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

Force Classification

Force Classification

Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...

You might also read

Related Articles

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

Sort by

Same author

Pyramidal Multiple Instance Detection Network With Mask Guided Self-Correction for Weakly Supervised Object Detection.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2021

Same author

microRNA deregulation in keloids: an opportunity for clinical intervention?

Cell proliferation·2015

Same author

The role of miRNAs in the pheochromocytomas.

Tumour biology : the journal of the International Society for Oncodevelopmental Biology and Medicine·2015

Same author

Abnormalities of cingulate cortex in antipsychotic-naïve chronic schizophrenia.

Brain research·2015

Same author

Pulse Pressure Variation Adjusted by Respiratory Changes in Pleural Pressure, Rather Than by Tidal Volume, Reliably Predicts Fluid Responsiveness in Patients With Acute Respiratory Distress Syndrome.

Critical care medicine·2015

Same author

Identification of a FOXP3(+)CD3(+)CD56(+) population with immunosuppressive function in cancer tissues of human hepatocellular carcinoma.

Scientific reports·2015

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

Search research articles

Related Experiment Video

Updated: Aug 4, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Cyclic Self-Training With Proposal Weight Modulation for Cross-Supervised Object Detection.

Yunqiu Xu, Chunluan Zhou, Xin Yu

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society

|April 4, 2023

Summary

This summary is machine-generated.

This study introduces Cyclic Self-Training (CST) to improve cross-supervised object detection (CSOD) by generating better bounding-box annotations for novel classes. This approach narrows the performance gap between weakly-supervised and fully-supervised object detection methods.

More Related Videos

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

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

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

Published on: February 6, 2020

Related Experiment Videos

Last Updated: Aug 4, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

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

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

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

Published on: February 6, 2020

Area of Science:

Computer Vision
Machine Learning
Artificial Intelligence

Background:

Weakly-supervised object detection (WSOD) uses image-level annotations, but has a performance gap with fully-supervised methods.
Cross-supervised object detection (CSOD) addresses this by using instance-level annotations for base classes and image-level for novel classes.

Purpose of the Study:

To narrow the performance gap in object detection by improving localization accuracy for novel classes in a cross-supervised setting.
To introduce instance-level supervision for novel classes by leveraging existing instance-level annotations from base classes.

Main Methods:

Proposes Cyclic Self-Training (CST) to enhance the online instance classifier refinement (OICR) method.
CST employs forward pseudo labeling to generate initial bounding-box predictions and backward pseudo labeling to refine these predictions for novel classes.
Introduces a Proposal Weight Modulation (PWM) module to mitigate the impact of inaccurate pseudo-labeled bounding boxes during training.

Main Results:

The proposed CST method significantly improves localization accuracy in cross-supervised object detection.
Experiments on PASCAL VOC and MS COCO datasets validate the effectiveness of the CST and PWM modules.
The method successfully alleviates supervision inconsistency between base and novel classes.

Conclusions:

Cyclic Self-Training (CST) effectively bridges the performance gap in weakly-supervised object detection by introducing better supervision for novel classes.
The integration of forward and backward pseudo labeling, along with Proposal Weight Modulation (PWM), offers a robust solution for cross-supervised object detection.