@article{m2clipamultimodalmultitaskadapting,
  title = {M2-CLIP: A Multimodal, Multi-task Adapting Framework for Video Action Recognition},
  author = {Mengmeng Wang and Jiazheng Xing and Boyuan Jiang and Jun Chen and Jianbiao Mei and Xingxing Zuo and Guang Dai and Jingdong Wang and Yong liu},
  year = {2024},
  eprint = {2401.11649},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2401.11649v1},
}