Deep Learning Innovations in Video Classification: A Survey on Techniques and Dataset Evaluations
Electronics · 11.07.2024 · 13 (14) · 2732
DOI: 10.3390/electronics13142732 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 11.07.2024. Verfasst von Makara Mao und 2 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 125 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea (NRF), BK21 FOUR, Soonchunhyang University Research Fund.
Abstract (Originalsprache)
Video classification has achieved remarkable success in recent years, driven by advanced deep learning models that automatically categorize video content. This paper provides a comprehensive review of video classification techniques and the datasets used in this field. We summarize key findings from recent research, focusing on network architectures, model evaluation metrics, and parallel processing methods that enhance training speed. Our review includes an in-depth analysis of state-of-the-art deep learning models and hybrid architectures, comparing models to traditional approaches and highlighting their advantages and limitations. Critical challenges such as handling large-scale datasets, improving model robustness, and addressing computational constraints are explored. By evaluating performance metrics, we identify areas where current models excel and where improvements are needed. Additionally, we discuss data augmentation techniques designed to enhance dataset accuracy and address specific challenges in video classification tasks. This survey also examines the evolution of convolutional neural networks (CNNs) in image processing and their adaptation to video classification tasks. We propose future research directions and provide a detailed comparison of existing approaches using the UCF-101 dataset, highlighting progress and ongoing challenges in achieving robust video classification.
Förderung
- National Research Foundation of Korea (NRF)
- BK21 FOUR
- Soonchunhyang University Research Fund
Zitieren
APA
Mao, M., Lee, A., & Hong, M. (2024). Deep Learning Innovations in Video Classification: A Survey on Techniques and Dataset Evaluations. Electronics, 13(14), 2732. https://doi.org/10.3390/electronics13142732
Vancouver
Mao M, Lee A, Hong M. Deep Learning Innovations in Video Classification: A Survey on Techniques and Dataset Evaluations. Electronics. 2024;13(14):2732. doi:10.3390/electronics13142732
BibTeX
@article{Mao2024,
author = {Mao, Makara and Lee, Ahyoung and Hong, Min},
title = {Deep Learning Innovations in Video Classification: A Survey on Techniques and Dataset Evaluations},
journal = {Electronics},
year = {2024},
volume = {13},
number = {14},
pages = {2732},
doi = {10.3390/electronics13142732}
}
EUVIMED