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

PixOOD: Pixel-Level Out-of-Distribution Detection.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Cascaded and Generalizable Neural Radiance Fields for Fast View Synthesis.

IEEE transactions on pattern analysis and machine intelligence·2023
Same author

eWaSR-An Embedded-Compute-Ready Maritime Obstacle Detection Network.

Sensors (Basel, Switzerland)·2023
Same author

Learning with Weak Annotations for Robust Maritime Obstacle Detection.

Sensors (Basel, Switzerland)·2022
Same author

Plant recognition by AI: Deep neural nets, transformers, and kNN in deep embeddings.

Frontiers in plant science·2022
Same author

Visual Object Tracking With Discriminative Filters and Siamese Networks: A Survey and Outlook.

IEEE transactions on pattern analysis and machine intelligence·2022
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

Related Experiment Video

Updated: Oct 9, 2025

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

3.0K

A Discriminative Single-Shot Segmentation Network for Visual Object Tracking.

Alan Lukezic, Jiri Matas, Matej Kristan

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |December 23, 2021
    PubMed
    Summary
    This summary is machine-generated.

    Discriminative Single-Shot Segmentation Tracker (D3S2) enhances object tracking by combining segmentation and tracking. This novel approach improves localization accuracy and outperforms existing methods on multiple benchmarks.

    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

    677
    Deep Learning-Based Segmentation of Cryo-Electron Tomograms
    10:25

    Deep Learning-Based Segmentation of Cryo-Electron Tomograms

    Published on: November 11, 2022

    9.6K

    Related Experiment Videos

    Last Updated: Oct 9, 2025

    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

    3.0K
    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

    677
    Deep Learning-Based Segmentation of Cryo-Electron Tomograms
    10:25

    Deep Learning-Based Segmentation of Cryo-Electron Tomograms

    Published on: November 11, 2022

    9.6K

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Artificial Intelligence

    Background:

    • Template-based discriminative trackers dominate visual object tracking.
    • Current methods are limited to bounding box tracking, reducing localization accuracy.
    • A gap exists between visual object tracking and video object segmentation.

    Purpose of the Study:

    • To bridge the gap between visual object tracking and video object segmentation.
    • To introduce a novel discriminative single-shot segmentation tracker (D3S2).
    • To improve tracking robustness and localization accuracy.

    Main Methods:

    • Developed a single-shot network employing two target models with complementary geometric properties.
    • One model is invariant to transformations (including non-rigid deformations).
    • The other model assumes a rigid object, enabling robust online target segmentation and decoupled scale estimation.

    Main Results:

    • D3S2 achieves superior performance on the VOT2020 short-term tracking benchmark without per-dataset finetuning.
    • It demonstrates competitive results on GOT-10k, TrackingNet, OTB100, and LaSoT benchmarks.
    • D3S2 surpasses SiamMask on video object segmentation benchmarks and matches top algorithms.

    Conclusions:

    • D3S2 effectively narrows the gap between visual object tracking and video object segmentation.
    • The proposed method offers robust online target segmentation and improved localization accuracy.
    • D3S2 represents a significant advancement in visual object tracking and segmentation.