Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Detection of Black Holes

Detection of Black Holes

Although black holes were theoretically postulated in the 1920s, they remained outside the domain of observational astronomy until the 1970s.
Their closest cousins are neutron stars, which are composed almost entirely of neutrons packed against each other, making them extremely dense. A neutron star has the same mass as the Sun but its diameter is only a few kilometers. Therefore, the escape velocity from their surface is close to the speed of light.
Not until the 1960s, when the first neutron...

You might also read

Related Articles

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

Sort by

Same author

Interactive effects of biochar, nitrogen fertilizer, and irrigation on SOC and crop yield in a rice-wheat rotation system.

Frontiers in plant science·2026

Same author

X-ray irradiation simultaneously mitigates chlorfenapyr and azoxystrobin residues and preserves postharvest quality of cowpea.

Food chemistry: X·2026

Same author

A CRISPR/dCas9 mediated electrochemical impedimetric biosensor for sensitive mtDNA detection.

Analytica chimica acta·2026

Same author

Effects and interactive effects of high-altitude environment on metabolism in normal and diabetic populations: a comparative metabolomics study.

Frontiers in endocrinology·2026

Same author

Edoxaban for stroke prevention in Chinese patients with atrial fibrillation: 1-year follow-up of the ETNA-AF-China study.

Frontiers in pharmacology·2026

Same author

Network pharmacology, molecular docking, and dynamics reveal the mechanisms of Hejie Shengfa Decoction against alopecia areata.

Medicine·2026

Search research articles

Related Experiment Video

Updated: Aug 6, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Object Detection Based on Swin Deformable Transformer-BiPAFPN-YOLOX.

Peicheng Shi¹, Xinhe Chen¹, Heng Qi¹

¹School of Mechanical Engineering, Anhui Polytechnic University, Wuhu 241000, China.

Computational Intelligence and Neuroscience

|March 20, 2023

Summary

This study introduces a novel object detection network, Swin Deformable Transformer-BiPAFPN-YOLOX, enhancing feature extraction and convergence speed. The new model significantly improves training efficiency and detection accuracy, especially for small objects.

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

Related Experiment Videos

Last Updated: Aug 6, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

Area of Science:

Computer Vision
Deep Learning
Object Detection

Background:

Current object detection networks often use convolutional neural networks, lacking global image understanding and potentially losing critical feature information.
Transformers offer global modeling capabilities but face challenges like limited long-range relation modeling and slow convergence in backbones like Swin Transformer.

Purpose of the Study:

To develop an improved object detection network addressing the limitations of existing Transformer-based models.
To enhance feature extraction, accelerate training convergence, and boost overall detection performance.

Main Methods:

Proposed an important region-based Reconstructed Deformable Self-Attention mechanism for efficient global modeling.
Developed the Swin Deformable Transformer backbone integrating the novel attention mechanism.
Introduced a new object detection network: Swin Deformable Transformer-BiPAFPN-YOLOX.

Main Results:

Achieved a 55.4% reduction in training period and a 35% increase in inference speed.
Improved overall average precision by 2.4% and average precision for small objects by 3.7% on the COCO dataset.

Conclusions:

The proposed Swin Deformable Transformer backbone significantly enhances feature extraction and convergence speed.
The novel Swin Deformable Transformer-BiPAFPN-YOLOX network demonstrates superior performance in object detection tasks, offering substantial improvements in efficiency and accuracy.