Joan Serrat
Polytechnic University of Catalonia
Publications 196
#1Matias Richart (University of the Republic)H-Index: 3
#2Javier Baliosian (University of the Republic)H-Index: 9
Last.Ramón Agüero (UC: University of Cantabria)H-Index: 17
view all 5 authors...
Network slicing is one of the key enabling technologies for 5G networks. It allows infrastructure owners to assign resources to service providers (tenants), which will afterwards use them to satisfy their end-user demands. This paradigm, which changes the way networks have been traditionally managed, was initially proposed in the wired realm (core networks). More recently, the scientific community has paid attention to the integration of network slicing in wireless cellular technologies (LTE). H...
2 CitationsSource
#1Javier Rubio-Loyola (CINVESTAV)H-Index: 11
#2Christian Aguilar-Fuster (CINVESTAV)H-Index: 2
Last.Joan SerratH-Index: 27
view all 6 authors...
The cell assignment problem is combinatorial, with increased complexity when it is tackled considering resource allocation. This paper models joint cell assignment and resource allocation for cellular heterogeneous networks, and formalizes cell assignment as an optimization problem. Exact algorithms can find optimal solutions to the cell assignment problem, but their execution time increases drastically with realistic network deployments. In turn, heuristics are able to find solutions in reasona...
1 CitationsSource
Apr 1, 2019 in WCNC (Wireless Communications and Networking Conference)
#1Matias Richart (UPC: Polytechnic University of Catalonia)
#2Javier Baliosian (University of the Republic)H-Index: 9
Last.Ramón Agüero (UC: University of Cantabria)H-Index: 17
view all 5 authors...
In forthcoming 5G networks, slicing has been proposed as a means to partition a shared physical network infrastructure into different self-contained logical parts (slices), which are set up to satisfy certain requirements. Although the topic has been thoroughly investigated by the scientific community and the industry, there are not many works addressing the challenges that appear when trying to exploit slicing techniques over WiFi networks. In this paper, we propose a novel method of allocating...
In this work we contribute a novel pipeline to automatically generate training data, and to improve over state-of-the-art multi-object tracking and segmentation (MOTS) methods. Our proposed tracklet mining algorithm turns raw street-level videos into high-fidelity MOTS training data, is scalable and overcomes the need of expensive and time-consuming manual annotation approaches. We leverage state-of-the-art instance segmentation results in combination with optical flow obtained from models also ...
#1Joan Serrat (Autonomous University of Barcelona)H-Index: 27
#2Felipe Lumbreras (Autonomous University of Barcelona)H-Index: 14
Last.Idoia Ruiz (Autonomous University of Barcelona)H-Index: 2
view all 3 authors...
Abstract Clothing is still manually manufactured for the most part nowadays, resulting in discrepancies between nominal and real dimensions, and potentially ill-fitting garments. Hence, it is common in the apparel industry to manually perform measures at preshipment time. We present an automatic method to obtain such measures from a single image of a garment that speeds up this task. It is generic and extensible in the sense that it does not depend explicitly on the garment shape or type. Instea...
When neural networks process images which do not resemble the distribution seen during training, so called out-of-distribution images, they often make wrong predictions, and do so too confidently. The capability to detect out-of-distribution images is therefore crucial for many real-world applications. We divide out-of-distribution detection between novelty detection ---images of classes which are not in the training set but are related to those---, and anomaly detection ---images with classes w...
5 Citations
#1Carme Julià (URV: Rovira i Virgili University)H-Index: 7
#2Joan Serrat (UPC: Polytechnic University of Catalonia)H-Index: 27
Last.T. Graf (VW: Volkswagen)H-Index: 5
view all 6 authors...
Intelligent vehicles are those equipped with sensors and information control systems that can assist human driving. In this context, we address the problem of detecting vehicles at night. The aim is to distinguish vehicles from lamp posts and traffic sign reflections by grouping the blob trajectories according to their apparent motion. We have adapted two factorization techniques, originally designed to estimate the scene structure from motion: the Costeira–Kanade and the Han–Kanade, named after...
3 Citations
#1Jeroen van der Hooft (UGent: Ghent University)H-Index: 5
#2Maxim Claeys (University of Antwerp)H-Index: 11
Last.Filip De Turck (UGent: Ghent University)H-Index: 35
view all 12 authors...
Network and service management is an established research field within the general area of computer networks. A few years ago, an initial taxonomy, organizing a comprehensive list of terms and topics, was established through interviews with experts from both industry and academia. This taxonomy has since been used to better partition standardization efforts, identify classes of managed objects and improve the assignment of reviewers to papers submitted in the field. Because the field of network ...
1 CitationsSource
#1Felipe S. Dantas Silva (UFRN: Federal University of Rio Grande do Norte)H-Index: 4
#2Marcilio O. O. Lemos (UFRN: Federal University of Rio Grande do Norte)H-Index: 1
Last.Panagiotis Papadimitriou (UoM: University of Macedonia)H-Index: 15
view all 17 authors...
The Novel Enablers for Cloud Slicing (NECOS) project addresses the limitations of current cloud computing infrastructures to respond to the demand for new services, as presented in two use-cases, that will drive the whole execution of the project. The first use-case is focused on Telco service provider and is oriented towards the adoption of cloud computing in their large networks. The second use-case is targeting the use of edge clouds to support devices with low computation and storage capacit...
4 CitationsSource
#2Joan Serrat (UPC: Polytechnic University of Catalonia)H-Index: 27
Last.Juan-Luis Gorricho (UPC: Polytechnic University of Catalonia)H-Index: 12
view all 3 authors...