StNet: Local and global spatial-temporal modeling for action recognitionDongliang HeZhichao Zhouet al.2019AAAI 2019
Attention Clusters: Purely Attention Based Local Feature Integration for Video ClassificationXiang LongChuang Ganet al.2018CVPR 2018
Purely Attention Based Local Feature Integration for Video ClassificationXiang LongGerard De Meloet al.2022IEEE TPAMI