@article{mf2summmultimodalfusionforvideo, title = {MF2Summ: Multimodal Fusion for Video Summarization with Temporal Alignment}, author = {Shuo Wang and Jihao Zhang}, year = {2025}, eprint = {2506.10430}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.10430v1}, }