@InProceedings{Yang_2023_CVPR,
    author    = {Yang, Antoine and Nagrani, Arsha and Seo, Paul Hongsuck and Miech, Antoine and Pont-Tuset, Jordi and Laptev, Ivan and Sivic, Josef and Schmid, Cordelia},
    title     = {Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2023},
    pages     = {10714-10726}
}