Home   Projects   CV   Misc    

CrossTransformers: spatially-aware few-shot transfer

Carl Doersch, Ankush Gupta, Andrew Zisserman submitted to NeurIPS 2020 [arXiv]

Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning

Jean-Bastien Grill, Florian Strub, Florent Altché, Corentin Tallec, Pierre H. Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila Pires, Zhaohan Daniel Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Koray Kavukcuoglu, Rémi Munos, Michal Valko submitted to NeurIPS 2020 [arXiv]

Data-Efficient Image Recognition with Contrastive Predictive Coding

Olivier J. Hénaff, Aravind Srinivas, Jeffrey De Fauw, Ali Razavi, Carl Doersch, S. M. Ali Eslami, Aaron van den Oord in ICML 2020 [arXiv]

Sim2real transfer learning for 3D human pose estimation: motion to the rescue

Carl Doersch, Andrew Zisserman in NeurIPS 2019 [arXiv]

Exploiting temporal context for 3D human pose estimation in the wild

Anurag Arnab, Carl Doersch in CVPR 2019 [arXiv]

Video Action Transformer Network

Rohit Girdhar, João Carreira, Carl Doersch, Andrew Zisserman in CVPR 2019 [arXiv]

A Better Baseline for AVA

Rohit Girdhar, João Carreira, Carl Doersch, Andrew Zisserman in CVPR 2018 ActivityNet Workshop [arXiv]

Kickstarting Deep Reinforcement Learning

Simon Schmitt, Jony Hudson, Augustin Zidek, Simon Osindero, Carl Doersch, Wojciech Czarnecki, Joel Leibo, Heinrich Kuttler, Andrew Zisserman, Karen Simonyan, Ali Eslami in NIPS 2018 Reinforcement Learning Workshop [arXiv]

Learning Visual Question Answering by Bootstrapping Hard Attention

Mateusz Malinowski, Carl Doersch, Adam Santoro, Peter Battaglia in ECCV 2018 [arXiv]

https://arxiv.org/abs/1809.04482

Mateusz Malinowski, Carl Doersch in ECCV 2018 Workshop on Shortcomings in Vision and Language [arXiv]

Multi-task Self-Supervised Visual Learning

Carl Doersch and Andrew Zisserman in ICCV 2017 [arXiv] [Show BibTex]

Supervision Beyond Manual Annotations for Learning Visual Representations

Carl Doersch.
Carnegie Mellon Thesis Dissertation [pdf] [Show BibTex]

Tutorial on Variational Autoencoders

Carl Doersch.
Arxiv Tech Report, June 2016 [arXiv] [Show BibTex]

An Uncertain Future: Forecasting from Static Images using Variational Autoencoders

Jacob Walker, Carl Doersch, Abhinav Gupta, and Martial Hebert.
in ECCV 2016 [webpage] [arXiv] [Show BibTex]

Data-dependent Initializations of Convolutional Neural Networks

Philipp Krähenbühl, Carl Doersch, Jeff Donahue, and Trevor Darrell.
ICLR, 2016 [arxiv]

Unsupervised Visual Representation Learning by Context Prediction

Carl Doersch, Abhinav Gupta, and Alexei A. Efros.
in ICCV 2015 (oral) [webpage] [arXiv] [Show BibTex]

Context as Supervisory Signal: Discovering Objects with Predictable Context

Carl Doersch, Abhinav Gupta, and Alexei A. Efros.
In ECCV 2014 [Show BibTex]

Mid-Level Visual Element Discovery as Discriminative Mode Seeking

Carl Doersch, Abhinav Gupta, and Alexei A. Efros.
In NIPS 2013 [Show BibTex]

What Makes Paris Look like Paris?

Carl Doersch, Saurabh Singh, Abhinav Gupta, Josef Sivic, and Alexei A. Efros.
In SIGGRAPH 2012 (oral) Republished on the cover of the CACM magazine Dec. 2015 [Show BibTex]

Bounding the Probability of Error for High Precision Optical Character Recognition

Gary B. Huang, Andrew Kae, Carl Doersch, and Erik Learned-Miller.
In JMLR 2012 [pdf] [Show BibTex]

Improving state-of-the-art OCR through high-precision document-specific modeling.

Andrew Kae, Gary B. Huang, Carl Doersch, and Erik Learned-Miller.
In CVPR 2010 [pdf] [Show BibTex]