no code implementations • 29 Oct 2023 • Tianhao Zhang, Shenglin Wang, Nidhal Bouaynaya, Radu Calinescu, Lyudmila Mihaylova
The superior performance of object detectors is often established under the condition that the test samples are in the same distribution as the training data.
no code implementations • 10 Nov 2021 • Giuseppina Carannante, Dimah Dera, Ghulam Rasool, Nidhal C. Bouaynaya, Lyudmila Mihaylova
Learning in uncertain, noisy, or adversarial environments is a challenging task for deep neural networks (DNNs).
1 code implementation • 3 Mar 2021 • Youngjoo Kim, Peng Wang, Lyudmila Mihaylova
With the real traffic speed data measured in the city of Santander, we demonstrate the proposed SRNN outperforms the image-based approaches using the capsule network (CapsNet) by 14. 1% and the convolutional neural network (CNN) by 5. 87%, respectively, in terms of root mean squared error (RMSE).
no code implementations • 2 Nov 2019 • Komlan Atitey, Pavel Loskot, Lyudmila Mihaylova
Estimating hidden processes from non-linear noisy observations is particularly difficult when the parameters of these processes are not known.
1 code implementation • 18 Feb 2019 • Youngjoo Kim, Peng Wang, Lyudmila Mihaylova
We use a graph of a vehicular road network with recurrent neural networks (RNNs) to infer the interaction between adjacent road segments as well as the temporal dynamics.
no code implementations • 29 Nov 2018 • Danil Kuzin, Olga Isupova, Lyudmila Mihaylova
A novel method to propagate uncertainty through the soft-thresholding nonlinearity is proposed in this paper.
1 code implementation • 23 Jul 2018 • Youngjoo Kim, Peng Wang, Yifei Zhu, Lyudmila Mihaylova
Traffic flow data from induction loop sensors are essentially a time series, which is also spatially related to traffic in different road segments.
no code implementations • 15 Jul 2018 • Danil Kuzin, Olga Isupova, Lyudmila Mihaylova
This paper introduces a new sparse spatio-temporal structured Gaussian process regression framework for online and offline Bayesian inference.
no code implementations • 9 Jul 2018 • Danil Kuzin, Le Yang, Olga Isupova, Lyudmila Mihaylova
The ensemble Kalman filter reduces the computational complexity required to obtain predictions with Gaussian processes preserving the accuracy level of these predictions.
no code implementations • 27 Apr 2017 • Danil Kuzin, Olga Isupova, Lyudmila Mihaylova
Video analytics requires operating with large amounts of data.
no code implementations • 27 Apr 2017 • Danil Kuzin, Olga Isupova, Lyudmila Mihaylova
In this paper a new Bayesian model for sparse linear regression with a spatio-temporal structure is proposed.
no code implementations • 2 Nov 2016 • Olga Isupova, Danil Kuzin, Lyudmila Mihaylova
Semi-supervised and unsupervised systems provide operators with invaluable support and can tremendously reduce the operators load.
1 code implementation • 27 Jun 2016 • Olga Isupova, Danil Kuzin, Lyudmila Mihaylova
The proposed method is compared with the method based on the non- dynamic Hierarchical Dirichlet Process, for which we also derive the online Gibbs sampler and the abnormality measure.
no code implementations • 27 Jun 2016 • Olga Isupova, Danil Kuzin, Lyudmila Mihaylova
A novel dynamic Bayesian nonparametric topic model for anomaly detection in video is proposed in this paper.
no code implementations • 5 Nov 2015 • Ata-ur-Rehman, Syed Mohsen Naqvi, Lyudmila Mihaylova, Jonathon Chambers
This paper considers the problem of multiple human target tracking in a sequence of video data.
no code implementations • 21 Sep 2015 • Matthew Hawes, Lyudmila Mihaylova, Francois Septier, Simon Godsill
A BCSKF can then be used to track the change in the DOA using the same framework.
no code implementations • 4 Jun 2013 • Christopher Nemeth, Paul Fearnhead, Lyudmila Mihaylova
This paper introduces an alternative approach for estimating these terms at a computational cost that is linear in the number of particles.