1 code implementation • 8 Dec 2023 • Daniel Rodriguez-Criado, Maria Chli, Luis J. Manso, George Vogiatzis
This paper introduces a novel methodology for bridging this `sim-real' gap by creating photorealistic images from 2D traffic simulations and recorded junction footage.
1 code implementation • ICCV 2023 • Kieran Saunders, George Vogiatzis, Luis Manso
For these architectures to be effective in real-world applications, we must create models that can generalise to all weather conditions, times of the day and image qualities.
Ranked #2 on Unsupervised Monocular Depth Estimation on KITTI-C (using extra training data)
1 code implementation • 16 Dec 2022 • Daniel Rodriguez-Criado, Pilar Bachiller, George Vogiatzis, Luis J. Manso
Its numerous applications make multi-human 3D pose estimation a remarkably impactful area of research.
1 code implementation • 8 Jun 2022 • Kieran Saunders, George Vogiatzis, Luis J. Manso
Much of the recent work focuses on improving depth estimation by increasing architecture complexity.
1 code implementation • 28 Jul 2020 • Daniel Rodriguez-Criado, Pilar Bachiller, Pablo Bustos, George Vogiatzis, Luis J. Manso
The proposal presented in this paper makes use of graph neural networks to merge the information acquired from multiple camera sources, achieving a mean absolute error below 125 mm for the location and 10 degrees for the orientation using low-resolution RGB images.
no code implementations • 11 Jul 2020 • Jordan J. Bird, Diego R. Faria, Cristiano Premebida, Anikó Ekárt, George Vogiatzis
The image and the audio datasets are first classified independently, using a fine-tuned VGG16 and an evolutionary optimised deep neural network, with accuracies of 89. 27% and 93. 72%, respectively.
no code implementations • 18 Dec 2018 • Thomas Carr, Maria Chli, George Vogiatzis
Deep reinforcement learning agents have recently been successful across a variety of discrete and continuous control tasks; however, they can be slow to train and require a large number of interactions with the environment to learn a suitable policy.
no code implementations • 23 Oct 2018 • Noa Garcia, George Vogiatzis
Automatic art analysis has been mostly focused on classifying artworks into different artistic styles.
no code implementations • 19 Oct 2017 • Noa Garcia, George Vogiatzis
This work proposes a system for retrieving clothing and fashion products from video content.
no code implementations • ICLR 2018 • Noa Garcia, George Vogiatzis
Theoretically, non-metric distances are able to generate a more complex and accurate similarity model than metric distances, provided that the non-linear data distribution is precisely captured by the system.
no code implementations • CVPR 2014 • Rasmus Jensen, Anders Dahl, George Vogiatzis, Engin Tola, Henrik Aanaes
The seminal multiple view stereo benchmark evaluations from Middlebury and by Strecha et al. have played a major role in propelling the development of multi-view stereopsis methodology.