Mandela Patrick
Mandela Patrick
Verified email at robots.ox.ac.uk
Title
Cited by
Cited by
Year
Understanding deep networks via extremal perturbations and smooth masks
R Fong, M Patrick, A Vedaldi
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2019
1322019
Multi-modal self-supervision from generalized data transformations
M Patrick, YM Asano, P Kuznetsova, R Fong, JF Henriques, G Zweig, ...
arXiv preprint arXiv:2003.04298, 2020
582020
Labelling unlabelled videos from scratch with multi-modal self-supervision
YM Asano, M Patrick, C Rupprecht, A Vedaldi
Advances in Neural Information Processing Systems 33, 4660--4671, 2020
252020
Support-set bottlenecks for video-text representation learning
M Patrick, PY Huang, Y Asano, F Metze, A Hauptmann, J Henriques, ...
International Conference of Learning Representations 2021, 2020
232020
Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models
PY Huang, M Patrick, J Hu, G Neubig, F Metze, A Hauptmann
Proceedings of the 2021 Conference of the North American Chapter of the …, 2021
62021
Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers
M Patrick, D Campbell, YM Asano, IMF Metze, C Feichtenhofer, A Vedaldi, ...
arXiv preprint arXiv:2106.05392, 2021
22021
Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning
M Patrick, YM Asano, B Huang, I Misra, F Metze, J Henriques, A Vedaldi
arXiv preprint arXiv:2103.10211, 2021
2021
On Compositions of Transformations in Contrastive Self-Supervised Learning
M Patrick, YM Asano, P Kuznetsova, R Fong, JF Henriques, G Zweig, ...
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021
2021
Learning and interpreting deep representations from multi-modal data
M Patrick
University of Oxford, 2021
2021
SELAVI: SELF-LABELLING VIDEOS WITHOUT ANY AN-NOTATIONS FROM SCRATCH
YM Asano, M Patrick, C Rupprecht, A Vedaldi
The system can't perform the operation now. Try again later.
Articles 1–10