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 Experiment Video

Updated: May 20, 2026

Artificial Intelligence-Based System for Detecting Attention Levels in Students
06:37

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

Learning sparse representations for human action recognition.

Tanaya Guha1, Rabab Kreidieh Ward

  • 1Department of Electrical and Computer Engineering, The University of British Columbia, Vancouver, BC, Canada. tanaya@ece.ubc.ca

IEEE Transactions on Pattern Analysis and Machine Intelligence
|June 30, 2012
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Fixed Action Patterns01:06

Fixed Action Patterns

A fixed action pattern (FAP) is a specific, hard-wired sequence of behaviors that occurs in response to an external stimulus, called a sign stimulus. The behavior is “fixed” because it is essentially unchangeable—proceeding similarly across individuals of a species every time it occurs.

You might also read

Related Articles

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

Sort by
Same author

Explainable human-centered traits from head motion and facial expression dynamics.

PloS one·2025
Same author

Towards Autism Screening through Emotion-guided Eye Gaze Response.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2021
Same author

Multi-Camera Trajectory Forecasting With Trajectory Tensors.

IEEE transactions on pattern analysis and machine intelligence·2021
Same author

Motion-Capture Patterns of Voluntarily Mimicked Dynamic Facial Expressions in Children and Adolescents With and Without ASD.

Journal of autism and developmental disorders·2018
Same author

A Computational Study of Expressive Facial Dynamics in Children with Autism.

IEEE transactions on affective computing·2018
Same author

On Quantifying Facial Expression-Related Atypicality of Children with Autism Spectrum Disorder.

Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference)·2015
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

This study introduces sparse representations using overcomplete dictionaries for effective video action recognition. The novel approach enhances classification accuracy for human movements and facial expressions.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Signal Processing

Background:

  • Action recognition in videos is crucial for human-computer interaction and surveillance.
  • Existing methods often rely on clustering or vector quantization, which may not capture rich spatio-temporal information effectively.

Purpose of the Study:

  • To explore the effectiveness of sparse representations derived from overcomplete dictionaries for video action recognition.
  • To develop novel classification algorithms tailored for these sparse representations.
  • To introduce a new local spatio-temporal feature for improved recognition.

Main Methods:

  • Learning overcomplete dictionaries from spatio-temporal descriptors extracted from video sequences.
  • Representing video descriptors as linear combinations of dictionary elements for compact and rich feature extraction.

Related Experiment Videos

Last Updated: May 20, 2026

Artificial Intelligence-Based System for Detecting Attention Levels in Students
06:37

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

  • Developing and applying novel classification algorithms for each dictionary learning framework.

    • Main Results:

    • The proposed approach using sparse representations yields more compact and richer video sequence representations compared to traditional methods.
    • A novel local spatio-temporal feature was developed, demonstrating distinctiveness, scale invariance, and computational efficiency.
    • State-of-the-art results were consistently achieved on multiple public datasets for physical actions and facial expressions.

    Conclusions:

    • Sparse representations learned via overcomplete dictionaries offer a powerful framework for action recognition.
    • The developed local spatio-temporal feature contributes to robust and efficient video analysis.
    • The generalizability of the approach suggests applicability to broader classification tasks beyond human actions.