Long-Term Video Question Answering via Multimodal Hierarchical Memory Attentive Networks

Ting Yu, Jun Yu 0002, Zhou Yu, Qingming Huang, Qi Tian 0001. Long-Term Video Question Answering via Multimodal Hierarchical Memory Attentive Networks. IEEE Trans. Circuits Syst. Video Techn., 31(3):931-944, 2021. [doi]

Abstract

Abstract is missing.