Key points are not available for this paper at this time.
Advancements in multimodal learning have experienced rapid growth over the past decade, particularly within various domains, with a significant emphasis on developments in computer vision. Multimodal data fusion has become increasingly prominent in the realm of image classification, where the integration of diverse data sources enhances the overall understanding and performance of classification models. This survey delves into the recent strides made in multimodal learning over the past decade, particularly within the field of image classification. Additionally, the paper undertakes a comparative study, critically evaluating the effectiveness and performance of different multimodal fusion approaches. The aim is to provide a comprehensive overview of the current state-of-the-art in multimodal data fusion for image classification and to identify key trends, challenges, and opportunities in this evolving field.
Datsi et al. (Wed,) studied this question.