Fully-attentive iterative networks for region-based controllable image and video captioning

Marcella Cornia, Lorenzo Baraldi, Ayellet Tal, Rita Cucchiara. Fully-attentive iterative networks for region-based controllable image and video captioning. Computer Vision and Image Understanding, 237:103857, December 2023. [doi]

Authors

Marcella Cornia

This author has not been identified. Look up 'Marcella Cornia' in Google

Lorenzo Baraldi

This author has not been identified. Look up 'Lorenzo Baraldi' in Google

Ayellet Tal

This author has not been identified. Look up 'Ayellet Tal' in Google

Rita Cucchiara

This author has not been identified. Look up 'Rita Cucchiara' in Google