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: Dec 29, 2025

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

941

Attention Based CNN-ConvLSTM for Pedestrian Attribute Recognition.

Yang Li1,2, Huahu Xu1,3, Minjie Bian3

  • 1School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China.

Sensors (Basel, Switzerland)
|February 8, 2020
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

Measurement Method for Mold Slag Thickness in Continuous Casting Mold Using Millimeter-Wave Radar and Eddy Current Sensors.

Sensors (Basel, Switzerland)·2026
Same author

MultiModal craniocerebral diagnose based on 3D CT and image reports.

Scientific reports·2025
Same author

Impact of the ADMIRE reconstruction algorithm combined with the Sa36 kernel on quantitative measurement of coronary artery calcification in AI: a single-arm prospective study.

Polish journal of radiology·2025
Same author

Assessing heavy metal risks in liquid milk: Dietary exposure and carcinogenicity in China.

Journal of dairy science·2025
Same author

Anomaly detection in virtual machine logs against irrelevant attribute interference.

PloS one·2025
Same author

A Joint De-Rain and De-Mist Network Based on the Atmospheric Scattering Model.

Journal of imaging·2023
Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
See all related articles

This study introduces a novel CNN-CAtt-ConvLSTM model for pedestrian attribute recognition, improving accuracy in video surveillance by considering spatial-temporal correlations. The method enhances performance on benchmark datasets, offering a superior solution for challenging computer vision tasks.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Deep Learning

Background:

  • Pedestrian attribute recognition is crucial for video surveillance but faces challenges due to viewpoint, illumination, resolution, and occlusion.
  • Existing methods often overlook the correlation between pedestrian attributes and spatial information, leading to suboptimal performance.

Purpose of the Study:

  • To propose an attention-based neural network, CNN-CAtt-ConvLSTM, for improved pedestrian attribute recognition.
  • To address the limitations of current methods by incorporating spatiotemporal and sequential information.

Main Methods:

  • A novel attention-based neural network (CNN-CAtt-ConvLSTM) integrating Convolutional Neural Networks (CNN), Channel Attention (CAtt), and Convolutional Long Short-Term Memory (ConvLSTM).
  • Extraction of salient visual features using pre-trained CNN and CAtt.
Keywords:
channel attention (CAtt)conventional long short-term memory (ConvLSTM)convolutional neutral networks (CNN)multi-label classificationpedestrian attribute recognition

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

5.1K

Related Experiment Videos

Last Updated: Dec 29, 2025

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

941
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

5.1K
  • Further extraction of spatial information and correlations using ConvLSTM.
  • Prediction of attributes based on optimized sequences considering attribute image area and importance.

    • Main Results:

    • The proposed CNN-CAtt-ConvLSTM model achieved higher performance compared to state-of-the-art methods on the PETA and RAP datasets.
    • Demonstrated the effectiveness of incorporating spatial-temporal and sequential information in pedestrian attribute recognition.

    Conclusions:

    • The CNN-CAtt-ConvLSTM method offers a superior and valid approach for pedestrian attribute recognition.
    • The model effectively addresses challenges posed by variations in viewpoints, illumination, resolution, and occlusion in video surveillance.