Guest Editors
Prof. Chen-Chiung Hsieh
Email: cchsieh@gm.ttu.edu.tw
Affiliation: Department of Computer Science and Engineering, Tatung University, Taipei City, 104, Taiwan
Homepage:
Research Interests: image processing, computer vision, deep learning
Prof. Yi-Zeng Hsieh
Email: yzhsieh@mail.ntust.edu.tw
Affiliation: Department of Electrical Engineering, National Taiwan University of Science and Technology
Homepage:
Research Interests: Deep Learning, Computer Vision, Pattern Recognition
Prof. De-Yuan Huang
Email: dyhuang@gm.ttu.edu.tw
Affiliation: Department of Computer Science and Engineering, Tatung University
Homepage:
Research Interests: Human-Computer Interaction, machine learning, AIoT
Summary
Aims and Scope:
Object detection, a fundamental task in computer vision, has witnessed revolutionary advancements with the advent of deep learning. Deep learning models, particularly convolutional neural networks (CNNs) and transformers, have significantly pushed the boundaries of accuracy, efficiency, and robustness in detecting objects across diverse environments and applications. This special issue aims to gather cutting-edge research on the latest developments and innovative applications of deep learning-based object detection. We invite submissions that address theoretical foundations, novel architectures, algorithmic improvements, and real-world implementations, fostering a comprehensive overview of the current state and future directions of this rapidly evolving field.
Topics of Interest:
We solicit original research articles and comprehensive review papers covering (but not limited to) the following topics:
Novel Deep Learning Architectures for Object Detection:
· One-stage and two-stage detectors (e.g., YOLO variants, RetinaNet, Faster R-CNN)
· Transformer-based object detectors (e.g., DETR, Deformable DETR, Swin Transformer-based detectors)
· Anchor-free object detection methods
· Lightweight and efficient deep learning models for real-time object detection
· Explainable AI (XAI) in deep object detection
Advanced Techniques and Methodologies:
· Few-shot, zero-shot, and open-set object detection
· Weakly supervised and semi-supervised object detection
· Multi-modal object detection (e.g., fusion of RGB, depth, thermal, LiDAR data)
· Object detection in challenging environments (e.g., adverse weather, low light, occlusions, cluttered scenes)
· Temporal object detection and video object detection
· Generative models for data augmentation in object detection
Applications of Deep Learning-Based Object Detection:
· Autonomous driving and intelligent transportation systems
· Medical image analysis and diagnostics
· Industrial inspection and quality control
· Security and surveillance systems
· Agricultural automation and smart farming
· Retail analytics and smart cities
· Environmental monitoring and wildlife detection
Conclusion:
This special issue will serve as a timely and valuable resource for researchers, practitioners, and students interested in the cutting-edge developments and diverse applications of deep learning for object detection. We are confident that this collection of high-quality research will significantly contribute to the existing literature and foster further innovation in this critical field.
Keywords
deep learning, object detection, computer vision, neural networks, autonomous systems,machine learning, target recognition
Login
Register
Submit a Paper
Propose a Special lssue