@article{enhancingvideotransformersforaction,
  title = {Enhancing Video Transformers for Action Understanding with VLM-aided Training},
  author = {Hui Lu and Hu Jian and Ronald Poppe and Albert Ali Salah},
  year = {2024},
  eprint = {2403.16128},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.16128v1},
}