bag of features (BoF) methods for human action recognition overlook crucial spatiotemporal relationships in local video features.
  • Accurate action recognition in videos is vital for applications ranging from surveillance to human-computer interaction.

Purpose of the Study:

  • To develop an improved feature coding method that explicitly models spatiotemporal relationships for enhanced human action recognition.
  • To address the limitations of existing methods by integrating spatial and temporal information within feature representation.

Main Methods:

  • Proposed Multiscale Locality-Constrained Spatiotemporal Coding (MLSC) method.
  • MLSC projects local features into a sub space-time-volume (sub-STV) and uses locality-constrained linear coding.

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.5K

Related Experiment Videos

Last Updated: May 6, 2026

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

8.6K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.5K
  • Classification employs Locality-Constrained Group Sparse Representation (LGSR) on pooled sub-STV features.

    • Main Results:

    • MLSC effectively models spatiotemporal relationships, outperforming methods that ignore this information.
    • Experimental validation on KTH, Weizmann, and UCF sports datasets demonstrated superior performance.
    • The proposed method achieved better accuracy compared to existing local spatiotemporal feature-based approaches.

    Conclusions:

    • MLSC offers a significant advancement in human action recognition by effectively leveraging spatiotemporal feature information.
    • The method provides a robust framework for video analysis and classification tasks.
    • Future work could explore further optimizations and applications of MLSC in complex video understanding scenarios.