Multi-view Classification (MVC) has emerged as a promising approach in machine learning, aimed at enhancing classification accuracy by leveraging information from multiple perspectives. As the demand for more robust, interpretable, and effective machine learning models grows, MVC has shown significant progress over the past decade, yet it faces new challenges. Despite extensive literature on this subject, there is a notable absence of a comprehensive synthesis of MVC methods. This paper addresses this gap by presenting a thorough overview and classification of MVC methods, categorizing them into seven distinct classes: text, image, time series, hyperspectral, video, signal, and 3D shape. Our meticulous examination within each class highlights advancements and evaluates their applicability in both supervised and semi-supervised learning contexts. Beyond this retrospective analysis, we explore future directions for research and development in this domain. This survey serves as a compendium of existing knowledge and as a guide for future endeavours in MVC, shaping the trajectory of ongoing research and innovation.
