![AImageLab](https://aimagelab.ing.unimore.it/imagelab/images/header_aimagelab.png)
Fully-Attentive Iterative Networks for Region-based Controllable Image and Video Captioning
Citation:
Cornia, Marcella; Baraldi, Lorenzo; Ayellet, Tal; Cucchiara, Rita "Fully-Attentive Iterative Networks for Region-based Controllable Image and Video Captioning" COMPUTER VISION AND IMAGE UNDERSTANDING, vol. 237, pp. 1 -10 , 2023 DOI: 10.1016/j.cviu.2023.103857not available