@article{crossvideomaecontrastivespatiotemporalan,
  title = {CrossVideoMAE: Contrastive Spatiotemporal and Semantic Representation Learning from Videos and Images with Masked Autoencoders},
  author = {Shihab Aaqil Ahamed and Malitha Gunawardhana and Liel David and Michael Sidorov and Daniel Harari and Muhammad Haris Khan},
  year = {2025},
  url = {https://www.arxiv.org/abs/2502.07811},
}