Object detection and recognition are foundational components in computer vision, enabling intelligent systems to perceive, interpret, and act upon visual information. These capabilities are critical to a broad spectrum of applications, including autonomous driving, medical diagnostics, industrial automation, robotics, and intelligent surveillance.

In recent years, the field has witnessed transformative progress driven by deep learning techniques such as convolutional neural networks (CNNs), vision transformers (ViTs), and attention mechanisms. However, numerous challenges remain—such as improving detection speed and accuracy in real-world scenarios, handling small or occluded objects, and enabling models to generalize with limited annotated data.

This Special Issue of Computers, Materials & Continua aims to showcase innovative research addressing both theoretical advances and practical implementations in object detection and recognition. We invite contributions covering a wide range of topics, including but not limited to:
· Lightweight models for real-time detection
· Multi-scale feature fusion and enhancement
· Recognition of small or occluded objects
· Few-shot and zero-shot learning strategies
· Multi-modal approaches incorporating visual, textual, or spatial data
· Knowledge graphs and knowledge-guided machine learning
· Object/image detection, classification, and identification
· Use of ViTs and Graph Convolutional Networks for object understanding

We particularly welcome studies that present novel methods with strong real-world implications—such as in biomedical imaging, or autonomous navigation—and works that address robustness, domain adaptation, and efficient annotation. This Special Issue seeks to bring together researchers, engineers, and practitioners from academia and industry to explore emerging trends and share cutting-edge solutions in the domain of object detection and recognition.