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

Protein Networks

Protein Networks

An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...

Protein Networks

Protein Networks

Sequence Networks of Rotating Machines

Sequence Networks of Rotating Machines

A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...

You might also read

Related Articles

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

Sort by

Same author

Expression, Purification, and Comparative Inhibition of <i>Helicobacter pylori</i> Urease by Regio-Selectively Alkylated Benzimidazole 2-Thione Derivatives.

Molecules (Basel, Switzerland)·2022

Same author

CX-ToM: Counterfactual explanations with theory-of-mind for enhancing human trust in image recognition models.

iScience·2022

Same author

The Planteome database: an integrated resource for reference ontologies, plant genomics and phenomics.

Nucleic acids research·2017

Same author

Learning and Inferring "Dark Matter" and Predicting Human Intents and Trajectories in Videos.

IEEE transactions on pattern analysis and machine intelligence·2017

Same author

Doubly Sparse Relevance Vector Machine for Continuous Facial Behavior Estimation.

IEEE transactions on pattern analysis and machine intelligence·2015

Same author

AISO: Annotation of Image Segments with Ontologies.

Journal of biomedical semantics·2015

Same journal

HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Adaptive Hardness-Driven Dictionary Distillation for Incomplete Streaming View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Achieving Text-based Person Retrieval with Any Granularity.

IEEE transactions on pattern analysis and machine intelligence·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Apr 3, 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

Sum Product Networks for Activity Recognition.

Mohamed R Amer, Sinisa Todorovic

IEEE Transactions on Pattern Analysis and Machine Intelligence

|September 22, 2015

Summary

This summary is machine-generated.

This study introduces a novel method for detecting and localizing human activities in videos using sum-product networks (SPNs) and a Counting Grid (CG) model. The approach achieves state-of-the-art performance in video classification and activity localization across multiple datasets.

More Related Videos

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification

Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification

Published on: February 14, 2018

Related Experiment Videos

Last Updated: Apr 3, 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

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification

Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification

Published on: February 14, 2018

Area of Science:

Computer Vision
Artificial Intelligence
Machine Learning

Background:

Human activity recognition in videos is challenging due to variable spatiotemporal arrangements and actor numbers.
Existing methods often struggle with complex activities and precise localization.

Purpose of the Study:

To develop a robust system for detecting and localizing human activities in videos.
To handle activities with diverse part arrangements and varying numbers of actors.
To improve the accuracy of video classification and activity localization.

Main Methods:

Utilized sum-product networks (SPNs) to model activities with variable part arrangements.
Employed a Counting Grid (CG) model for visual word-based evidence in space-time windows.
Jointly learned SPN and CG parameters in supervised and weakly supervised settings.
Propagated evidence bottom-up and top-down to parse the SPN graph for video explanation.

Main Results:

Achieved superior performance in video classification and activity localization compared to state-of-the-art methods.
Demonstrated effectiveness on benchmark datasets including VIRAT, UT-Interactions, KTH, and TRECVID MED 2011, plus a new Volleyball dataset.

Conclusions:

The proposed SPN and CG integrated approach effectively addresses complex human activity detection and localization.
The method shows significant improvements in accuracy and robustness for video analysis tasks.