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

Modeling and Similitude

Modeling and Similitude

Scaled modeling is a fundamental technique in engineering, enabling the study of large and complex systems by creating smaller, manageable replicas that recreate critical characteristics of the original. In hydrology and civil infrastructure, for example, scaled models of dams help analyze water flow, turbulence, and pressure. This method allows for accurate predictions of real-world behavior within a controlled environment, significantly reducing the cost and time involved in full-scale...

Stereotype Content Model

Stereotype Content Model

The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...

You might also read

Related Articles

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

Sort by

Same author

CoVR-2: Automatic Data Construction for Composed Video Retrieval.

IEEE transactions on pattern analysis and machine intelligence·2024

Same author

Visible-light driven dual heterojunction formed between g-C<sub>3</sub>N<sub>4</sub>/BiOCl@MXene-Ti<sub>3</sub>C<sub>2</sub> for the effective degradation of tetracycline.

Environmental pollution (Barking, Essex : 1987)·2022

Same author

A Tandem Semipinacol Rearrangement/Aldehyde Arylation or Alkylation of Trisubstituted 2,3-Epoxy Alcohols with Grignard Reagents for Functionalized 1,3-Diols.

The Journal of organic chemistry·2022

Same author

<sup>13</sup>C-Labeled Diethyl Ketoglutarate Derivatives as Hyperpolarized Probes of 2-Ketoglutarate Dehydrogenase Activity.

Analysis & sensing·2022

Same author

Phytochemically stabilized chitosan encapsulated Cu and Ag nanocomposites to remove cefuroxime axetil and pathogens from the environment.

International journal of biological macromolecules·2022

Same author

Contemporary Strategies to Promote Dialysis Access Fistula Maturation.

Vascular and endovascular surgery·2022

Search research articles

Related Experiment Video

Updated: Mar 24, 2026

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Expanded Parts Model for Semantic Description of Humans in Still Images.

Gaurav Sharma, Frederic Jurie, Cordelia Schmid

IEEE Transactions on Pattern Analysis and Machine Intelligence

|March 9, 2016

Summary

We developed an Expanded Parts Model (EPM) for improved human attribute and action recognition in images. This model efficiently identifies relevant parts, outperforming existing methods on challenging datasets.

More Related Videos

Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues

Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues

Published on: June 3, 2013

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: Mar 24, 2026

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues

Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues

Published on: June 3, 2013

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:

Current models for human attribute and action recognition often use a limited number of 'average' templates.
This approach can be inefficient and less accurate in capturing diverse human appearances and actions.

Purpose of the Study:

To introduce an Expanded Parts Model (EPM) for robust human attribute and action recognition in still images.
To develop a novel method that learns discriminative part templates for specific image regions.

Main Methods:

The Expanded Parts Model (EPM) utilizes a collection of learned part templates.
It employs a subset of parts for image scoring, focusing on relevant regions and ignoring background.
A new algorithm automatically mines parts and learns discriminative templates and their locations.

Main Results:

The EPM achieves state-of-the-art quantitative results on three challenging human attribute and action datasets.
Qualitative results demonstrate convincing performance in recognizing human attributes and actions.

Conclusions:

The Expanded Parts Model (EPM) offers a more effective approach to human attribute and action recognition.
The proposed method for learning part templates and locations is efficient and accurate.