A survey of multimodal recommendation systems
Keywords: Multimodal、Recommendation
Abstract: With the continuous development of network applications, the network resources are growing exponentially, and the phenomenon of information overload is becoming more and more serious. How to efficiently obtain the resources that meet the needs has become one of the problems that plague people. The recommendation system can effectively filter the massive information, and recommend the resources that meet their needs for the users.With the emergence of multimedia services such as short videos and news, it has become increasingly important to understand this content in recommendation. In addition, multimodal features also help alleviate the data sparsity problem in RS. Therefore, multimodal recommendation systems (MRS) have attracted wide attention from academia and industry in recent years.In this paper, we first introduced three traditional recommendation technologies, and then introduced the components of the MRS and the general process of MRS, and according to the different classification methods, introduced four multimodal recommendation systems. Finally, we discuss the challenges MRS Faces and summarize the paper.
Submission Number: 3
Loading