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: Mar 19, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.2K

Human Action Recognition Using Improved Salient Dense Trajectories.

Qingwu Li1, Haisu Cheng1, Yan Zhou1

  • 1Key Laboratory of Sensor Networks and Environmental Sensing, Hohai University, Changzhou 213022, China.

Computational Intelligence and Neuroscience
|June 14, 2016
PubMed
Summary
This summary is machine-generated.

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

Asymmetric Feature Consistency Reinforcement Network for Visual-Depth-Thermal Salient Object Detection and a New Benchmark.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

Cross-modal collaborative optimization for semantic segmentation of RGB-T power equipment images.

Applied optics·2026
Same author

Kinesins control male germ unit assembly for sperm delivery in Arabidopsis.

Nature plants·2025
Same author

CAMSAP3 forms dimers via its α-helix domain that directly stabilize non-centrosomal microtubule minus ends.

Journal of cell science·2024
Same author

Object phase-valid region segmentation method for FPP-based three-dimensional measurement.

Applied optics·2024
Same author

A dual-modal dynamic contour-based method for cervical vascular ultrasound image instance segmentation.

Mathematical biosciences and engineering : MBE·2024
Same journal

RETRACTION: Multidimensional Heterogeneous Network Link Adaptation Based on Mobile Environment.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Framework to Segment and Evaluate Multiple Sclerosis Lesion in MRI Slices Using VGG-UNet.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Facial Emotion Recognition Using a Novel Fusion of Convolutional Neural Network and Local Binary Pattern in Crime Investigation.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Automatic Intelligent System Using Medical of Things for Multiple Sclerosis Detection.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Intangible Cultural Heritage Reproduction and Revitalization: Value Feedback, Practice, and Exploration Based on the IPA Model.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: CNN Based Multiclass Brain Tumor Detection Using Medical Imaging.

Computational intelligence and neuroscience·2025
See all related articles

This study introduces improved salient dense trajectories for enhanced human action recognition in videos. The novel approach refines trajectory extraction and optimizes video representation for competitive performance.

Area of Science:

  • Computer Vision
  • Machine Learning

Background:

  • Human action recognition in videos is a critical area of research.
  • Dense Trajectory (DT) features are established for effective video representation.

Purpose of the Study:

  • To develop a more effective video representation approach for human action recognition.
  • To improve upon existing Dense Trajectory methods by incorporating motion saliency.

Main Methods:

  • Detecting motion salient regions and extracting dense trajectories across spatial scales.
  • Refining trajectories using motion saliency analysis and computing spatiotemporal descriptors (HOG, HOF, MBH).
  • Optimizing the bag-of-words framework with motion saliency and sparse coefficient reconstruction.

Main Results:

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

5.6K
Trajectory Data Analyses for Pedestrian Space-time Activity Study
16:14

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

14.3K

Related Experiment Videos

Last Updated: Mar 19, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.2K
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

5.6K
Trajectory Data Analyses for Pedestrian Space-time Activity Study
16:14

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

14.3K
  • The proposed method demonstrates competitive performance on standard action recognition datasets (KTH, UCF sports, HMDB51, UCF50).
  • Improved salient dense trajectories lead to enhanced video representation.

Conclusions:

  • The novel approach offers a more effective method for human action recognition.
  • The integration of motion saliency significantly enhances video representation quality.