@article{multimodalfusionandqueryrefinement, title = {Multi-modal Fusion and Query Refinement Network for Video Moment Retrieval and Highlight Detection}, author = {Yifang Xu and Yunzhuo Sun and Benxiang Zhai and Zien Xie and Youyao Jia and Sidan Du}, year = {2025}, eprint = {2501.10692}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2501.10692v1}, }