DSAMT: Dual-Source Aligned Multimodal Transformers for TextCaps

Chenyang Liao, Ruifang Liu, Sheng Gao. DSAMT: Dual-Source Aligned Multimodal Transformers for TextCaps. In 7th IEEE International Conference on Network Intelligence and Digital Content, IC-NIDC 2021, Beijing, China, November 17-19, 2021. pages 373-377, IEEE, 2021. [doi]

Bibliographies