Joint long and short span self-attention network for multi-view classification

Zhikui Chen, Kai Lou, Zhenjiao Liu, Yue Li, Yiming Luo, Liang Zhao

Abstract: Highlights•A novel end-to-end unified multi-view classification framework is proposed.•A long and short span self-attention layer is constructed.•An adaptive weight loss fusion strategy is designed.•The performance of our method outperforms the popular models.