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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Computational Method Using Attribute-Aware Message Passing and Graph Convolutional Network for Potential miRNA-Disease Association Prediction.

International journal of molecular sciences·2026
Same author

Enhancing subharmonic response by controlling initial state of monodisperse microbubbles via a multi-gas core.

Ultrasonics sonochemistry·2026
Same author

Dynamic evolution of higher alcohols from CO<sub>2</sub> on Fe<sub>3</sub>O<sub>4</sub>-Fe<sub>5</sub>C<sub>2</sub>-Cu catalytic interfaces with amorphous Ti layout.

Nature communications·2026
Same author

Heat-triggered phospholipid flipping stabilizes plasma membrane fluidity.

Nature·2026
Same author

Unveiling the corrosion inhibition mechanism of titanium nitride composite carbon dots in saline-alkali environments: An experimental and theoretical study.

Journal of colloid and interface science·2026
Same author

Imidazole-Modified Graphene Quantum Dots Enhance RNAi Efficiency in Spodoptera litura (Lepidoptera: Noctuidae): A Study Using Cuticular Protein Gene Silencing.

Archives of insect biochemistry and physiology·2026

Related Experiment Video

Updated: Nov 15, 2025

Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut
08:32

Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut

Published on: June 15, 2020

12.9K

Robust Template Adjustment Siamese Network for Object Visual Tracking.

Chuanming Tang1,2,3, Peng Qin2,3, Jianlin Zhang2

  • 1Key Laboratory of Optical Engineering, Chinese Academy of Sciences, Chengdu 610200, China.

Sensors (Basel, Switzerland)
|March 6, 2021
PubMed
Summary

This study introduces the Template Adjustment Siamese Network (TA-Siam) to improve visual tracking by adapting templates to target appearance changes, effectively preventing model drift and target loss in long-term sequences.

Keywords:
anchor-free regressionclassification labelssiamese networktemplate adjustmentvisual tracking

More Related Videos

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

7.9K
Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

7.1K

Related Experiment Videos

Last Updated: Nov 15, 2025

Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut
08:32

Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut

Published on: June 15, 2020

12.9K
A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

7.9K
Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

Published on: April 8, 2019

7.1K

Area of Science:

  • Computer Vision
  • Machine Learning
  • Artificial Intelligence

Background:

  • Existing visual trackers often fail due to model degeneration, leading to drift and target loss.
  • Appearance templates extracted from initial frames struggle with long-term target variations.

Purpose of the Study:

  • To propose a novel visual tracking framework, the Template Adjustment Siamese Network (TA-Siam).
  • To address model drift and target loss challenges in Siamese networks.
  • To enhance tracking accuracy and robustness for long-term sequences.

Main Methods:

  • Introduced TA-Siam, a framework with template adjustment and classification-regression subnetworks.
  • The template adjustment module adaptively updates templates using subsequent frame features.
  • Utilized rhombus labels to reduce classification errors and an effective regression loss for training.

Main Results:

  • TA-Siam demonstrated state-of-the-art performance on challenging benchmarks (VOT2016, VOT2018, OTB50, OTB100, GOT-10K, LaSOT).
  • Achieved a high tracking speed of 45 FPS.
  • Effectively mitigated model drift and improved target localization accuracy.

Conclusions:

  • The proposed TA-Siam framework significantly enhances visual tracking robustness and accuracy.
  • Adaptive template adjustment is crucial for handling appearance variations in long-term tracking.
  • TA-Siam offers a promising solution for real-time, high-performance visual object tracking.