1 code implementation • ICML 2020 • Jiri Fajtl, Vasileios Argyriou, Dorothy Monekosso, Paolo Remagnino
In this work, we pose a question whether it is possible to design and train an autoencoder model in an end-to-end fashion to learn latent representations in multivariate Bernoulli space, and achieve performance comparable with the current state-of-the-art variational methods.
no code implementations • 17 Jun 2019 • Mahdi Maktabdar Oghaz, Anish R. Khadka, Vasileios Argyriou, Paolo Remagnino
Precise knowledge about the size of a crowd, its density and flow can provide valuable information for safety and security applications, event planning, architectural design and to analyze consumer behavior.
no code implementations • 6 Jun 2019 • Antoine Rimboux, Rob Dupre, Thomas Lagkas, Panagiotis Sarigiannidis, Paolo Remagnino, Vasileios Argyriou
In order to provide related behavioural models, simulation and tracking approaches have been considered in the literature.
no code implementations • 6 Jun 2019 • Mahdi Maktabdar Oghaz, Manzoor Razaak, Hamideh Kerdegari, Vasileios Argyriou, Paolo Remagnino
In this paper, a review of studies applying deep learning on UAV imagery for smart farming is presented.
no code implementations • 24 May 2019 • Hamideh Kerdegari, Manzoor Razaak, Vasileios Argyriou, Paolo Remagnino
The results by the proposed semi-supervised GAN achieves high classification accuracy and demonstrates the potential of GAN-based methods for the challenging task of multispectral image classification.
no code implementations • 9 Dec 2018 • Chloe Eunhyang Kim, Mahdi Maktab Dar Oghaz, Jiri Fajtl, Vasileios Argyriou, Paolo Remagnino
Recent advancements in parallel computing, GPU technology and deep learning provide a new platform for complex image processing tasks such as person detection to flourish.
4 code implementations • 5 Dec 2018 • Jiri Fajtl, Hajar Sadeghi Sokeh, Vasileios Argyriou, Dorothy Monekosso, Paolo Remagnino
In this work we propose a novel method for supervised, keyshots based video summarization by applying a conceptually simple and computationally efficient soft, self-attention mechanism.
Ranked #3 on Video Summarization on TvSum (using extra training data)
no code implementations • 6 Nov 2018 • Anish R. Khadka, Paolo Remagnino, Vasileios Argyriou
Our suggested approach is to recover scene properties in the presence of indirect illumination.
no code implementations • 18 Apr 2018 • Hajar Sadeghi Sokeh, Vasileios Argyriou, Dorothy Monekosso, Paolo Remagnino
The goal of video segmentation is to turn video data into a set of concrete motion clusters that can be easily interpreted as building blocks of the video.
1 code implementation • CVPR 2018 • Jiri Fajtl, Vasileios Argyriou, Dorothy Monekosso, Paolo Remagnino
Further on we study the impact of the attention mechanism on the memorability estimation and evaluate our network on the SUN Memorability and the LaMem datasets.
1 code implementation • 28 Jun 2015 • Sue Han Lee, Chee Seng Chan, Paul Wilkin, Paolo Remagnino
This paper studies convolutional neural networks (CNN) to learn unsupervised feature representations for 44 different plant species, collected at the Royal Botanic Gardens, Kew, England.
no code implementations • 15 Oct 2014 • Mei Kuan Lim, Chee Seng Chan, Dorothy Monekosso, Paolo Remagnino
The increasing number of cameras and a handful of human operators to monitor the video inputs from hundreds of cameras leave the system ill equipped to fulfil the task of detecting anomalies.
no code implementations • 14 Oct 2014 • Mei Kuan Lim, Chee Seng Chan, Dorothy Monekosso, Paolo Remagnino
Conventional tracking solutions are not feasible in handling abrupt motion as they are based on smooth motion assumption or an accurate motion model.