@article{beyondboxesmaskguidedspatiotemporal,
  title = {Beyond Boxes: Mask-Guided Spatio-Temporal Feature Aggregation for Video Object Detection},
  author = {Khurram Azeem Hashmi and Talha Uddin Sheikh and Didier Stricker and Muhammad Zeshan Afzal},
  year = {2024},
  eprint = {2412.04915},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.04915v1},
}