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

Masking and Demasking Agents01:19

Masking and Demasking Agents

2.5K
EDTA titrations may necessitate masking and demasking agents to temporarily protect a particular metal ion in a mixture from the EDTA reaction. These agents facilitate the sequential analysis of the metal ions by forming stable complexes with some—but not all—metal ions during certain steps.
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on...
2.5K
Structural Classification of Joints01:20

Structural Classification of Joints

3.5K
Joints, also known as articulations, are classified based on their structural characteristics, i.e., based on whether the articulating surfaces of the adjacent bones are directly connected by fibrous connective tissue or cartilage, or whether the articulating surfaces contact each other within a fluid-filled joint cavity. These differences serve to divide the joints of the body into three structural classifications.
A fibrous joint is where the adjacent bones are united by fibrous connective...
3.5K
Sequence Networks of Rotating Machines01:24

Sequence Networks of Rotating Machines

105
A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
105

You might also read

Related Articles

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

Sort by
Same author

Generalized Distribution Aggregation Protocol for Federated Statistical Heterogeneity.

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

Dual-balancing for multi-task learning.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

Sentence-Level Relation Semantics Learning via Contrastive Sentences.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

DXA-Net: Dual-Task Cross-Lingual Alignment Network for Zero-Shot Cross-Lingual Spoken Language Understanding.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

Generalized Probabilistic Graphical Modeling for Multi-View Bipartite Graph Clustering.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

Decouple Before Align: Visual Disentanglement Enhances Prompt Tuning.

IEEE transactions on pattern analysis and machine intelligence·2025
Same journal

Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

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

AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

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

BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

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

GoP-based Quality Enhancement on Video Compression.

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

Align then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

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

Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
See all related articles

Related Experiment Video

Updated: Jul 13, 2025

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

565

Structure-Informed Shadow Removal Networks.

Yuhao Liu, Qing Guo, Lan Fu

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |October 17, 2023
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a new deep learning method for shadow removal, StructNet, which tackles persistent shadow remnants by focusing on image structure. This structure-informed approach significantly improves shadow removal performance.

    More Related Videos

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    437
    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    9.2K

    Related Experiment Videos

    Last Updated: Jul 13, 2025

    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

    565
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    437
    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    9.2K

    Area of Science:

    • Computer Vision
    • Deep Learning
    • Image Processing

    Background:

    • Current deep learning shadow removal techniques often leave residual shadows, particularly in low-intensity homogeneous regions.
    • These remnants are difficult to address with traditional image-to-image mapping due to their subtle nature.
    • Shadows primarily impact image perception at the structural level, affecting perceived object shapes and color continuity.

    Purpose of the Study:

    • To develop a novel deep learning framework for shadow removal that addresses the issue of shadow remnants.
    • To leverage image-structure information to guide the shadow removal process effectively.
    • To improve the quality and completeness of shadow removal in digital images.

    Main Methods:

    • Proposed a structure-informed shadow removal network (StructNet) that operates at the image-structure level.
    • Introduced a mask-guided shadow-free extraction (MSFE) module to extract structural features.
    • Implemented a multi-scale feature & residual aggregation (MFRA) module to utilize shadow-free structure priors for feature regularization.
    • Extended the framework to MStructNet for enhanced performance using multi-level structural information.

    Main Results:

    • StructNet successfully reconstructs shadow-free structural information and uses it to guide image-level shadow removal.
    • The proposed MSFE and MFRA modules effectively extract and utilize structural features, mitigating shadow remnants.
    • Experiments on three benchmarks show that StructNet outperforms existing shadow removal methods.
    • The extended MStructNet further boosts performance with minimal computational increase.

    Conclusions:

    • Shadow removal can be significantly improved by addressing image degradation at the structural level.
    • StructNet provides an effective solution to the persistent shadow remnant problem in deep learning-based shadow removal.
    • The proposed method is versatile and can be integrated with existing techniques to enhance their performance.