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

Introduction to Learning01:18

Introduction to Learning

646
Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
646
Observational Learning01:12

Observational Learning

493
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
493
Force Classification01:22

Force Classification

1.9K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
1.9K

You might also read

Related Articles

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

Sort by
Same author

Class-Incremental Learning on Video-Based Action Recognition by Distillation of Various Knowledge.

Computational intelligence and neuroscience·2022
Same author

Entropy-Based Video Steganalysis of Motion Vectors.

Entropy (Basel, Switzerland)·2020
See all related articles

Related Experiment Video

Updated: Oct 30, 2025

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

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

9.2K

Scaling Human-Object Interaction Recognition in the Video through Zero-Shot Learning.

Vali Ollah Maraghi1, Karim Faez1

  • 1Department of Electrical Engineering, Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran.

Computational Intelligence and Neuroscience
|July 2, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces zero-shot learning for human-object interaction (HOI) recognition in videos. The method identifies unseen HOI classes by recognizing verbs and objects, improving scalability and reducing the need for extensive labeled data.

More Related Videos

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.6K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

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

Published on: December 15, 2023

4.6K

Related Experiment Videos

Last Updated: Oct 30, 2025

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

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

9.2K
A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.6K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

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

Published on: December 15, 2023

4.6K

Area of Science:

  • Computer Vision
  • Artificial Intelligence

Background:

  • Human-object interaction (HOI) recognition is crucial in computer vision.
  • Current HOI methods require fully supervised training on all interaction categories, which is costly and impractical due to the vast number of possible HOIs.

Purpose of the Study:

  • To address the limitations of fully supervised HOI recognition by proposing a scalable approach using zero-shot learning.
  • To enable the recognition of novel HOI classes not present in the training data.

Main Methods:

  • A novel neural network architecture is introduced for video understanding and representation.
  • The system learns to recognize verbs and objects separately during training and combines them at test time.
  • Lateral information from word embeddings is used to validate verb-object pairs, preventing the detection of rare or incorrect HOIs.
  • A new feature aggregation method is proposed for effectively combining high-level features from video frames, particularly for actions with multiple sub-actions.

Main Results:

  • The proposed zero-shot learning approach successfully recognizes unseen human-object interaction classes.
  • The system demonstrates acceptable recognition of seen HOI types.
  • The method significantly increases the number of identifiable HOI classes beyond the training set.

Conclusions:

  • Zero-shot learning offers a scalable solution for human-object interaction recognition in videos.
  • The proposed method effectively identifies novel HOI combinations by recognizing constituent verbs and objects.
  • The integration of lateral information and advanced feature aggregation enhances the robustness and accuracy of HOI recognition.