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 Videos

Visual tracker using sequential bayesian learning: discriminative, generative, and hybrid.

Yun Lei1, Xiaoqing Ding, Shengjin Wang

  • 1Department of Electronic Engineering, Tsinghua University, Beijing 100084, China.

IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics : a Publication of the IEEE Systems, Man, and Cybernetics Society
|November 22, 2008
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Associative Learning01:27

Associative Learning

Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
Observational Learning01:12

Observational Learning

Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning because...

You might also read

Related Articles

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

Sort by
Same author

Multiplexed Sepsis Immunosorbent Assay Based on Flower-like CoFe<sub>2</sub>O<sub>4</sub>/MoS<sub>2</sub> with Dual Substrate Affinity.

Analytical chemistry·2026
Same author

Selinexor in combination with azacitidine or ruxolitinib in myelodysplastic/myeloproliferative neoplasm overlap syndromes: A multicenter prospective study.

Cancer·2026
Same author

Pharmacological inhibition of TRPM4 channel stabilizes atherosclerotic plaque via inhibiting AMPK-Beclin1-mediated autophagy.

European journal of pharmacology·2026
Same author

Decoding the crosstalk between ubiquitination and other post-translational modifications in cancer immunity: from mechanisms to clinical prospects.

NPJ precision oncology·2026
Same author

Nanozyme-Enhanced Paper-Based Bipolar Electrode Biosensor for Dual-Mode Detection for M918T in Serum with Single-Base Specificity.

Analytical chemistry·2026
Same author

Lactylation-regulated ferroptosis: mechanisms, disease associations, and therapeutic strategies.

Archives of pharmacal research·2026
Same journal

Strategic Ability Updating in Concurrent Games by Coalitional Commitment.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2015
Same journal

Meta-Analysis of the First Facial Expression Recognition Challenge.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

Adjustable model-based fusion method for multispectral and panchromatic images.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

Face Feature Weighted Fusion Based on Fuzzy Membership Degree for Video Face Recognition.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

A New Adaptive Fast Cellular Automaton Neighborhood Detection and Rule Identification Algorithm.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
Same journal

Human-arm-and-hand-dynamic model with variability analyses for a stylus-based haptic interface.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2012
See all related articles

This study introduces an adaptive visual object tracking method combining discriminative and generative models. This approach effectively handles challenges like illumination changes and occlusion, outperforming existing methods.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Pattern Recognition

Background:

  • Visual object tracking is crucial for many applications.
  • Existing methods struggle with significant variations in illumination, viewpoint, pose, scale, and occlusion.
  • Integrating discriminative and generative models offers a promising direction for robust tracking.

Purpose of the Study:

  • To develop a novel and robust visual object tracking solution.
  • To investigate effective strategies for combining discriminative and generative tracking models.
  • To enhance tracking performance under challenging real-world conditions.

Main Methods:

  • Sequential Bayesian learning framework.
  • Development of a discriminative tracker using a fast relevance vector machine (RVM).

Related Experiment Videos

  • Development of a generative tracker using a novel sequential Gaussian mixture model (GMM).
  • Introduction of a three-level hierarchical model combination: learner, classifier, and decision combination.

    • Main Results:

    • The proposed adaptive combination of discriminative and generative models achieved superior overall performance.
    • Quantitative comparisons on diverse video sequences validated the method's effectiveness.
    • Qualitative assessments demonstrated robustness against illumination, viewpoint, pose, scale, and occlusion variations.

    Conclusions:

    • The hierarchical combination of discriminative and generative models offers a significant advancement in visual object tracking.
    • The proposed method provides an effective and efficient solution for real-world tracking challenges.
    • This adaptive approach enhances tracking reliability and accuracy across various scenarios.