Guest Editors
Prof. Rui Yao
Email: ruiyao@cumt.edu.cn
Affiliation: School of Computer Sciences and Technology, China University of Mining and Technology, Xuzhou, 221116, China
Homepage:
Research Interests: computer vision, pattern recognition, deep learning, and artificial intelligence
Prof. Huanlong Zhang
Email: zhl_lit@163.com
Affiliation: College of Electric and Information Engineering, Zhengzhou University of Light Industry, Zhengzhou, 450000, China
Homepage:
Research Interests: pattern recognition, machine learning, image processing, computer vision, and intelligent man-machine systems
Assoc. Prof. Hancheng Zhu
Email: zhuhancheng@cumt.edu.cn
Affiliation: School of Computer Sciences and Technology, China University of Mining and Technology, Xuzhou, 221116, China
Homepage:
Research Interests: computer vision, visual aesthetics assessment and enhancement
Dr. Kunyang Sun
Email: kunyang_sun@cumt.edu.cn
Affiliation: School of Computer Sciences and Technology, China University of Mining and Technology, Xuzhou, 221116, China
Homepage:
Research Interests: object detection,segmentation,6G communication
Summary
With the explosive growth of video data across surveillance, autonomous driving, robotics, and multimedia platforms, robust object tracking and scene-understanding have become central to modern intelligent systems and interactive applications.
This special issue aims to bring together cutting-edge research on video object tracking and scene understanding from both theoretical and applied perspectives. We invite manuscripts that make significant advances in modeling temporal dynamics, leveraging multimodal inputs (e.g., RGB, T, D, event), exploiting self-supervised or few-shot regimes, and integrating scene semantics and context into tracking pipelines. The scope includes new architectures, generative and adversarial strategies, domain adaptation, and real-world deployment, with emphasis on both algorithmic novelty and system-level performance.
Suggested Themes
- Multimodal video tracking (RGB-T, RGB-D, thermal, event-based)
- Transformer, graph, and generative model frameworks for video tracking
- Self-supervised, few-shot, or zero-shot tracking approaches
- Robust and adversarial tracking in complex scenarios (occlusion, lighting, deformation)
- Scene-understanding and semantic context integration for tracking (behaviour prediction, crowd analytics)
- Lightweight, real-time tracking systems for edge/embedded platforms
- Applications in autonomous driving, UAVs, robotics, smart surveillance, and multimedia analytics
Keywords
video object tracking, scene understanding, multimodal fusion, transformer networks, self-supervised learning
Login
Register
Submit a Paper
Propose a Special lssue