author    = {Arghyadeep Sen and Shantipriya Parida and Ketan Kotwal and Subhadarshi Panda and Ondřej Bojar and Satya Ranjan Dash},
  year      = 2021,
  title     = {Bengali Visual Genome: A Multimodal Dataset for Machine Translation and Image Captioning},
  booktitle = {9th International Conference on Frontiers of Intelligent Computing: Theory and Applications (FICTA 2021)},
  pages     = {63--70},
  publisher = {Springer Nature Singapore},
  address   = {Singapore},
  isbn      = {978-981-16-6624-7},