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]
@article{CorniaBTC23, title = {Fully-attentive iterative networks for region-based controllable image and video captioning}, author = {Marcella Cornia and Lorenzo Baraldi and Ayellet Tal and Rita Cucchiara}, year = {2023}, month = {December}, doi = {10.1016/j.cviu.2023.103857}, url = {https://doi.org/10.1016/j.cviu.2023.103857}, researchr = {https://researchr.org/publication/CorniaBTC23}, cites = {0}, citedby = {0}, journal = {Computer Vision and Image Understanding}, volume = {237}, pages = {103857}, }