Compound-Attention Network with Original Feature injection for visual question and answering

Chunlei Wu, Jing Lu, Haisheng Li, Jie Wu, Hailong Duan, Shaozu Yuan. Compound-Attention Network with Original Feature injection for visual question and answering. Signal, Image and Video Processing, 15(8):1853-1861, 2021. [doi]

Authors

Chunlei Wu

This author has not been identified. Look up 'Chunlei Wu' in Google

Jing Lu

This author has not been identified. Look up 'Jing Lu' in Google

Haisheng Li

This author has not been identified. Look up 'Haisheng Li' in Google

Jie Wu

This author has not been identified. Look up 'Jie Wu' in Google

Hailong Duan

This author has not been identified. Look up 'Hailong Duan' in Google

Shaozu Yuan

This author has not been identified. Look up 'Shaozu Yuan' in Google