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

Hybrid Zones

Hybrid Zones

Hybrid zones are narrow regions where two closely related species interact, mate, and produce hybrids. Relative to either parent species, hybrids may possess distinct phenotypic or genetic differences that impact their survival and reproductive success. The genetic variances introduced by hybridization influence species diversity and speciation processes within the hybrid zone.

Hybridoma Technology

Hybridoma Technology

Hybridoma technology is used for the large-scale production of monoclonal antibodies. Monoclonal antibodies bind to only a single antigenic determinant or epitope. Such antibodies are used in research, diagnostics, and disease therapy. The hybridoma technology established in 1975 by Georges Köhler and Cesar Milstein was awarded the Nobel Prize in Medicine in 1984 for revolutionizing research and therapy.
Hybridoma Selection
Commonly used fusion techniques — electroporation, polyethylene glycol...

Health Information Technology and Healthcare Information System

Health Information Technology and Healthcare Information System

Health Information Technology (HIT)
Health Information Technology, commonly called HIT, integrates advanced information systems and technology in healthcare settings. Its primary functions include:

In-situ Hybridization

In-situ Hybridization

In situ hybridization (ISH) is a technique used to detect and localize specific DNA or RNA molecules in cells, tissue, or tissue sections using a labeled probe. The technique was first used in 1969 for the investigation of nucleic acids. It is currently an essential tool in scientific research and clinical settings, especially for diagnostic purposes.
Types of probes and labels
A probe is a complementary strand of DNA or RNA that binds to corresponding nucleotide sequences in a cell. Many...

Fischer Projections

Fischer Projections

Learning to draw Fischer projections of molecules and understanding their relevance plays a crucial role in the visual depiction of organic molecules. A Fischer projection is a two-dimensional projection on a planar surface to simplify the three-dimensional wedge–dash representation of molecules. This is especially helpful in the case of molecules with multiple chiral centers that can be difficult to draw. Here, all the bonds of interest are represented as horizontal or vertical lines. While...

Hybridization of Atomic Orbitals II

Hybridization of Atomic Orbitals II

sp3d and sp3d 2 Hybridization

You might also read

Related Articles

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

Sort by

Same author

IntentQA: Intent Question Answering in Videos by Cognitive Context Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

Cross-robot behavior adaptation through intention alignment.

Science robotics·2026

Same author

M<sup>2</sup> Diffuser: Diffusion-based Trajectory Optimization for Mobile Manipulation in 3D Scenes.

IEEE transactions on pattern analysis and machine intelligence·2025

Same author

Human-level few-shot concept induction through minimax entropy learning.

Science advances·2024

Same author

In situ bidirectional human-robot value alignment.

Science robotics·2022

Same author

CX-ToM: Counterfactual explanations with theory-of-mind for enhancing human trust in image recognition models.

iScience·2022

Search research articles

Related Experiment Video

Updated: May 26, 2026

Superior Auto-Identification of Trypanosome Parasites by Using a Hybrid Deep-Learning Model

Superior Auto-Identification of Trypanosome Parasites by Using a Hybrid Deep-Learning Model

Published on: October 27, 2023

Learning Hybrid Image Templates (HIT) by Information Projection.

Zhangzhang Si¹, Song-Chun Zhu

¹Statistics Department, University of California Los Angeles, 8125 Math Sciences Building, Los Angeles, CA 90095 USA. zzsi@stat.ucla.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence

|December 7, 2011

Summary

This study introduces a new method for creating image representations called hybrid image templates (HITs) using few examples. These HITs effectively capture object characteristics and perform well in image classification tasks.

More Related Videos

Digital Inline Holographic Microscopy (DIHM) of Weakly-scattering Subjects

Digital Inline Holographic Microscopy (DIHM) of Weakly-scattering Subjects

Published on: February 8, 2014

Related Experiment Videos

Last Updated: May 26, 2026

Superior Auto-Identification of Trypanosome Parasites by Using a Hybrid Deep-Learning Model

Superior Auto-Identification of Trypanosome Parasites by Using a Hybrid Deep-Learning Model

Published on: October 27, 2023

Digital Inline Holographic Microscopy (DIHM) of Weakly-scattering Subjects

Digital Inline Holographic Microscopy (DIHM) of Weakly-scattering Subjects

Published on: February 8, 2014

Area of Science:

Computer Vision
Machine Learning
Pattern Recognition

Background:

Learning generative image representations from limited data is challenging.
Existing methods often require large datasets for effective training.
Developing robust representations that handle variations in shape and texture is crucial.

Purpose of the Study:

To propose a novel framework for learning hybrid image templates (HITs) from a small number of image examples (3-20).
To develop a generative image representation that captures intrinsic object or scene characteristics.
To achieve competitive or superior performance in image classification, especially with limited training data.

Main Methods:

Learning a generative image representation (HIT) composed of adaptive image patches.
Utilizing four types of heterogeneous descriptors: local sketch, texture gradients, flatness regions, and colors.
Employing an information projection framework for automatic patch ranking and selection based on information gain.
Integrating heterogeneous feature statistics using a well-normalized probability model.

Main Results:

The learned HITs effectively capture intrinsic characteristics of object and scene categories.
Classification performance is on par with state-of-the-art methods like HoG+SVM.
The proposed system demonstrates a clear advantage when using small training sample sizes.
The automated feature selection enables scalability across diverse image categories.

Conclusions:

The hybrid image template (HIT) framework provides an effective method for learning generative image representations from limited data.
The approach offers a robust solution for image classification, particularly in low-data regimes.
The automated feature selection and integration of heterogeneous descriptors contribute to the method's scalability and performance.