Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Naturalistic Observations02:30

Naturalistic Observations

15.6K
If you want to understand how behavior occurs, one of the best ways to gain information is to simply observe the behavior in its natural context. However, people might change their behavior in unexpected ways if they know they are being observed. How do researchers obtain accurate information when people tend to hide their natural behavior? As an example, imagine that your professor asks everyone in your class to raise their hand if they always wash their hands after using the restroom. Chances...
15.6K
Stereotype Content Model02:16

Stereotype Content Model

14.8K
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...
14.8K

You might also read

Related Articles

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

Sort by
Same author

Syntactic language change in English and German: Metrics, parsers, and convergences.

PloS one·2026
Same author

Machine learning in psychiatric health records: A gold standard approach to trauma annotation.

Translational psychiatry·2025
Same author

Machine Learning in Psychiatric Health Records: A Gold Standard Approach to Trauma Annotation.

medRxiv : the preprint server for health sciences·2025
Same author

Dense Paraphrasing for multimodal dialogue interpretation.

Frontiers in artificial intelligence·2025
Same author

Neither neural networks nor the language-of-thought alone make a complete game.

The Behavioral and brain sciences·2023
Same author

Editorial: Multimodal communication and multimodal computing.

Frontiers in artificial intelligence·2023

Related Experiment Video

Updated: Aug 9, 2025

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

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

Published on: April 21, 2023

1.7K

Grounding human-object interaction to affordance behavior in multimodal datasets.

Alexander Henlein1, Anju Gopinath2, Nikhil Krishnaswamy2

  • 1Text Technology Lab, Faculty of Computer Science and Mathematics, Institute of Computer Science, Goethe University Frankfurt, Frankfurt, Germany.

Frontiers in Artificial Intelligence
|February 16, 2023
PubMed
Summary
This summary is machine-generated.

This study distinguishes between Gibsonian and telic affordances, enhancing datasets and models for Human-Object Interaction (HOI) detection. The AffordanceUPT model effectively differentiates these affordance types, revealing new data correlations.

Keywords:
affordance detectionhabitat detectionhuman-object interactionmultimodal datasetsmultimodal groundingneural modelstransformers

More Related Videos

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior
10:52

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

Published on: April 13, 2016

8.9K
A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

11.0K

Related Experiment Videos

Last Updated: Aug 9, 2025

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

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

Published on: April 21, 2023

1.7K
Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior
10:52

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

Published on: April 13, 2016

8.9K
A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

11.0K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Cognitive Science

Background:

  • Affordance detection and Human-Object Interaction (HOI) detection are related but distinct tasks.
  • Traditional affordances (Gibsonian) focus on action possibilities, while telic affordances consider conventionalized purpose.
  • Existing datasets like HICO-DET lack detailed affordance annotations.

Purpose of the Study:

  • To augment the HICO-DET dataset with Gibsonian and telic affordance annotations.
  • To adapt and evaluate an HOI model for affordance detection, including object and human orientation.
  • To investigate the distinction between Gibsonian and telic affordances and their correlation with visual features.

Main Methods:

  • Augmented the HICO-DET dataset with Gibsonian and telic affordance and orientation annotations.
  • Trained an adapted Human-Object Interaction (HOI) model, AffordanceUPT, based on the Unary-Pairwise Transformer (UPT).
  • Modularized the UPT model to decouple affordance detection from object detection.

Main Results:

  • The AffordanceUPT model demonstrated generalization to novel objects and actions.
  • The model successfully distinguished between Gibsonian and telic affordances.
  • The study found correlations between affordance distinctions and features not present in standard HOI annotations.

Conclusions:

  • The proposed method effectively differentiates between Gibsonian and telic affordances.
  • Augmenting datasets with affordance-specific annotations improves model understanding.
  • The distinction between affordance types is linked to subtle visual cues beyond basic HOI detection.