Transformer and Deep Learning Applications in Image Processing, 2nd Edition

Dear Colleagues,

Following the success of the first edition (Transformer and Deep Learning Applications in Image Processing), we are pleased to launch the second edition of this Topic.

Convolutional Neural Networks (CNNs) represent a class of deep learning architectures specifically designed to process spatial data, such as images and videos. Due to their ability to autonomously extract features, maintain translational invariance, and perceive local patterns, CNNs have found extensive applications in domains such as image classification, object recognition, object tracking, and medical image processing. However, CNNs are unable to model long-range dependencies effectively and struggle to extract long-distance feature information of the target to be tracked, which impacts the efficiency and accuracy of target tracking. Since the release of ChatGPT 3.0 based on transformers on June 11, 2020, transformers have demonstrated strong capabilities in handling sequential data.

Although CNN models have achieved significant success in the field of image processing imagery over the years, many challenges remain in practical applications, such as complex scene image classification, specific object recognition and tracking, and medical image processing. This situation highlights a noticeable gap between theoretical advancements and practical applications in the image processing field.

Therefore, we invite submissions of studies on theoretical research and practical applications related to transformer and deep learning architectures in the fields of medical image analysis, image classification, recognition, and tracking.

We welcome submissions on—including but not limited to—the following topics:

• Novel architectures and variations in transformers and deep learning models;
• Fine-tuning strategies for pre-trained transformers and deep learning models;
• Image classification based on transformers and deep learning models;
• Image recognition based on transformers and deep learning models;
• Medical image processing based on transformers and deep learning models;
• Object tracking based on transformers and deep learning models;
• Transformers and deep learning for sciences;
• Transformers and convolutional neural network fusion architecture;
• Transformers and deep learning for diverse machine learning tasks;
• Natural language processing.

Prof. Dr. Fengping An
Prof. Dr. Haitao Xu
Dr. Chuyang Ye
Topic Editors