|
Petia Radeva, Maya Dimitrova, Ch. Roumenin, David Rotger, D. Nikolov, & Juan J. Villanueva. (2004). Integration of Multiple Sensor Modalities in ActiveVessel Cardiology Workstation.
|
|
C. Mariño, M.G. Penas, M. Penedo, David Lloret, & M.J. Carreira. (2001). Integration of Mutual Information and Creaseness Based Methods for the Automatic Registration of SLO Sequences..
|
|
David Rotger, Petia Radeva, J. Mauri, & E Fernandez-Nofrerias. (2002). Internal and External Coronary Vessel Images Registration..
|
|
Oriol Pujol, Misael Rosales, Petia Radeva, & E Fernandez-Nofrerias. (2003). Intravascular Ultrasound Images Vessel Characterization using AdaBoost.
|
|
Maya Dimitrova, I. Terziev, Petia Radeva, & Juan J. Villanueva. (2004). Java-Servlet Technology for Building New Web Document Classifiers.
|
|
David Guillamet, & B. Moghaddam. (2002). Joint Distribution of Local Image Features for Appearance Moldeling..
|
|
David Lloret, C. Mariño, Joan Serrat, Antonio Lopez, & Juan J. Villanueva. (2001). Landmark-based registration of full SLO video sequences..
|
|
G.Estape, & Enric Marti. (2008). L’ús d’aplicacions de visualització 3D com a eina d’aprenenetatge en activitats formatives dirigides i autònomes: el cas del programa Bluestar.
|
|
A. Pujol, H. Wechsler, & Juan J. Villanueva. (2001). Learning and Caricaturing the Face Space Using Self-Organization and Hebbian Learning for Face Processing..
|
Pau Riba, Andreas Fischer, Josep Llados, & Alicia Fornes. (2020). Learning Graph Edit Distance by Graph NeuralNetworks.
Abstract: The emergence of geometric deep learning as a novel framework to deal with graph-based representations has faded away traditional approaches in favor of completely new methodologies. In this paper, we propose a new framework able to combine the advances on deep metric learning with traditional approximations of the graph edit distance. Hence, we propose an efficient graph distance based on the novel field of geometric deep learning. Our method employs a message passing neural network to capture the graph structure, and thus, leveraging this information for its use on a distance computation. The performance of the proposed graph distance is validated on two different scenarios. On the one hand, in a graph retrieval of handwritten words~\ie~keyword spotting, showing its superior performance when compared with (approximate) graph edit distance benchmarks. On the other hand, demonstrating competitive results for graph similarity learning when compared with the current state-of-the-art on a recent benchmark dataset.
|
Mikel Menta, Adriana Romero, & Joost Van de Weijer. (2020). Learning to adapt class-specific features across domains for semantic segmentation.
Abstract: arXiv:2001.08311
Recent advances in unsupervised domain adaptation have shown the effectiveness of adversarial training to adapt features across domains, endowing neural networks with the capability of being tested on a target domain without requiring any training annotations in this domain. The great majority of existing domain adaptation models rely on image translation networks, which often contain a huge amount of domain-specific parameters. Additionally, the feature adaptation step often happens globally, at a coarse level, hindering its applicability to tasks such as semantic segmentation, where details are of crucial importance to provide sharp results. In this thesis, we present a novel architecture, which learns to adapt features across domains by taking into account per class information. To that aim, we design a conditional pixel-wise discriminator network, whose output is conditioned on the segmentation masks. Moreover, following recent advances in image translation, we adopt the recently introduced StarGAN architecture as image translation backbone, since it is able to perform translations across multiple domains by means of a single generator network. Preliminary results on a segmentation task designed to assess the effectiveness of the proposed approach highlight the potential of the model, improving upon strong baselines and alternative designs.
|
|
Oriol Ramos Terrades, & Ernest Valveny. (2003). Line Detection Using Ridgelets Transform for Graphic Symbol Representation.
|
|
X. Binefa, J.M. Sanchez, Petia Radeva, & Jordi Vitria. (2000). Linking Visual Cues and Semantic Terms Under Specific Digital Video Domains..
|
|
J.M. Sanchez, X. Binefa, Jordi Vitria, & Petia Radeva. (1999). Local Analysis for Scene Break Detection Applied to TV Commercials Recognition..
|
|
B. Moghaddam, David Guillamet, & Jordi Vitria. (2003). Local Appearance-Based Models using High-Order Statistics of Image Features.
|
