Mandela Patrick

15 papers A* 6Journal 7Unranked 1

Year	Rank	Type	Title / Venue / Authors
2021	A*	`conf`	Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers. NeurIPS Mandela Patrick, Dylan Campbell, Yuki M. Asano, Ishan Misra, Florian Metze, Christoph Feichtenhofer, Andrea Vedaldi, João F. Henriques
2021	J	`jnl`	Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers. CoRR Mandela Patrick, Dylan Campbell, Yuki Markus Asano, Ishan Misra, Florian Metze, Christoph Feichtenhofer, Andrea Vedaldi, João F. Henriques
2021	—	`—`	Learning and interpreting deep representations from multi-modal data Mandela Patrick
2021	—	`conf`	Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models. NAACL-HLT Poyao Huang, Mandela Patrick, Junjie Hu, Graham Neubig, Florian Metze, Alex Hauptmann
2021	J	`jnl`	Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models. CoRR Po-Yao Huang, Mandela Patrick, Junjie Hu, Graham Neubig, Florian Metze, Alexander G. Hauptmann
2021	A*	`conf`	On Compositions of Transformations in Contrastive Self-Supervised Learning. ICCV Mandela Patrick, Yuki Markus Asano, Polina Kuznetsova, Ruth Fong, João F. Henriques, Geoffrey Zweig, Andrea Vedaldi
2021	A*	`conf`	Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning. ICCV Mandela Patrick, Po-Yao Huang, Ishan Misra, Florian Metze, Andrea Vedaldi, Yuki M. Asano, João F. Henriques
2021	J	`jnl`	Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning. CoRR Mandela Patrick, Yuki Markus Asano, Bernie Huang, Ishan Misra, Florian Metze, João F. Henriques, Andrea Vedaldi
2021	A*	`conf`	Support-set bottlenecks for video-text representation learning. ICLR Mandela Patrick, Po-Yao Huang, Yuki Markus Asano, Florian Metze, Alexander G. Hauptmann, João F. Henriques, Andrea Vedaldi
2020	A*	`conf`	Labelling unlabelled videos from scratch with multi-modal self-supervision. NeurIPS Yuki Markus Asano, Mandela Patrick, Christian Rupprecht, Andrea Vedaldi
2020	J	`jnl`	Labelling unlabelled videos from scratch with multi-modal self-supervision. CoRR Yuki Markus Asano, Mandela Patrick, Christian Rupprecht, Andrea Vedaldi
2020	J	`jnl`	Multi-modal Self-Supervision from Generalized Data Transformations. CoRR Mandela Patrick, Yuki Markus Asano, Ruth Fong, João F. Henriques, Geoffrey Zweig, Andrea Vedaldi
2020	J	`jnl`	Support-set bottlenecks for video-text representation learning. CoRR Mandela Patrick, Po-Yao Huang, Yuki Markus Asano, Florian Metze, Alexander G. Hauptmann, João F. Henriques, Andrea Vedaldi
2019	A*	`conf`	Understanding Deep Networks via Extremal Perturbations and Smooth Masks. ICCV Ruth Fong, Mandela Patrick, Andrea Vedaldi
2019	J	`jnl`	Understanding Deep Networks via Extremal Perturbations and Smooth Masks. CoRR Ruth Fong, Mandela Patrick, Andrea Vedaldi