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 | 436 | 2019 |
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 | 262 | 2020 |
Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers M Patrick, D Campbell, YM Asano, IMF Metze, C Feichtenhofer, A Vedaldi, ... Advances in Neural Information Processing Systems, 2021 | 241 | 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 | 232* | 2021 |
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 | 163 | 2020 |
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 | 58 | 2021 |
Space-time crop & attend: Improving cross-modal video representation learning M Patrick, PY Huang, I Misra, F Metze, A Vedaldi, YM Asano, ... Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021 | 38 | 2021 |
Learning and interpreting deep representations from multi-modal data M Patrick University of Oxford, 2021 | | 2021 |