@article{henasylearningtoassemblesceneentities,
  title = {HENASY: Learning to Assemble Scene-Entities for Egocentric Video-Language Model},
  author = {Khoa Vo and Thinh Phan and Kashu Yamazaki and Minh Tran and Ngan Le},
  year = {2024},
  eprint = {2406.00307},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.00307v4},
}