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

Multi-input and Multi-variable systems

Multi-input and Multi-variable systems

Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...

You might also read

Related Articles

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

Sort by

Same author

High-Dimensional Feature Selection Using Improved Hybrid Breeding Optimization Algorithm with Feature Grouping.

Biomimetics (Basel, Switzerland)·2026

Same author

Vitamin D receptor regulate placental ABCB1 expression transcriptionally by recruiting coactivator SRC-1.

Pharmacogenetics and genomics·2026

Same author

Inhibition of the Primary Bile Acid Synthesis Pathways in SD Rats at Different Altitudes.

Animals : an open access journal from MDPI·2026

Same author

Association of AGAHR with metabolic dysfunction-associated steatotic liver disease (MASLD).

Hormones (Athens, Greece)·2026

Same author

Diagnostic Accuracy of Large Language Models for Rare Diseases: A Systematic Review and Meta-Analysis.

medRxiv : the preprint server for health sciences·2026

Same author

Wearable Flexible Acoustic Alarm Device Based on MXene/Laser-Induced Graphene@Polyimide Thermoacoustic Film.

ACS sensors·2026

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

Search research articles

Related Experiment Video

Updated: Jun 7, 2026

Computer-Generated Animal Model Stimuli

Computer-Generated Animal Model Stimuli

Published on: July 29, 2007

MIGC++: Advanced Multi-Instance Generation Controller for Image Synthesis.

Dewei Zhou, You Li, Fan Ma

IEEE Transactions on Pattern Analysis and Machine Intelligence

|March 3, 2025

Summary

This summary is machine-generated.

We introduce Multi-Instance Generation (MIG), a new task for creating multiple image instances with specific attributes and positions. Our methods, MIGC and MIGC++, overcome challenges like attribute leakage and ensure consistent iterative generation.

More Related Videos

Localizing Protein in 3D Neural Stem Cell Culture: a Hybrid Visualization Methodology

Localizing Protein in 3D Neural Stem Cell Culture: a Hybrid Visualization Methodology

Published on: December 19, 2010

Creating Virtual-hand and Virtual-face Illusions to Investigate Self-representation

Creating Virtual-hand and Virtual-face Illusions to Investigate Self-representation

Published on: March 1, 2017

Related Experiment Videos

Last Updated: Jun 7, 2026

Computer-Generated Animal Model Stimuli

Computer-Generated Animal Model Stimuli

Published on: July 29, 2007

Localizing Protein in 3D Neural Stem Cell Culture: a Hybrid Visualization Methodology

Localizing Protein in 3D Neural Stem Cell Culture: a Hybrid Visualization Methodology

Published on: December 19, 2010

Creating Virtual-hand and Virtual-face Illusions to Investigate Self-representation

Creating Virtual-hand and Virtual-face Illusions to Investigate Self-representation

Published on: March 1, 2017

Area of Science:

Computer Vision
Artificial Intelligence
Machine Learning

Background:

Generating multiple objects in an image with precise control over their attributes and positions is a challenging task.
Existing methods struggle with attribute leakage, diverse instance descriptions, and maintaining consistency during iterative generation.

Purpose of the Study:

To introduce the Multi-Instance Generation (MIG) task for generating multiple, precisely controlled image instances.
To develop novel methods addressing key challenges in MIG, including attribute leakage, diverse descriptions, and iterative consistency.

Main Methods:

Propose the Multi-Instance Generation Controller (MIGC) using a divide-and-conquer strategy for single-instance tasks.
Introduce MIGC++ for enhanced attribute control (text/image) and position control (boxes/masks).
Develop the Consistent-MIG algorithm to ensure consistency during iterative instance manipulation.

Main Results:

Demonstrate substantial performance improvements over existing techniques on COCO-MIG, Multimodal-MIG, COCO-Position, and DrawBench benchmarks.
Achieve precise control over instance position, attributes (color, shape, category), and quantity.
Validate the effectiveness of MIGC, MIGC++, and Consistent-MIG in addressing MIG challenges.

Conclusions:

The proposed MIG task and associated methods (MIGC, MIGC++, Consistent-MIG) represent a significant advancement in controlled image generation.
These methods offer robust solutions for generating multiple instances with high fidelity and user-specified control.
The developed benchmarks facilitate future research and evaluation in the multi-instance generation domain.