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: Apr 4, 2026

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

1.2K

Regionlets for Generic Object Detection.

Xiaoyu Wang, Ming Yang, Shenghuo Zhu

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |September 10, 2015
    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

    [Effect of safflor yellow B on vascular endothelial cells injury induced by angiotensin-II].

    Yao xue xue bao = Acta pharmaceutica Sinica·2012
    Same author

    Core-shell hybrid liposomal vesicles loaded with panax notoginsenoside: preparation, characterization and protective effects on global cerebral ischemia/reperfusion injury and acute myocardial ischemia in rats.

    International journal of nanomedicine·2012
    Same author

    Conjugation of cyclodextrin with fullerene as a new class of HCV entry inhibitors.

    Bioorganic & medicinal chemistry·2012
    Same author

    Expression differences of circulating microRNAs in metastatic castration resistant prostate cancer and low-risk, localized prostate cancer.

    The Prostate·2012
    Same author

    [Intestinal absorption effect of Angelica dahurica extract on puerarin of puerariae Lobatae Radix].

    Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica·2012
    Same author

    The emerging role of fumarate as an oncometabolite.

    Frontiers in oncology·2012
    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

    This study introduces regionlets, a novel approach for object detection that handles variations in viewpoints and deformations. This method achieves competitive performance on benchmark datasets and integrates with deep convolutional neural networks.

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Pattern Recognition

    Background:

    • Object detection faces challenges with variations in viewpoints and deformations.
    • Existing methods require descriptive and flexible object representations for efficient evaluation.

    Purpose of the Study:

    • To propose a novel regionlet-based approach for object detection that addresses variations and deformations.
    • To develop a cascaded boosting classifier integrating regionlet features for improved detection accuracy.

    Main Methods:

    • Modeling object classes with cascaded boosting classifiers using regionlets (groups of subregions).
    • Organizing regionlets in groups with stable relative positions to capture spatial layouts.
    • Aggregating regionlet features for flexibility against deformations and selecting discriminative regionlets via boosting.

    More Related Videos

    Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
    05:57

    Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

    Published on: April 8, 2019

    7.3K

    Related Experiment Videos

    Last Updated: Apr 4, 2026

    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

    1.2K
    Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus
    05:57

    Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster Nephrops norvegicus

    Published on: April 8, 2019

    7.3K

    Main Results:

    • Achieved competitive performance on PASCAL VOC 2007 (41.7% mAP) and VOC 2010 (39.7% mAP) for 20 object categories.
    • Developed support pixel integral images to augment regionlet features with deep convolutional neural network responses.
    • Regionlet-based method secured second place in the ILS VRC 2013 challenge.

    Conclusions:

    • The regionlet approach offers a robust and flexible solution for generic object detection.
    • This method demonstrates strong performance across popular benchmarks, even without contextual information.
    • Integration with deep learning enhances the capabilities of regionlet-based object detection.