Publications and Output

  • Gupta, Ankush and Vedaldi, Andrea and Zisserman, Andrew.  Synthetic Data for Text Localisation in Natural Images The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) June 2016
  • Ghoshal, Sid and S. Roberts, Extracting Predictive Information from Heterogeneous Data Streams using Gaussian Processes, Algorithmic Finance, vol. 5, no. 1-2, pp. 21-30, 2016.
  • Leonard Hasenclever, Stefan Webb, Thibaut Lienart, Sebastian Vollmer, Balaji Lakshminarayanan, Charles Blundell, Yee Whye Teh, Distributed Bayesian Learning with Stochastic Natural-gradient Expectation Propagation and the Posterior Server. Journal of Machine Learning Research 18 (2017) 1-37.
  • Learning Grimaces by Watching TV”  – Sam Albanie and Andrea Vedaldi, accepted into BMVC 2016.
  • James Thewlis, Shuai Zheng, Philip H. S. Torr, Andrea Vedaldi.  Fully-Trainable Deep Matching. British  Machine Vision Conference (BMVC), 2016.
  • Bartlett, O, C. Gurau, L. Marchegiani, and I. Posner, “Enabling Intelligent Energy Management for Robots using Publicly Available Maps,” in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Daejeon, South Korea, 2016. PDF
  • Berrada, Leo, Trusting SVM for Piecewise Linear CNNs” has been accepted at ICLR 2017 (International Conference on Learning Representations). It is available on arXiv at https://arxiv.org/abs/1611.02185
  • Ghoshal, S and Roberts, S. Reading the Tea Leaves: A Neural Network Perspective on Technical Trading. Knowledge Discovery and Data Mining (KDD), 2017.
  • Cobb, A and Markham, A and Roberts, S. Learning from lions: inferring the utility of agents from their trajectories. Available at https://arxiv.org/pdf/1709.02357.pdf
  • Jakob Foerster, Nantas Nardelli, Gregory Farquhar, Triantafyllos Afouras, Philip H.S. Torr, Pushmeet Kohli, Shimon Whiteson, Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning.   Accepted at ICML2017. Available at https://arxiv.org/abs/1702.08887
  • Unsupervised object learning from dense invariant image labelling, J.Thewlis and H. Bilen and A. Vedaldi, Proceedings of Advances in Neural Information Processing Systems (NIPS), 2017 (oral presentation)
  • Unsupervised learning of object landmarks by factorized spatial embeddings, J. Thewlis and H. Bilen and A. Vedaldi, Proceedings of the International Conference on Computer Vision (ICCV), 2017 (oral presentation)
  • Zand, Jaleh & Roberts, S. MiDGaP: Mixture Density Gaussian Processes.  NIPS time series workshop 2017.
  • Closed-loop quantitative verification of rate-adaptive pacemakers. N Paoletti, A Patane, M Kwiatkowska. ACM Transactions on Cyber-Physical Systems, to appear, 2018
  • Stefan Webb and Yee Whye Teh. A Tighter Monte Carlo Objective with Renyi divergence Measures. NIPS2016 Workshop in Bayesian Deep Learning.
  • Stefan Webb, Adam Golinski, Robert Zinkov and Frank Wood. Faithful Model Inversion Substantially Improves Auto-encoding Variational Inference. NIPS2017 Workshop in Bayesian Deep Learning.
  • Foerster, J., Farquhar, G., Afouras, T., Nardelli, N., & Whiteson, S. (2018). Counterfactual multi-agent policy gradients. 32nd AAAI Conference on Artificial Intelligence (AAAI’18)
  • Farquhar, G., Rocktäschel, T., Igl, M., & Whiteson, S.  TreeQN and ATreeC: Differentiable Tree Planning for Deep Reinforcement Learning. ICLR 2018. (To appear)
  • Border, R. D. Gammell, and P. Newman, “Surface Edge Explorer (SEE): Planning Next Best Views Directly from 3D Observations,” ICRA, 2018.
  •  Le, Tuan Anh, Igl, Maximilian, Jin, Tom, Rainforth, Tom, Wood, Frank. Auto-encoding sequential Monte Carlo. In ICLR (To Appear), 2018.
  • D. Novotny*, S. Albanie*, D. Larlus, A. Vedaldi, Self-supervised Learning of Geometrically Stable Features Through Probabilistic Introspection, CVPR, 2018. (* denotes equal contribution)
  • A. Nagrani, S. Albanie, A. Zisserman, Seeing Voices and Hearing Faces: Cross-modal biometric matching, CVPR, 2018.  (* denotes equal contribution)
  • S. Albanie, H. Shakespeare and T. Gunter, Unknowable Manipulators: Social Network Curator Algorithms, (NIPS 2016 Symposium: Machine Learning and the Law)
  • Cornish, R., Wood, F., & Yang, H. (2017). “Towards a testable notion of generalisation for generative adversarial networks”. In NIPS Workshop on Deep Learning: Bridging Theory and Practice.
  • Baydin, A. G., Cornish, R., Martínez Rubio, D., Schmidt, M., & Wood, F. (2017).  Online Learning Rate Adaptation with Hypergradient Descent.  In Sixth International Conference on Learning Representations (ICLR), Vancouver, Canada, April 30 – May 3, 2018.
  • Adam D. Cobb, Richard Everett, Andrew Markham, Stephen J. Roberts. (2018). Identifying Sources and Sinks in the Presence of Multiple Gaents with Gaussian Process Vector Calculus, https://arxiv.org/abs/1802.10446
  • When Your Fitness Tracker Betrays You: Quantifying the Predictability of Biometric Features Across Contexts. Simon Eberz, Giulio Lovisotto, Andrea Patané, Marta Kwiatkowska, Vincent Lenders, and Ivan Martinovic. IEEE Symposium on Security and Privacy (S&P), San Francisco, CA, USA, May 2018
  • CommonSense: Collaborative learning of scene semantics by robots and humans. Stefano Rosa, Andrea Patanè, Xiaoxuan Lu, and Niki Trigoni. In Proceedings of the 1st International Workshop on Internet of People, Assistive Robots and ThingS (pp. 1-6). ACM. 2018, June.
  • Loss-Calibrated Approximate Inference in Bayesian Neural Betworks. Adam D. Cobb, Stephen J. Roberts, Yarin Gal.  https://arxiv.org/abs/1805.03901
  • T. Afouras, J. S. Chung, A. Zisserman. Deep Lip Reading: a comparison of models and an online application  INTERSPEECH, 2018
  • T. Afouras, J. S. Chung, A. Zisserman. The Conversation: Deep Audio-Visual Speech Enhancement  INTERSPEECH, 2018
  • L. Berrada, A. Zisserman, M. P. Kumar. Smooth Loss Functions for Deep Top-k Classification  International Conference on Learning Representations, 2018
  • A. Nagrani*, S. Albanie*, and A. Zisserman, Learnable PINs: Cross-Modal Embeddings for Person Identity, ECCV 2018
  • D. Novotny*, S. Albanie*, D. Larlus, A. Vedaldi, Semi-convolutional operators for instance segmentation, ECCV 2018
  • Rainforth, T., Cornish, R., Yang, H., Warrington, A., & Wood, F. (2018). On Nesting Monte Carlo Estimators. International Conference on Machine Learning (ICML)
  • Tim G. J. Rudner and Dino Sejdinovic. Inter-domain Deep Gaussian Processes. Bayesian Deep Learning NIPS Workshop, 2017
  • Ghoshal, S. and Roberts, S. Thresholded ConvNet Ensembles: Neural Networks for Technical Forecasting. Data Science in Fintech, KDD 2018
  • Smith, Lewis and Gal, Yarin. Understanding Measures of Uncertainty for Adversarial Example Detection. UAI 2018
  • Gupta, Ankush, Vedaldi, Andrea and Zisserman, Andrew, Inductive Visual Localisation: Factorised Training for Superior Generalisation. Proceedings of the British Machine Vision Conference (BMVC), 2018
  • Golinski, Adam, Teh, Yee Whye, Wood Frank and Rainforth, Tom, Amortized Monte Carlo Integration, UAI 2018 Workshop on Uncertainity in Deep Learning
  • Ivan Kiskin, Davide Zilli, Yunpeng Li, Marianne Sinka, Kathy Willis, Stephen Roberts, Bioacoustic detection with wavelet-conditioned convolutional neural networksSpringer, Neural Computing and Applications
  • Oliver Groth, Fabian B. Fuchs, Ingmar Posner, Andrea Vedaldi, ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking ECCV 2018
  • Benjamin Moseley, Andrew Markham, Tarje Nissen-Meyer, Fast approximate simulation of seismic waves with deep learning
  • M. Igl, L. Zintgraf, TA. Le, F. Wood and S. Whiteson. Deep variational reinforcement learning for POMDPs, ICML 2018
  • Tom Rainforth, Adam R. Kosiorek, Tuan Anh Le, Chris J Maddision, Maximilian Igl, Frank Wood and Yee Whye Teh. Tighter variational bounds are not necessarily better. International Conference on Machine Learning (ICML), 2018
  • Tomas Jakab*, Ankush Gupta*, Hakan Bilen, Andrea Vedaldi. Conditional Image Generation for Learning the Structure of Visual. NIPS2018 (* indicates equal contribution)
  • James Thewlis, Hakan Bilen and Andea Vedaldi. Modelling and unsupervised of symmetric deformable object categories.  NIPS2018
  • Stefan Webb, Adam Golinski, Robert Zinkov, N. Siddharth, Tom Rainforth, Yee Whye Teh and Frank Wood. Faithdul Inversion of Generative Models for Effective Amortized Inference. NIPS2018
  • Aravindh Mahendran, James Thewlis, Andrea Vedaldi. Cross Pixel Optical Flow Similarity for Self-Supervised Learning. ACCV 2018
  • Aravindh Mahendran, James Thewlis, Andrea Vedaldi. Self-Supervised Segmentation by Grouping Optical-Flow. POCV Workshop on Action, Perception and Organization, ECCV 2018 Workshops
  • Learning to Read by Spelling: Towards Unsupervised Text Recognition Ankush Gupta, Andrea Vedaldi, Andrew Zisserman arXiv preprint arXiv:1809.08675 2018
  • Robustness Guarantees for Bayesian Inference with Gaussian Processes.  L Cardelli, M Kwiatkowska, L Laurenti, A Patane, arXiv preprint arXiv:1809.06452 Link: https://arxiv.org/pdf/1809.06452.pdf 
  • Calibrating the Classifier: Siamese Neural Network Architecture for End-to-End Arousal Recognition from ECG. A Patane, M Kwiatkowska. The Fourth International Conference on Machine Learning, Optimization, and Data Science. 2018 Link: http://qav.comlab.ox.ac.uk/papers/pk18.pdf 
  • Automated Recognition of Sleep Arousal using Multimodal and Personalized Deep Ensembles of Neural Networks. A Patane, S Ghiasi, E P Scilingo, M Kwiatkowska. Computing in Cardiology 2018
  • Jack Hunt, Victor A. Prisacariu, Stuart Golodetz, Tommaso Cavallari, Nicholas A. Lord and Philip H. S. Torr. Probabilistic Object Reconstruction with Online Global Model Correction. Proceedings of the 5th International Conference on 3D Vision (3DV) 2017.
  • Fabian B. Fuchs, Oliver Groth, Adam R. Kosiorek, Alex Bewley, Markus Wulfmeier, Andrea Vedaldi, Ingmar Posner. Neural Stethoscopes: Unifying Analytic, Auxiliary and Adversarial Network Probing. https://arxiv.org/abs/1806.05502
  • Kyriacos Shiarlis, Markus Wulfmeier, Sasha Salter, Shimon Whiteson, Ingmar Posner. TACO: Learning Task Decomposition via Temporal Alignment for Control. https://arxiv.org/abs/1803.01840 
  • Oliver E Bent, Sekou L Remy, Nelson K Bore. A machine learning environment to determine novel malaria policies. NIPS Demonstration 2018
  • Kevin M. Judd, Jonathan D. Gammell and Paul Newman, Multimotion Visual Odometry (MVO): Simultaneous Estimation of Camera and Third-Party Motions. IROS2018
  • Maximilian Igl, Wendelin Boehmer, Andrew Gambardella, Nantas Nardelli, Siddharth Narayanaswamy and Shimon Whiteson.  Bayesian hierarchical multitask learning. NIPS workshop 2018