Quo Vadis, action recognition? A new model and the kinetics dataset by Carreira, J, Zisserman, A

The visual centrifuge: Model-free layered video representations by Alayrac, J-B, Carreira, J, Zisserman, A

Video action transformer network by Girdhar, R, Carreira, J, Doersch, C, Zisserman, A

Massively parallel video networks by Carreira, J, Patraucean, V, Mazare, L, Zisserman, A, Osindero, S

Controllable attention for structured layered video decomposition by Alayrac, J-B, Carreira, J, Arandjelovic, R, Zisserman, A

Input-level inductive biases for 3D reconstruction by Yifan, W, Doersch, C, Arandjelović, R, Carreira, J, Zisserman, A

Quality assessment of compost prepared with municipal solid waste by Jodar J. R., Ramos N., Carreira J. A., Pacheco R., Fernández-Hernández A.

Get full text

TAPIR: tracking any point with per-frame initialization and temporal refinement by Doersch, C, Yang, Y, Vecerik, M, Gokay, D, Gupta, A, Aytar, Y, Carreira, J, Zisserman, A

Visual grounding in video for unsupervised word translation by Sigurdsson, GA, Alayrac, JB, Nematzadeh, A, Smaira, L, Malinowski, M, Carreira, J, Blunsom, P, Zisserman, A