https://scholar.google.com/scholar?lr&ie=UTF-8&oe=UTF-8&q=Rethinking%20Video%20ViTs:%20Sparse%20Video%20Tubes%20for%20Joint%20Image%20and%20Video%20Learning%20Anelia%20Angelova%20Weicheng%20Kuo%20AJ%20Piergiovanni