The classifier judged this item not relevant to AI security, so it is left out of lists, feeds, the API and dataset releases. If that is wrong, report a correction on this page.
InfoResearchPeer-reviewed
A Comprehensive Survey on Multimodal Recommender Systems: Taxonomy, Evaluation, and Future Directions
- Published
- Record updated
Summary
This survey reviews recent research on multimodal recommender systems, which infer user preferences from historical interactions and from data across several modalities. It lays out the pipeline most such systems follow, classifies existing models by method, and runs a performance analysis of several baseline models. It also introduces a code framework for implementing state-of-the-art models and benchmarking recommender performance.