ViCo: A Multitask Video-enhanced and Cognition-preserving Modality Alignment Training Framework

@inproceedings{yu2025vico,
  title = {ViCo: A Multitask Video-enhanced and Cognition-preserving Modality Alignment Training Framework},
  author = {Zhenda Yu and Jin Chen and Jiayu Shen and Lanxiang Zhou and Han Fang and Xianghao Zang and Chao Ban and Jing-Feng Chen and Zhongjiang He and Hao Sun and Zerui Li and Yanmei Kang},
  year = {2025},
  booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing},
  doi = {10.1109/icassp49660.2025.10888636},
  url = {https://doi.org/10.1109/icassp49660.2025.10888636},
}