Definition
Multimodal fusion refers to the process of combining information from multiple modalities in order to enhance the understanding or analysis of a certain phenomenon or problem. In essence, it involves integrating data from different sources, such as text, images, audio, video, and sensor readings to gain a more comprehensive and accurate representation of the underlying information.
In the context of HCI, multi-modal fusion concerns the understanding of the synchronization between the different input devices in a multi-modal interaction context
References
(Lelli, Blouin, Baudry, 2015a) https://www.educative.io/answers/what-is-multimodal-fusion