@article{lifelongaudiovideomaskedautoencoderwith,
  title = {STELLA: Continual Audio-Video Pre-training with Spatio-Temporal Localized Alignment},
  author = {Jaewoo Lee and Jaehong Yoon and Wonjae Kim and Yunji Kim and Sung Ju Hwang},
  year = {2023},
  eprint = {2310.08204},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2310.08204v3},
}