Carl Doersch
Carl Doersch
Research Scientist, DeepMind
Verified email at google.com - Homepage
TitleCited byYear
Unsupervised visual representation learning by context prediction
C Doersch, A Gupta, AA Efros
Proceedings of the IEEE International Conference on Computer Vision, 1422-1430, 2015
5042015
Tutorial on Variational Autoencoders
C Doersch
arXiv preprint arXiv:1606.05908, 2016
4962016
What makes Paris look like Paris?
C Doersch, S Singh, A Gupta, J Sivic, AA Efros
ACM Transactions on Graphics (SIGGRAPH) 31 (4), 101, 2012
4732012
An Uncertain Future: Forecasting from Static Images Using Variational Autoencoders
J Walker, C Doersch, A Gupta, M Hebert
European Conference on Computer Vision, 835-851, 2016
2722016
Mid-level Visual Element Discovery as Discriminative Mode Seeking
C Doersch, A Gupta, AA Efros
Advances in Neural Information Processing Systems, 494-502, 2013
2592013
Multi-task self-supervised visual learning
C Doersch, A Zisserman
Proceedings of the IEEE International Conference on Computer Vision, 2051-2060, 2017
1422017
Data-dependent Initializations of Convolutional Neural Networks
P Krähenbühl, C Doersch, J Donahue, T Darrell
arXiv preprint arXiv:1511.06856, 2015
1262015
What makes Paris look like Paris?
C Doersch, S Singh, A Gupta, J Sivic, AA Efros
Communications of the ACM 58 (12), 103-110, 2015
322015
Kickstarting Deep Reinforcement Learning
S Schmitt, JJ Hudson, A Zidek, S Osindero, C Doersch, WM Czarnecki, ...
arXiv preprint arXiv:1803.03835, 2018
302018
Improving state-of-the-art OCR through high-precision document-specific modeling
A Kae, G Huang, C Doersch, E Learned-Miller
2010 IEEE Computer Society Conference on Computer Vision and Pattern …, 2010
282010
Context as supervisory signal: Discovering objects with predictable context
C Doersch, A Gupta, AA Efros
European Conference on Computer Vision, 362-377, 2014
262014
Video action transformer network
R Girdhar, J Carreira, C Doersch, A Zisserman
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2019
252019
Learning visual question answering by bootstrapping hard attention
M Malinowski, C Doersch, A Santoro, P Battaglia
Proceedings of the European Conference on Computer Vision (ECCV), 3-20, 2018
242018
Data-Efficient Image Recognition with Contrastive Predictive Coding
OJ Hénaff, A Razavi, C Doersch, SM Eslami, A Oord
arXiv preprint arXiv:1905.09272, 2019
202019
A Better Baseline for AVA
R Girdhar, J Carreira, C Doersch, A Zisserman
arXiv preprint arXiv:1807.10066, 2018
132018
Mid-level Elements for Object Detection
A Bansal, A Shrivastava, C Doersch, A Gupta
arXiv preprint arXiv:1504.07284, 2015
112015
Exploiting temporal context for 3D human pose estimation in the wild
A Arnab, C Doersch, A Zisserman
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2019
82019
The Visual QA Devil in the Details: The Impact of Early Fusion and Batch Norm on CLEVR
M Malinowski, C Doersch
arXiv preprint arXiv:1809.04482, 2018
62018
Bounding the probability of error for high precision optical character recognition
GB Huang, A Kae, C Doersch, E Learned-Miller
Journal of Machine Learning Research 13 (Feb), 363-387, 2012
52012
Structured agents for physical construction
V Bapst, A Sanchez-Gonzalez, C Doersch, KL Stachenfeld, P Kohli, ...
arXiv preprint arXiv:1904.03177, 2019
42019
The system can't perform the operation now. Try again later.
Articles 1–20