SciTePress - Affiliation Profile

Affiliation

Select a Subject
Refine Ontology Subject

Pompeu Fabra University, Spain

Context (please use complete words only)

Field

Sort by

44 Papers

An Enhanced Adversarial Network with Combined Latent Features for Spatio-temporal Facial Affect Estimation in the Wild

Topics: Image Enhancement and Restoration; Face and Expression Recognition; Visual Attention and Image Saliency; Human and Computer Interaction; Deep Learning for Visual Understanding

Authors: Decky Aspandi ^{1

;

2} , Federico Sukno ² , Björn Schuller ^{1

;

3} and Xavier Binefa ²

Affiliations: ¹ Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany , ² Department of Information and Communication Technologies, Pompeu Fabra University, Barcelona, Spain , ³ GLAM – Group on Language, Audio, & Music, Imperial College London, U.K.

Digital Object Identifier: 10.5220/0010332001720181

Proceedings of VISAPP 2021, ISBN: 978-989-758-488-6

Quick Abstract

Affective Computing has recently attracted the attention of the research community, due to its numerous applications in diverse areas. In this context, the emergence of video-based data allows to enrich the widely used spatial features with the inclusion of temporal information. However, such spatio-temporal modelling often results in very high-dimensional feature spaces and large volumes of data, making training difficult and time consuming. This paper addresses these shortcomings by proposing a novel model that efficiently extracts both spatial and temporal features of the data by means of its enhanced temporal modelling based on latent features. Our proposed model consists of three major networks, coined Generator, Discriminator, and Combiner, which are trained in an adversarial setting combined with curriculum learning to enable our adaptive attention modules. In our experiments, we show the effectiveness of our approach by reporting our competitive results on both the AFEW-VA and SEWA datasets, suggesting that temporal modelling improves the affect estimates both in qualitative and quantitative terms. Furthermore, we find that the inclusion of attention mechanisms leads to the highest accuracy improvements, as its weights seem to correlate well with the appearance of facial movements, both in terms of temporal localisation and intensity. Finally, we observe the sequence length of around 160 ms to be the optimum one for temporal modelling, which is consistent with other relevant findings utilising similar lengths.

Multi-agent Modeling Simulation of In-vitro T-cells for Immunologic Alternatives to Cancer Treatment

Topics: Multi-Agent Systems; Cooperation and Coordination; Simulation; Collective Intelligence

Authors: David Nettleton ¹ , Vladimir Estivill-Castro ² and Enrique Jiménez ³

Affiliations: ¹ Department of Information and Communications Technology (DTIC), Universitat Pompeu Fabra, Spain , ² Department of Information and Communications Technology (DTIC), Universitat Pompeu Fabra, Spain, School of ICT, Griffith University, Brisbane, Australia , ³ Institut d’Investigació Biomèdica de Bellvitge, Barcelona, Spain

Digital Object Identifier: 10.5220/0008915601690178

Proceedings of ICAART 2020, ISBN: 978-989-758-395-7

Quick Abstract

There is exciting news in recent developments suggesting the potential to treat some human cancers by stimulating the patients own immune system. However, there is still much to understand; therefore, modelling the battle between those cells that are constituents of the human immune system against tumorous cells can significantly provide insights as mathematical modelling has done regarding the immune system behaviour against virus infections. In this paper we innovate in two directions. First, we move the modelling of immune struggles from the sphere of ordinary-differential equation models to the modelling by multi-agent simulations. We highlight the advantages of the multi-agent simulation, for example the consideration of elaborate spatial proximity interactions. Secondly, we move away from the realm of infectious diseases to the complex modelling of the stimulation of T-cells and their participation in fighting cancerous cell tumours.

Iterated Local Search: Applications and Extensions

Author: Helena Ramalhinho Lourenço

Affiliation: Universitat Pompeu Fabra, Spain

Digital Object Identifier: 10.5220/0008345800070015

Proceedings of ICORES 2019, ISBN: 978-989-758-352-0

Quick Abstract

Iterated Local Search (ILS) is a conceptually simple and efficient well-known Metaheuristic. The main idea behind ILS is to drive the search not on the full space of all feasible solutions but on the solutions that are returned by some underlying algorithm; typically, local optimal solutions obtained by the application of a local search heuristic. This method has been applied to many different optimization problems having about 10,000 entries in Google Scholar. In this talk, we will review briefly the ILS method emphasizing the extensions of ILS. We will describe three relevant types of extensions: the hybrid ILS approaches combining ILS with other metaheuristics and/or exact methods; the SimILS (Simulation+ILS) to solve Stochastic Combinatorial Optimization Problems; the MoILS to solve Multiobjective Combinatorial Optimization, including multiobjective and stochastic problems. We will discuss the advantages and disadvantages of these extensions and present some applications, including real ones in areas like Marketing, Supply Chain Management, Logistics or Health Care.

LASER: Lightweight and Secure Remote Keyless Entry Protocol

Topics: Access Control; Security Protocols; Network Security; Wireless Network Security

Authors: Vanesa Daza and Xavier Salleras

Affiliation: Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain, CYBERCAT - Center for Cybersecurity Research of Catalonia and Spain

Digital Object Identifier: 10.5220/0007830103720377

Proceedings of SECRYPT 2019, ISBN: 978-989-758-378-0

Quick Abstract

Since Remote Keyless Entry (RKE) systems started to be widely used, several vulnerabilities in their protocols have been found. Attacks such as jamming-and-replay attacks and relay attacks are still effective against most recent RKE systems (Ibrahim et al., 2018), even when many secure schemes have been designed. Although they are interesting from a theoretical point of view, the complexity of these solutions is excessive to implement them into a fob (Karani et al., 2016). This paper presents a lightweight and general solution based on a one message protocol, which guarantees the integrity and validity of the authentication in RKE systems, protecting the communication against the well-known jamming-and-replay and relay attacks, without using complex cryptographic schemes. Moreover, we also adapt our protocol for passive RKE (PRKE) systems. Our solution also includes a novel frequency-hopping-based approach which mitigates deny-of-service attacks. Finally, a prototype has been implemented using non-expensive hardware. Obtained results assure scalability, effectiveness and robustness.

Related Ontology Subjects/Areas/Topics (9)

Access Control	Information and Systems Security	Security Protocols
Data Engineering	Internet Technology	Web Information Systems and Technologies
Databases and Data Security	Network Security	Wireless Network Security

Semantic Image Inpainting through Improved Wasserstein Generative Adversarial Networks

Topics: Color and Texture Analyses; Shape Representation and Matching; Features Extraction; Visual Attention and Image Saliency

Authors: Patricia Vitoria , Joan Sintes and Coloma Ballester

Affiliation: Department of Information and Communication Technologies, University Pompeu Fabra, Barcelona and Spain

Digital Object Identifier: 10.5220/0007367902490260

Proceedings of VISAPP 2019, ISBN: 978-989-758-354-4

Quick Abstract

Image inpainting is the task of filling-in missing regions of a damaged or incomplete image. In this work we tackle this problem not only by using the available visual data but also by incorporating image semantics through the use of generative models. Our contribution is twofold: First, we learn a data latent space by training an improved version of the Wasserstein generative adversarial network, for which we incorporate a new generator and discriminator architecture. Second, the learned semantic information is combined with a new optimization loss for inpainting whose minimization infers the missing content conditioned by the available data. It takes into account powerful contextual and perceptual content inherent in the image itself. The benefits include the ability to recover large regions by accumulating semantic information even it is not fully present in the damaged image. Experiments show that the presented method obtains qualitative and quantitative top-tier results in different experimental situations and also achieves accurate photo-realism comparable to state-of-the-art works.

Related Ontology Subjects/Areas/Topics (6)

Color and Texture Analyses		Features Extraction		Shape Representation and Matching
Computer Vision, Visualization and Computer Graphics		Image and Video Analysis		Visual Attention and Image Saliency

Jointly Optical Flow and Occlusion Estimation for Images with Large Displacements

Topic: Optical Flow and Motion Analyses

Authors: Vanel Lazcano ¹ , Luis Garrido ² and Coloma Ballester ³

Affiliations: ¹ Universidad Mayor, Chile , ² Universitat de Barcelona, Spain , ³ University Pompeu Fabra, Spain

Digital Object Identifier: 10.5220/0006716305880595

Proceedings of VISAPP 2018, ISBN: 978-989-758-290-5

Quick Abstract

This paper deals with motion estimation of objects in a video sequence. This problem is known as optical flow estimation. Traditional models to estimate it fail in presence of occlusions and non-uniform illumination. To tackle these problems we propose a variational model to jointly estimate optical flow and occlusions. The proposed model is able to deal with the usual drawback of variational methods in dealing with large displacements of objects in the scene which are larger than the object itself. The addition of a term that balances gradient and intensities increases the robustness to illumination changes of the proposed model. The inclusion of a supplementary matching obtained by exhaustive search in specific locations helps to follow large displacements.

Related Ontology Subjects/Areas/Topics (3)

Computer Vision, Visualization and Computer Graphics

Motion, Tracking and Stereo Vision

Optical Flow and Motion Analyses

Joint Large Displacement Scene Flow and Occlusion Variational Estimation

Topics: Image-Based Modeling and 3D Reconstruction; Optical Flow and Motion Analyses

Authors: Roberto P. Palomares , Gloria Haro and Coloma Ballester

Affiliation: Universitat Pompeu Fabra, Spain

Digital Object Identifier: 10.5220/0006110601720180

Proceedings of VISAPP 2017/VISIGRAPP, ISBN: 978-989-758-227-1

Quick Abstract

This paper presents a novel variational approach for the joint estimation of scene flow and occlusions. Our method does not assume that a depth sensor is available. Instead, we use a stereo sequence and exploit the fact that points that are occluded in time, might be visible from the other view and thus the 3D geometry can be densely reinforced in an appropriate manner through a simultaneous motion occlusion characterization. Moreover, large displacements are correctly captured thanks to an optimization strategy that uses a set of sparse image correspondences to guide the minimization process. We include qualitative and quantitative experimental results on several datasets illustrating that both proposals help to improve the baseline results.

Related Ontology Subjects/Areas/Topics (8)

Applications	Image-Based Modeling	Pattern Recognition
Computer Vision, Visualization and Computer Graphics	Motion, Tracking and Stereo Vision	Software Engineering
Geometry and Modeling	Optical Flow and Motion Analyses

Affine Invariant Self-similarity for Exemplar-based Inpainting

Topic: Image Enhancement and Restoration

Authors: Vadim Fedorov ¹ , Pablo Arias ² , Gabriele Facciolo ³ and Coloma Ballester ¹

Affiliations: ¹ University Pompeu Fabra, Spain , ² ENS Cachan, France , ³ Ecole Nationale des Ponts et Chaussées, France

Digital Object Identifier: 10.5220/0005728100480058

Proceedings of VISAPP 2016/VISIGRAPP, ISBN: 978-989-758-175-5

Quick Abstract

This paper presents a new method for exemplar-based image inpainting using transformed patches. We build upon a recent affine invariant self-similarity measure which automatically transforms patches to compare them in an appropriate manner. As a consequence, it intrinsically extends the set of available source patches to copy information from. When comparing two patches, instead of searching for the appropriate patch transformation in a highly dimensional parameter space, our approach allows us to determine a single transformation from the texture content in both patches. We incorporate the affine invariant similarity measure in a variational formulation for inpainting and present an algorithm together with experimental results illustrating this approach.

Related Ontology Subjects/Areas/Topics (3)

Computer Vision, Visualization and Computer Graphics

Image Enhancement and Restoration

Image Formation and Preprocessing

Monocular Depth Ordering using Perceptual Occlusion Cues

Topics: Image-Based Modeling and 3D Reconstruction; Entertainment Imaging Applications; Early and Biologically-Inspired Vision; Categorization and Scene Understanding

Authors: Babak Rezaeirowshan , Coloma Ballester and Gloria Haro

Affiliation: Universitat Pompeu Fabra, Spain

Digital Object Identifier: 10.5220/0005726404310441

Proceedings of VISAPP 2016/VISIGRAPP, ISBN: 978-989-758-175-5

Quick Abstract

In this paper we propose a method to estimate a global depth order between the objects of a scene using information from a single image coming from an uncalibrated camera. The method we present stems from early vision cues such as occlusion and convexity and uses them to infer both a local and a global depth order. Monocular occlusion cues, namely, T-junctions and convexities, contain information suggesting a local depth order between neighbouring objects. A combination of these cues is more suitable, because, while information conveyed by T-junctions is perceptually stronger, they are not as prevalent as convexity cues in natural images. We propose a novel convexity detector that also establishes a local depth order. The partial order is extracted in T-junctions by using a curvature-based multi-scale feature. Finally, a global depth order, i.e., a full order of all shapes that is as consistent as possible with the computed partial orders that can tolerate conflicting partial orders is computed. An integration scheme based on a Markov chain approximation of the rank aggregation problem is used for this purpose. The experiments conducted show that the proposed method compares favorably with the state of the art.

Related Ontology Subjects/Areas/Topics (10)

Applications	Entertainment Imaging Applications	Image-Based Modeling
Applications and Services	Geometry and Modeling	Pattern Recognition
Computer Vision, Visualization and Computer Graphics	Image and Video Analysis	Software Engineering
Early and Biologically-Inspired Vision

Citizens Collaboration to Minimize Power Costs in Smart Grids - A Game Theoretic Approach

Topics: Optimization Techniques for Efficient Energy Consumption; Economic Models of Energy Efficiency; Greener Systems Planning and Design; User-Centred and Participatory Design of Services and Systems for Smart Cities

Authors: Tarek AlSkaif ¹ , Manel Guerrero Zapata ² and Boris Bellalta ³

Affiliations: ¹ Universitat Politecnica de Catalunya (UPC), Spain , ² Universitat Politècnica de Catalunya (UPC), Spain , ³ Universitat Pompeu Fabra (UPF), Spain

Digital Object Identifier: 10.5220/0005490103000305

Proceedings of SMARTGREENS 2015, ISBN: 978-989-758-105-2

Quick Abstract

Generating the power necessary to run our future cities is one of the major concerns for scientists and policy makers alike. The increasing global energy demands with simultaneously decreasing fossil energy sources will drastically affect future energy prices. Strategies are already being implemented to develop solutions for the generation and efficient usage of energy at different levels. Involving citizens in the efficient planning and usage of power is a key. In this paper, we propose a game theory based power sharing mechanism between end-users in smart grids. We consider that citizens can produce some amount of electric power obtained from on-site renewable sources rather than just purchasing their whole demands from the grid. Simulation results show that consumers can achieve considerable cost savings if they adopt the proposed scheme. It is also noticed that the more the consumers cooperate, the higher the percentage of cost savings is.

Related Ontology Subjects/Areas/Topics (7)

Economic Models of Energy Efficiency	Greener Systems Planning and Design	Smart Cities
Energy and Economy	Optimization Techniques for Efficient Energy Consumption	User-Centred and Participatory Design of Services and Systems for Smart Cities
Energy-Aware Systems and Technologies

Topic(s):

Filter listed results, by

Publication date

From:

To:

Author

Locate Author in list below

Data pager
Data pager
1 2 3 4 5 6 7 8 9 10 Page 1 of 10, items 1 to 10 of 99.

Add Author(s) to filter:

Josep Blat (7)

Coloma Ballester (6)

Xavier Binefa (5)

Alun Evans (4)

Andrey Bankart (4)

David Nettleton (3)

Vicent Caselles (3)

Jaime Delgado (3)

Marcelo Bertalmío (2)

Marco Romeo (2)

Conference

Locate Conference in list below

Data pager
Data pager
1 2 Page 1 of 2, items 1 to 10 of 16.

Add Conference(s) to filter:

VISAPP(16)

SECRYPT(4)

WEBIST(3)

CSEDU(3)

GRAPP(3)

ICAART(2)

ICETE(2)

KDIR(2)

ICORES(1)

IVAPP(1)

Title:
ISBN:
Year:
Acronym:
Subject:

Title:
Author:
Affiliation:
Subject:

Name:
Affiliation:
Country:
Conference:
Subject:

Name:
Country:
Subject: