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: Mar 8, 2026

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

9.7K

Semantic Pooling for Complex Event Analysis in Untrimmed Videos.

Xiaojun Chang, Yao-Liang Yu, Yi Yang

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |January 24, 2017
    PubMed
    Summary

    This study introduces a novel semantic pooling method for video analysis. By prioritizing important video segments, it enhances event detection and recognition accuracy in long, untrimmed videos.

    Related Concept Videos

    You might also read

    Related Articles

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

    Sort by
    Same author

    CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation.

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

    PertAdapt: unlocking single-cell foundation models for genetic perturbation prediction via condition-sensitive adaptation.

    Bioinformatics (Oxford, England)·2026
    Same author

    Bridging Subjectivity in Affective Explanation Captioning via Consensus-Prompted Emotion Reasoning.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same author

    Looking Broader for Knowledge Distillation Via Receptive-Field Alignment.

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

    Parallel Diffusion Solver via Residual Dirichlet Policy Optimization.

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

    Zero-Shot Neural Network Evaluation with Sample-Wise Activation Patterns.

    IEEE transactions on pattern analysis and machine intelligence·2026

    Area of Science:

    • Computer Science
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Video analysis relies on effective pooling strategies to create discriminative representations.
    • Existing methods often lose crucial information by aggregating all video shots equally.
    • Challenging event analysis in long, untrimmed videos is hindered by irrelevant or misleading segments.

    Purpose of the Study:

    • To propose a new semantic pooling approach for improved video event analysis.
    • To address information loss in conventional pooling methods for long untrimmed videos.
    • To enhance the discriminative power of video representations for event detection, recognition, and recounting.

    Main Methods:

    • Defined a novel concept of semantic saliency to assess shot relevance to an event.

    Related Experiment Videos

    Last Updated: Mar 8, 2026

    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

    9.7K
  • Prioritized video shots based on their semantic saliency scores.
  • Developed a new isotonic regularizer to leverage semantic ordering information.
  • Proposed a nearly-isotonic support vector machine classifier.
  • Implemented an efficient proximal gradient algorithm with closed-form proximal steps.

    • Main Results:

    • Achieved promising improvements in event analysis tasks.
    • Demonstrated higher discriminative power compared to conventional pooling strategies.
    • Validated the approach through extensive experiments on three real-world video datasets.

    Conclusions:

    • The proposed semantic pooling approach effectively enhances video event analysis.
    • Prioritizing semantically salient shots leads to more informative video representations.
    • The new method offers a significant advancement for analyzing complex events in untrimmed videos.