Deep Learning Innovations in Video Classification: A Survey on Techniques and Dataset Evaluations

Electronics, Journal Year: 2024, Volume and Issue: 13(14), P. 2732 - 2732

Published: July 11, 2024

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 techniques and the datasets used this field. We summarize key findings from research, focusing on network architectures, model evaluation metrics, parallel processing methods enhance training speed. Our includes an in-depth analysis state-of-the-art hybrid comparing to traditional approaches highlighting their advantages limitations. Critical challenges such as handling large-scale datasets, improving robustness, addressing computational constraints are explored. By evaluating performance we identify areas where current excel improvements needed. Additionally, discuss data augmentation designed dataset accuracy address specific tasks. survey also examines evolution convolutional neural networks (CNNs) image adaptation propose future research directions provide detailed comparison existing using UCF-101 dataset, progress ongoing achieving robust classification.

Language: Английский

---

Optimising Random Forest Machine Learning Algorithms for User VR Experience Prediction Based on Iterative Local Search-Sparrow Search Algorithm

2022 4th International Conference on Communications, Information System and Computer Engineering (CISCE), Journal Year: 2024, Volume and Issue: unknown, P. 1387 - 1391

Published: May 10, 2024

Language: Английский

---

Efficient Fabric Classification and Object Detection Using YOLOv10

Electronics, Journal Year: 2024, Volume and Issue: 13(19), P. 3840 - 3840

Published: Sept. 28, 2024

The YOLO (You Only Look Once) series is renowned for its real-time object detection capabilities in images and videos. It highly relevant industries like textiles, where speed accuracy are critical. In the textile industry, accurate fabric type classification essential improving quality control, optimizing inventory management, enhancing customer satisfaction. This paper proposes a new approach using YOLOv10 model, which offers enhanced accuracy, processing speed, on torn path of each fabric. We developed utilized specialized, annotated dataset featuring diverse samples, including cotton, hanbok, cotton yarn-dyed, blend plain fabrics, to detect model was selected superior performance, leveraging advancements deep learning architecture applying data augmentation techniques improve adaptability generalization various patterns textures. Through comprehensive experiments, we demonstrate effectiveness YOLOv10, achieved an 85.6% outperformed previous variants both precision speed. Specifically, showed 2.4% improvement over YOLOv9, 1.8% YOLOv8, 6.8% YOLOv7, 5.6% YOLOv6, 6.2% YOLOv5. These results underscore significant potential automating processes, thereby operational efficiency productivity manufacturing retail.

Language: Английский

---

Method for the Visualization of Architectural Structures by Means of Virtual Reality Techniques

Published: Aug. 7, 2024

Language: Английский

---