Priyankar Bose, Pratip Rana, Preetam Ghosh. Attention-Based Multimodal Deep Learning on Vision-Language Data: Models, Datasets, Tasks, Evaluation Metrics and Applications. IEEE Access, 11:80624-80646, 2023. [doi]
@article{BoseRG23,
title = {Attention-Based Multimodal Deep Learning on Vision-Language Data: Models, Datasets, Tasks, Evaluation Metrics and Applications},
author = {Priyankar Bose and Pratip Rana and Preetam Ghosh},
year = {2023},
doi = {10.1109/ACCESS.2023.3299877},
url = {https://doi.org/10.1109/ACCESS.2023.3299877},
researchr = {https://researchr.org/publication/BoseRG23},
cites = {0},
citedby = {0},
journal = {IEEE Access},
volume = {11},
pages = {80624-80646},
}