Multimodal Ensemble Fusion for Disambiguation and Retrieval

作者：Peng Yang^*; Zhou Xiaofeng; Wang Daisy Zhe; Patwa Ishan; Gong Dihong; Fang Chunsheng Victor

来源：IEEE Multimedia, 2016, 23(2): 42-52.

DOI：10.1109/mmul.2016.22

The proposed multimodal ensemble fusion model captures complementary and correlative relations between two modalities. Experimental results show that it outperforms approaches using only a single modality for word sense disambiguation and information retrieval.

• 出版日期2016-6