Search research articles

ACERCA DE JoVE

Visión General Liderazgo Blog Centro de Ayuda JoVE

AUTORES

Proceso de Publicación Consejo Editorial Alcance y Políticas Revisión por Pares Preguntas Frecuentes Enviar

BIBLIOTECARIOS

Testimonios Suscripciones Acceso Recursos Consejo Asesor de Bibliotecas Preguntas Frecuentes

INVESTIGACIÓN

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archivo

EDUCACIÓN

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Centro de Recursos para Profesores Sitio de Profesores

Términos y Condiciones de Uso

Política de Privacidad

Videos de Conceptos Relacionados

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...

Support Reactions in Three Dimensions

Support Reactions in Three Dimensions

Support reactions in three dimensions help maintain the stability and equilibrium of various structures and systems. These reactions prevent the system from translating and rotating, ensuring the design can withstand external forces and perform its intended function efficiently and safely. Some of the supports providing support reactions in three dimensions are discussed below:
Ball and Socket Joint is one of the supports allowing free rotation about any axis. This freedom of rotation is...

Automatic Processing and Automatic Social Behavior

Automatic Processing and Automatic Social Behavior

Automatic processing refers to the cognitive operations that occur without conscious intent or awareness, playing a fundamental role in shaping social cognition and behavior. These processes enable individuals to navigate complex social environments efficiently by relying on mental shortcuts and pre-existing knowledge structures known as schemas. One of the most influential mechanisms underlying automatic processing is priming, which subtly activates mental representations through exposure to...

Three-Dimensional Force System:Problem Solving

Three-Dimensional Force System:Problem Solving

A three-dimensional force system refers to a scenario in which three forces act simultaneously in three different directions. This type of problem is commonly encountered in physics and engineering, where it is necessary to calculate the resultant force on the system, which can then be used to predict or analyze the behavior of the object or structure under consideration.
To solve a three-dimensional force system, first resolve each force into its respective scalar components. Do this using...

Structural Classification of Joints

Structural Classification of Joints

Joints, also known as articulations, are classified based on their structural characteristics, i.e., based on whether the articulating surfaces of the adjacent bones are directly connected by fibrous connective tissue or cartilage, or whether the articulating surfaces contact each other within a fluid-filled joint cavity. These differences serve to divide the joints of the body into three structural classifications.
A fibrous joint is where the adjacent bones are united by fibrous connective...

Muscles for Facial Expressions

Muscles for Facial Expressions

The craniofacial muscles are a collection of approximately 20 thin skeletal muscles situated beneath the skin of the face and scalp. These muscles, primarily responsible for the vast array of human facial expressions, originate from the bones or fibrous structures of the skull and extend outwards to connect with the skin. While most skeletal muscles in the body are enveloped in thick fascia, facial muscles generally have a more delicate fascial covering, with the buccinator muscle being a...

También podría leer

Artículos Relacionados

Artículos vinculados a este trabajo por autores compartidos, revista y gráfico de citas.

Ordenar por

Same author

Dissociating spatial frequency reliance from adversarial robustness advantages in neurally guided deep convolutional neural networks.

ArXiv·2026

Same author

Bottom-up and generative computations uniquely explain neural responses across the social brain.

bioRxiv : the preprint server for biology·2026

Same author

Aligning Video Models with Human Social Judgments via Behavior-Guided Fine-Tuning.

ArXiv·2025

Same author

Generative adversarial collaborations: a new model of scientific discourse.

Trends in cognitive sciences·2024

Same author

Early Neural Development of Social Interaction Perception: Evidence from Voxel-Wise Encoding in Young Children and Adults.

The Journal of neuroscience : the official journal of the Society for Neuroscience·2024

Same author

Neural Encoding of Bodies for Primate Social Perception.

The Journal of neuroscience : the official journal of the Society for Neuroscience·2024

Search research articles

Video Experimental Relacionado

Updated: Feb 28, 2026

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Características simples de pose 3D para la comprensión de escenas sociales humanas y de máquinas

Wenshuo Qin, Leyla Isik

|February 27, 2026

Resumen

Los humanos utilizan información de pose 3D para la percepción social, superando a las redes neuronales profundas (DNN). Las características mínimas de pose 3D son clave para reconocer interacciones sociales y mejorar el rendimiento de las DNN.

Palabras clave:

pose 3D percepción social interacción social redes neuronales profundas inteligencia artificial

Más Videos Relacionados

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

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

Videos de Experimentos Relacionados

Last Updated: Feb 28, 2026

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

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

Área de la Ciencia:

Ciencias Cognitivas
Visión por Computadora
Inteligencia Artificial

Sus antecedentes:

El reconocimiento de la interacción social humana es un esfuerzo sin esfuerzo pero computacionalmente complejo.
Las redes neuronales profundas (DNN) actuales tienen dificultades con el reconocimiento de la interacción social.

Objetivo del estudio:

Investigar si los humanos utilizan la pose 3D visuoespacial para juicios sociales.
Comparar el poder predictivo de la información de pose 3D frente a las DNN para la percepción social.

Principales métodos:

Una tubería novedosa extrajo posiciones de las articulaciones del cuerpo en 3D de los videos.
Se utilizaron articulaciones del cuerpo en 3D y incrustaciones de DNN para predecir juicios sociales humanos.
Los conjuntos de características se redujeron a información mínima de pose 3D y 2D.

Principales resultados:

Las articulaciones del cuerpo en 3D superaron a la mayoría de las DNN en la predicción de juicios sociales.
Las características mínimas de pose 3D, no las 2D, fueron necesarias y suficientes para la predicción.
Estas características 3D mejoraron la alineación y el rendimiento de las DNN en tareas sociales.

Conclusiones:

La percepción social humana se basa en información explícita de pose 3D.
La información 3D visuoespacial es crucial para comprender las interacciones sociales.
La incorporación de la pose 3D puede mejorar la inteligencia social artificial.