@article{wheretofocusquerymodulatedmultimodalkeyf,
  title = {Where to Focus: Query-Modulated Multimodal Keyframe Selection for Long Video Understanding},
  author = {Shaoguang Wang and Weiyu Guo and Ziyang Chen and Xuming Hu and Hui Xiong},
  year = {2026},
  eprint = {2604.17422},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.17422},
}