Detect to track and track to detect by Feichtenhofer, C, Pinz, A, Zisserman, A

Convolutional two-stream network fusion for video action recognition by Feichtenhofer, C, Pinz, A, Zisserman, A

What have we learned from deep representations for action recognition? by Feichtenhofer, C, Pinz, A, Wildes, R, Zisserman, A

Deep insights into convolutional networks for video recognition by Feichtenhofer, C, Pinz, A, Wildes, RP, Zisserman, A

Keeping your eye on the ball: Trajectory attention in video transformers by Patrick, M, Campbell, D, Asano, Y, Misra, I, Metze, F, Feichtenhofer, C, Vedaldi, A, Henriques, JF