Adam R. Kosiorek
Adam R. Kosiorek
PhD in Information Engineering, University of Oxford
Verified email at - Homepage
Cited by
Cited by
Tighter variational bounds are not necessarily better
T Rainforth, AR Kosiorek, TA Le, CJ Maddison, M Igl, F Wood, YW Teh
International Conference on Machine Learning, 2018
Sequential attend, infer, repeat: Generative modelling of moving objects
A Kosiorek, H Kim, YW Teh, I Posner
Advances in Neural Information Processing Systems, 8606-8616, 2018
Set transformer: A framework for attention-based permutation-invariant neural networks
J Lee, Y Lee, J Kim, AR Kosiorek, S Choi, YW Teh
arXiv preprint arXiv:1810.00825, 2018
Hierarchical attentive recurrent tracking
A Kosiorek, A Bewley, I Posner
Advances in neural information processing systems, 3053-3061, 2017
Revisiting reweighted wake-sleep for models with stochastic control flow
TA Le, A Kosiorek, N Siddharth, YW Teh, F Wood
Association for Uncertainty in Artificial Intelligence, 2019
Stacked Capsule Autoencoders
AR Kosiorek, S Sabour, YW Teh, GE Hinton
Advances in Neural Information Processing Systems, 2019
Genesis: Generative scene inference and sampling with object-centric latent representations
M Engelcke, AR Kosiorek, OP Jones, I Posner
arXiv preprint arXiv:1907.13052, 2019
Guiding Physical Intuition with Neural Stethoscopes
F Fuchs, O Groth, A Kosiorek, A Bewley, M Wulfmeier, A Vedaldi, I Posner
Bayesian delay embeddings for dynamical systems
N Dhir, AR Kosiorek, I Posner
NIPS Timeseries Workshop, 2017
End-to-end Recurrent Multi-Object Tracking and Trajectory Prediction with Relational Reasoning
FB Fuchs, AR Kosiorek, L Sun, OP Jones, I Posner
arXiv preprint arXiv:1907.12887, 2019
MetaFun: Meta-Learning with Iterative Functional Updates
J Xu, JF Ton, H Kim, AR Kosiorek, YW Teh
arXiv preprint arXiv:1912.02738, 2019
Scrutinizing and de-biasing intuitive physics with neural stethoscopes
FB Fuchs, O Groth, AR Kosiorek, A Bewley, M Wulfmeier, A Vedaldi, ...
British Machine Vision Association, 2019
Klasyfikacja obiektów 3D na podstawie danych RGBD
A Kosiorek
Instytut Automatyki i Robotyki, 2014
An Efficient Event-Based Optical Flow Implementation in C/C++ and CUDA
A Kosiorek, D Adrian, J Rausch, J Conradt
The system can't perform the operation now. Try again later.
Articles 1–14