Revisited Visual Saliency Detection with Deep Learning: A Review of Recent Advancements

Salient Object Detection (SOD) focuses on identifying the most noticeable regions in images or videos those that naturally draw human attention. It has become an active area of research in computer vision, with direct applications in tasks such as video summarization, intelligent cropping, image captioning, and visual tracking. Over the past two decades, many efforts have been made to simulate how the human visual system processes and prioritizes visual information. These approaches have evolved from conventional, handcrafted techniques to more recent deep learning-based models. This review aims at providing a clear and structured overview of the progress in deep learning methods for saliency detection. It also summarizes widely used benchmark datasets, evaluation metrics, and key application areas where saliency detection plays an important role.