Greedy modality selection via approximate submodular maximization

Runxiang Cheng, Gargi Balasubramaniam, Yifei He, Yao-Hung Hubert Tsai, Han Zhao

Abstract: Multimodal learning considers learning from multi-modality data, aiming to fuse heterogeneous sources of information. However, it is not always feasible to leverage all available modalities due to ...