Mandela Patrick

Publication Activity (10 Years)

Years Active: 2019-2021
Publications (10 Years): 14

Top Topics

Video Representation

Multiple Modalities

Text Representation

Point Trajectories

Top Venues

Publications

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