@inproceedings{medvtmultiscaleencoderdecodervideo,
  title = {MED-VT++: Unifying Multimodal Learning with a Multiscale Encoder-Decoder Video Transformer},
  author = {Rezaul Karim and He Zhao and Richard P. Wildes and Mennatullah Siam},
  year = {2023},
  booktitle = {CVPR 2023 1},
  eprint = {2304.05930},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2304.05930v3},
}