Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Mar 26, 2026

Methods to Test Visual Attention Online

Methods to Test Visual Attention Online

Published on: February 19, 2015

DeepTrack: Learning Discriminative Feature Representations Online for Robust Visual Tracking.

Hanxi Li, Yi Li, Fatih Porikli

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society

|February 4, 2016

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

Interfacial Donor-Acceptor Engineering in MOFs: Synergizing Self-Excitation and External Charge Utilization for High-Efficiency Photocatalytic Hydrogen Evolution.

Angewandte Chemie (International ed. in English)·2026

Same author

Genome-wide identification of WRKY gene family members in <i>Populus trichocarpa</i> and their response to biotic stresses.

PeerJ·2026

Same author

PabIAA33-PabARF16 module regulates PabWOX13 expression to promote adventitious root formation in poplar cuttings.

Plant science : an international journal of experimental plant biology·2026

Same author

Automated 10-m Resolution In-season Crop-type Data Layer Mapping for Contiguous United States.

Scientific data·2026

Same author

Construction and Microenvironment Regulation of Short Charge Transfer Tunnel at MOF/COF Heterointerfaces for Visible-Light-Driven Hydrogen Evolution.

Advanced materials (Deerfield Beach, Fla.)·2026

Same author

'Why I left the county': Exploring EFL teachers' emotional labour trajectories through complex dynamic systems theory.

Acta psychologica·2026

Same journal

Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

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

Same journal

AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

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

Same journal

BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

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

Same journal

GoP-based Quality Enhancement on Video Compression.

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

Same journal

Align then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

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

Same journal

Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

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

See all related articles

This study introduces an efficient deep learning method for online visual tracking. The novel approach uses a single convolutional neural network (CNN) to learn target features, improving robustness and performance in challenging conditions.

Area of Science:

Computer Vision
Machine Learning
Deep Learning

Background:

Deep neural networks (DNNs) excel at feature learning but are often impractical for online visual tracking due to extensive training requirements.
Existing methods struggle with long training times and large datasets, hindering real-time applications.

Purpose of the Study:

To develop an efficient and robust online visual tracking algorithm using a single convolutional neural network (CNN).
To enable effective feature representation learning for target objects in a purely online manner.

Main Methods:

Introduced a novel truncated structural loss function to preserve training samples and mitigate tracking error accumulation.
Enhanced stochastic gradient descent with a robust sample selection mechanism considering temporal relations and label noise.

More Related Videos

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

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

Related Experiment Videos

Last Updated: Mar 26, 2026

Methods to Test Visual Attention Online

Methods to Test Visual Attention Online

Published on: February 19, 2015

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

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

Implemented a lazy yet effective updating scheme for CNN training, enhancing robustness to occlusion and incorrect detections.

Main Results:

The proposed CNN tracker outperformed all state-of-the-art methods on two benchmark datasets comprising over 60 video sequences.
Demonstrated superior performance attributed to online learned feature representations via the deep learning framework.

Conclusions:

The developed deep learning framework offers an efficient and robust solution for online visual tracking.
The novel methods enable effective feature learning and adaptation to appearance changes, overcoming common tracking challenges.