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 Video

Updated: Dec 28, 2025

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine
07:05

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Published on: October 27, 2016

9.5K

Semi-Supervised Multi-View Deep Discriminant Representation Learning.

Xiaodong Jia, Xiao-Yuan Jing, Xiaoke Zhu

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |February 20, 2020
    PubMed
    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

    LoRASculpt: Harmonious Low-Rank Adaptation for Multimodal Large Language Models.

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

    Towards clinical-level interpretation of dental panoramic radiography using an instance-guided vision-language model.

    Nature biomedical engineering·2026
    Same author

    Thermal Conductivity and Dielectric Properties of EP Composites Enhanced by BNNS-AgNP Synergistic Doping.

    Nanomaterials (Basel, Switzerland)·2026
    Same author

    Systemic immune-inflammation index predicts post-thrombectomy outcomes and reveals a mediating role in the association between neurocardiac stress and prognosis: a multicenter study.

    Frontiers in neurology·2026
    Same author

    Differentiable Clustering Graph Convolutional Network for Hyperspectral Unmixing: Methodology and Benchmark.

    IEEE transactions on neural networks and learning systems·2026
    Same author

    Holistic Invariant Retracing for Distortion-Resilient Multi-Modal Learning in Spatial Transcriptomics.

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

    HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

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

    Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

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

    Adaptive Hardness-Driven Dictionary Distillation for Incomplete Streaming View Clustering.

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

    Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation.

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

    Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads.

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

    Achieving Text-based Person Retrieval with Any Granularity.

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

    This study introduces a semi-supervised deep learning method for multi-view data representation. It effectively learns shared and specific features, reducing redundancy for better performance in classification tasks.

    Area of Science:

    • Machine Learning
    • Computer Vision
    • Data Science

    Background:

    • Learning expressive representations from multi-view data is crucial for many applications.
    • Existing methods struggle to leverage both consensus and complementary properties of multi-view data.

    Purpose of the Study:

    • To propose a novel semi-supervised multi-view deep discriminant representation learning (SMDDRL) approach.
    • To simultaneously learn inter-view shared and intra-view specific representations.
    • To address redundancy in learned representations.

    Main Methods:

    • Developed a shared and specific representation learning network.
    • Incorporated orthogonality and adversarial similarity constraints to reduce redundancy.
    • Designed a semi-supervised framework combining deep metric learning and density clustering.

    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

    941

    Related Experiment Videos

    Last Updated: Dec 28, 2025

    Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine
    07:05

    Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

    Published on: October 27, 2016

    9.5K
    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

    941

    Main Results:

    • The SMDDRL approach effectively utilizes consensus and complementary properties of multi-view data.
    • Redundancy in learned representations is significantly reduced.
    • Demonstrated effectiveness on webpage, image, and document classification tasks.

    Conclusions:

    • The proposed SMDDRL method offers a powerful approach for semi-supervised multi-view representation learning.
    • It outperforms existing methods by learning comprehensive shared and specific representations.
    • The approach is validated across diverse classification benchmarks.