Shraman Pramanick, Yale Song, Sayan Nag, Kevin Qinghong Lin, Hardik Shah, Mike Zheng Shou, Rama Chellappa, Pengchuan Zhang. EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone. In IEEE/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023. pages 5262-5274, IEEE, 2023. [doi]
Abstract is missing.