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

Biological Safety Analysis of Nanoparticles: Exploring Toxicity, Mechanisms, and Safety Factors for Pharmaceuticals.

International journal of nanomedicine·2026
Same author

Recent Progress of Single-Ion Conducting Polymer Electrolytes for Rechargeable Mono- and Multivalent Cation-Based Metal Batteries.

Angewandte Chemie (International ed. in English)·2026
Same author

Analysis of plasma exosomal differential proteins and bioinformatics in intrahepatic cholestasis of pregnancy.

Frontiers in global women's health·2026
Same author

Knockdown of Ddx3x in mPFC induces autistic-like phenotype in mice via altered synaptic plasticity.

Translational psychiatry·2026
Same author

Revisiting steel slag as a modified catalyst in advanced oxidation processes for the degradation of emerging pollutants in water: A review.

Environmental research·2026
Same author

Novel chitosan-based phase-selective organogelator for efficient separation of oil/water mixtures.

International journal of biological macromolecules·2026

Related Experiment Video

Updated: Jan 1, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

707

Local Semantic Siamese Networks for Fast Tracking.

Zhiyuan Liang, Jianbing Shen

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |December 24, 2019
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces the Local Semantic Siamese (LSSiam) network for robust object tracking. LSSiam extracts local semantic features, significantly improving performance and speed compared to global feature methods.

    More Related Videos

    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

    968
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    3.3K

    Related Experiment Videos

    Last Updated: Jan 1, 2026

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    707
    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

    968
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    3.3K

    Area of Science:

    • Computer Vision
    • Machine Learning

    Background:

    • Robust feature representation is crucial for Siamese trackers.
    • Global appearance features in existing trackers lead to drift issues due to occlusion and deformation.

    Purpose of the Study:

    • To develop a novel Siamese tracker, Local Semantic Siamese (LSSiam), for enhanced robustness.
    • To address drift problems in object tracking by utilizing local semantic features.

    Main Methods:

    • Proposed the Local Semantic Siamese (LSSiam) network incorporating a classification branch for semantic feature learning during offline training.
    • Introduced a focal logistic loss to effectively mine hard negative samples.
    • Implemented an efficient template updating strategy for online tracking, removing the classification branch to reduce computational load.

    Main Results:

    • The LSSiam tracker achieves high-speed performance at 100 Frames-per-Second (FPS).
    • Demonstrated state-of-the-art performance on popular object tracking benchmarks.
    • Achieved robust tracking even with partial occlusion and non-rigid object deformation.

    Conclusions:

    • LSSiam offers a superior approach to feature representation for Siamese trackers.
    • The proposed method significantly enhances tracking robustness and speed, outperforming existing methods.