Stay in Grid: Improving Video Captioning via Fully Grid-Level Representation

Mingkang Tang, Zhanyu Wang, Zhaoyang Zeng, Xiu Li, Luping Zhou. Stay in Grid: Improving Video Captioning via Fully Grid-Level Representation. IEEE Trans. Circuits Syst. Video Techn., 33(7):3319-3332, July 2023. [doi]

Abstract

Abstract is missing.