Wei J, Qin L, Yu B, Zou T, Yan C, Xiao D, Yu Y, Yang L, Li K, Liu J. VA-AR: Learning Velocity-Aware Action Representations with Mixture of Window Attention. AAAI [Internet]. 2025Apr.11 [cited 2026May3];39(8):8286-94. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/32894