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

ZNF184 negatively regulates HR repair and predicts poor prognosis in acute lymphoblastic leukemia.

Nucleic acids research·2026
Same author

BiSAUM: Bi-Directional Sparse Attention Transformer for Cancer Cell Prediction in Multi-Domain Sustainable Healthcare Systems.

IEEE journal of biomedical and health informatics·2025
Same author

Human coronavirus 3CL protease manipulates host protein STIM1 to facilitate immune evasion.

Proceedings of the National Academy of Sciences of the United States of America·2025
Same author

Proteomic discovery of DEK and NUMA1 as new players in UV-induced DNA damage repair mechanisms.

Cell death discovery·2025
Same author

Engineering TME-gated inducible CAR-T cell therapy for solid tumors.

Molecular therapy : the journal of the American Society of Gene Therapy·2025
Same author

Synergistic enhancement of PARP inhibition via small molecule UNI66-mediated suppression of BRD4-dependent transcription of <i>RAD51</i> and <i>CtIP</i>.

NAR cancer·2025

Related Experiment Video

Updated: Jun 20, 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

515

Attention-based scale sequence network for small object detection.

Young-Woon Lee1, Byung-Gyu Kim2

  • 1Department of Computer Engineering, Sunmoon University, Asan, Republic of Korea.

Heliyon
|July 18, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces an attention-based scale sequence network (ASSN) to improve small object recognition in computer vision. ASSN enhances feature pyramid networks, boosting performance in critical applications like aerial search.

Keywords:
Attention mechanismDeep learningFeature pyramid networkScale sequenceSmall object detection

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

384
A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.4K

Related Experiment Videos

Last Updated: Jun 20, 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

515
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

384
A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.4K

Area of Science:

  • Computer Vision
  • Deep Learning
  • Artificial Intelligence

Background:

  • Object recognition is crucial in computer vision, with deep learning advancements driving progress.
  • Recognizing small objects remains a significant challenge, impacting applications like aerial search and rescue.
  • Feature Pyramid Networks (FPNs) are fundamental to object recognition, with You Only Look Once (YOLO) being a prominent FPN-based model.

Purpose of the Study:

  • To enhance the performance of FPN-based object detectors, particularly for small objects.
  • To introduce a novel, lightweight attention module, the Attention-based Scale Sequence Network (ASSN).
  • To improve the scale sequence feature pyramid network (ssFPN) for better small object detection.

Main Methods:

  • Proposed the Attention-based Scale Sequence Network (ASSN), a lightweight attention module.
  • Integrated ASSN into FPN-based detectors, specifically targeting improvements in the scale sequence feature pyramid network (ssFPN).
  • Evaluated ASSN's performance against baseline models like YOLOv7 and YOLOv8.

Main Results:

  • ASSN demonstrated performance improvements over baseline models, with average precision (AP) increasing by up to 0.6%.
  • The detection of small objects showed significant gains, with AP for small objects improving by up to 1.9%.
  • ASSN outperformed ssFPN, offering enhanced performance with improved computational efficiency and processing speed.

Conclusions:

  • ASSN effectively enhances small object detection capabilities in FPN-based models.
  • The proposed module is lightweight, versatile, and optimizes computational complexity and processing speed.
  • ASSN represents a valuable contribution to object recognition, particularly for challenging small object scenarios, and is available as open-source.