Acc. Int. E-A ARFAI DOREMI DRIMS ENJAMBRE GRE-12-34 GRE16-14 GRE19-04 GV-JRRJ GV/2020/030 HispaMus ISIC 2010 Leonardo2021 MIPRCV MultiScore PASCAL2 Prometeo 2012 PROSEMUS REPERTORIUM ROMA TADMar TIASA TIMuL UA-CPS

All years 20242023202220212020201920182017201620152014201320122011201020092008200720062005200420032002200120001999199819971996199519941993199219911990198919880000 All types Journal ArticlesBooksConferencesBook ChaptersProceedings ArticlesPhD ThesesPresentationsTechnical Reports All authors Abreu, J. Adriaans, P. Alacid, B. Alashhab, S. Albarrán, P. Alfaro-Contreras, M. Alonso-Jiménez, P. Anagnostopoulou, C. Arista, N. R. Arroyo, V. Asins, E. Ayllon, E. Aznar, I. Balboa, R. M. Barbancho, A. M. Barbancho, I. Barber, F. Barber, X. Baró, A. Barrachina, R. O. Bellet, A. Belmonte, M. A. Benedí, J. Benetos, E. Berlanga, R. Bernabeu, J. F. Bernabeu, M. Bosch, V. Boyer, L. Bresson, J. Buendía, M. Bustos, A. Calera-Rubio, J. Calvo-Zaragoza, J. Cano-Espinosa, C. Canteras, M. Caparrós, M. Cardoso, J. S. Carrasco, R. C. Casacuberta, F. Castellanos, A. Castellanos, F. J. Castellanos, Francisco José Cazorla, M. Cervera, J. M. Cibirían, R. Coltell, O. Compañ-Rosique, P. Conklin, D. Corbí-Bellot, A. M. Costa, A. Cuenca-Asensi, S. Cuevas-Velasquez, H. Dalmau-Espert, J. L. Danger, R. Delgado, T. Desmond, K. Domenech, J. Doménech, S. Domingo, A. Efford, N. Escalona, F. Espí, D. Esplà-Gomis, M. Esposito, Y. Ezquerro, A. Falcone, G. Ferri, F. Fiore, T. M. M. Fisher, R. B. Forcada, M. L. Fornés, A. Fuente, Cde la Fuente, C. Fuente, C. Fujinaga, I. Galant, J. Gallego, A. J. Gallego-Sánchez, A. J. Gallego-Sánchez, J. Garay-Maestre, U. García, P. García-Doménech, R. V. García-García, F. García-Iasci, P. Garrido, A. Garrido-Alenda, A. Garrido-Munoz, C. Gil, P. Gil, R. Gilabert-Zarco, P. Gómez, E. Gómez, J. A. Gómez-Ballester, E. Gomez-Donoso, F. González, G. González, L. A. González-Barrachina, P. Gracia, I. Gracia, J. M. Gras-Martí, A. Grecu, A. Habrard, A. Hazan, A. Hemming, J. Heredia-Agoiz, J. L. Herrero-Vicente, J. Higuera, C. De La Hontanilla, M. Iglesia-Vayá, M. Illescas, P. R. Iñesta, J. M. Izquierdo, E. Jakas, M. M. Jiménez, V. Jiménez, V. M. Jimeno-Morenilla, A. Jr., J. Hajic Kersten, S. Klapuri, A. Lartillot, O. Lemström, K. León, P. J. Ponce De León, P. J. Ponce León, Pedro J. Ponce Lidy, T. Llixiona, J. López, D. López-García, G. López-Gutiérrez, J. C. Lozano, M. Á. Madueño, A. Maestre, E. Manjón, J. V. Marín, R. Marsden, A. Martínez, M. T. Martínez-Álvarez, A. Martinez-Martin, E. Martínez-Sevilla, J. C. Mas-Candela, E. Mateiu, T. N. Mayer, R. Mazón, J. N. Mencarelli, A. Mico, L. Miotto, R. Molina-Carmona, A. J. R. Gallego Molina-Carmona, R. Mollineda, R. A. Montell, J. À. Morales, A. Moreno-Seco, F. Münnich, S. Nieto-Hidalgo, M. Nuñez-Alcover, Alicia Olivares-Rodríguez, C. Oncina, J. Orio, N. Orozco-Beltrán, D. Ortega-Bastida, J. Ortiz, A. Ortiz-Rojas, S. Pacha, A. Pascual, B. Pascual-León, N. Pérez, A. Pérez-Francisco, M. Pérez-García, Pérez-Sancho T. Pérez-García, T. Pérez-Herranz, F. M. Pérez-Ortiz, J. A. Perez-Sancho, C. Pertusa, A Pertusa, A. Piccoli, H. C. B. Pla, F. Pobil, A. P. Del Pomata, P. A. Pons, A. Pugin, L. Quesada, T. Quiles, J. A. Ramirez, R. Ramírez-Sánchez, G. Rauber, A. Recatalá, G. Regalado, Francisco José Castellanos Regimbal, J. Requena, A. Riba, P. Rico, J. R. Rico-Juan, J. R Rico-Juan, J. R. Ríos-Vila, A. Rizo, D. Rocamora, M. T. Rodríguez, R. Rojas, G. Roldán, J. M. Román, M. A. Rosello, A. Rulot, H. M. Saborit-Torres, J. M. Saenz-Gamboa, J. J. Sáez-Pérez, J. Salamon, J. Salas, F. Salinas, J. M. Salvador, C. Sanches, J. M. Sanches, J. Sánchez, J. A. Sánchez, J. S. Sánchez-Ferrer, A. Sánchez-Hernández, A. Sánchez-Martínez, F. Sanchiz, J. M. Sanz, P. J. Sanz, P. P. Sapp, C. S. Sarti, M. A. Scalco, M. Sebban, M. Segarra, E. Serra, X. Serrano, A. Serrano, J. F. Silla, C. N. Jr. Sober-Mira, J. Socorro, R. Sotoca, J. M. Sroubek, Z. Stefan, I. Suárez, A. Tardón, L. J. Thollard, F. Thomae, M. E. Toselli, A. H. Traver, V. J. Tuijl, B. Tylecek, R. Úbeda, J. I. Valero, S. Valero-Mas, J. J. Varo, M. A. Vayá, Saborit M. Iglesia Verdú-Mas, J. L. Vicente, O. Vidal, E. Viejo, D. Vigliensoni, G. Villegas, J. A. Vivas-Tejuelo, L. A. Yepes, J. A. Zaanen, M. Van All users David RizoJosé Manuel IñestaJorge Calvo-ZaragozaPedro José Ponce de LeónFrancisco J. CastellanosMaría AlfaroAntonio Ríos Vila

Show all

2021

Castellanos, F. J.; Gallego, A. J.; Calvo-Zaragoza, J.

An Unsupervised Domain Adaptation framework for Layout Analysis of Music Score Images Proceedings Article

In: Proceedings of the 14th Machine Learning and Music Workshop, pp. 6, 2021.

BibTeX | Tags: GRE19-04, ROMA

@inproceedings{k482,

title = {An Unsupervised Domain Adaptation framework for Layout Analysis of Music Score Images},

author = {F. J. Castellanos and A. J. Gallego and J. Calvo-Zaragoza},

year  = {2021},

date = {2021-12-01},

booktitle = {Proceedings of the 14th Machine Learning and Music Workshop},

pages = {6},

keywords = {GRE19-04, ROMA},

pubstate = {published},

tppubtype = {inproceedings}

}

Close

Castellanos, F. J.; Gallego, A. J.; Calvo-Zaragoza, J.

Unsupervised Neural Domain Adaptation for Document Image Binarization Journal Article

In: Pattern Recognition, vol. 119, pp. 108099, 2021.

BibTeX | Tags: GRE19-04, HispaMus

@article{k467,

title = {Unsupervised Neural Domain Adaptation for Document Image Binarization},

author = {F. J. Castellanos and A. J. Gallego and J. Calvo-Zaragoza},

year  = {2021},

date = {2021-11-01},

urldate = {2021-11-01},

journal = {Pattern Recognition},

volume = {119},

pages = {108099},

keywords = {GRE19-04, HispaMus},

pubstate = {published},

tppubtype = {article}

}

Close

Gallego, A. J.; Calvo-Zaragoza, J.; Fisher, R. B.

Incremental Unsupervised Domain-Adversarial Training of Neural Networks Journal Article

In: IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 11, pp. 4864-4878, 2021, ISSN: 2162-2388.

Abstract | Links | BibTeX | Tags: GRE19-04, HispaMus

@article{k455,

title = {Incremental Unsupervised Domain-Adversarial Training of Neural Networks},

author = {A. J. Gallego and J. Calvo-Zaragoza and R. B. Fisher},

url = {https://grfia.dlsi.ua.es/repositori/grfia/pubs/455/2001.04129.pdf},

issn = {2162-2388},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

journal = {IEEE Transactions on Neural Networks and Learning Systems},

volume = {32},

number = {11},

pages = {4864-4878},

abstract = {In the context of supervised statistical learning, it is typically assumed that the training set comes from the same distribution that draws the test samples. When this is not the case, the behavior of the learned model is unpredictable and becomes dependent upon the degree of similarity between the distribution of the training set and the distribution of the test set. One of the research topics that investigates this scenario is referred to as Domain Adaptation (DA). Deep neural networks brought dramatic advances in pattern recognition and that is why there have been many attempts to provide good domain adaptation algorithms for these models. Here we take a different avenue and approach the problem from an incremental point of view, where the model is adapted to the new domain iteratively. We make use of an existing unsupervised domain-adaptation algorithm to identify the target samples on which there is greater confidence about their true label. The output of the model is analyzed in different ways to determine the candidate samples. The selected samples are then added to the source training set by self-labeling, and the process is repeated until all target samples are labeled. This approach implements a form of adversarial training in which, by moving the self-labeled samples from the target to the source set, the DA algorithm is forced to look for new features after each iteration. Our results report a clear improvement with respect to the non-incremental case in several datasets, also outperforming other state-of-the-art domain adaptation algorithms.},

keywords = {GRE19-04, HispaMus},

pubstate = {published},

tppubtype = {article}

}

Close

In the context of supervised statistical learning, it is typically assumed that the training set comes from the same distribution that draws the test samples. When this is not the case, the behavior of the learned model is unpredictable and becomes dependent upon the degree of similarity between the distribution of the training set and the distribution of the test set. One of the research topics that investigates this scenario is referred to as Domain Adaptation (DA). Deep neural networks brought dramatic advances in pattern recognition and that is why there have been many attempts to provide good domain adaptation algorithms for these models. Here we take a different avenue and approach the problem from an incremental point of view, where the model is adapted to the new domain iteratively. We make use of an existing unsupervised domain-adaptation algorithm to identify the target samples on which there is greater confidence about their true label. The output of the model is analyzed in different ways to determine the candidate samples. The selected samples are then added to the source training set by self-labeling, and the process is repeated until all target samples are labeled. This approach implements a form of adversarial training in which, by moving the self-labeled samples from the target to the source set, the DA algorithm is forced to look for new features after each iteration. Our results report a clear improvement with respect to the non-incremental case in several datasets, also outperforming other state-of-the-art domain adaptation algorithms.

Close

• https://grfia.dlsi.ua.es/repositori/grfia/pubs/455/2001.04129.pdf

Close

Castellanos, F. J.; Gallego, A. J.; Calvo-Zaragoza, J.

Unsupervised Domain Adaptation for Document Analysis of Music Score Images Proceedings Article

In: Proc. of the 22nd International Society for Music Information Retrieval Conference, 2021.

BibTeX | Tags: GRE19-04

@inproceedings{k475,

title = {Unsupervised Domain Adaptation for Document Analysis of Music Score Images},

author = {F. J. Castellanos and A. J. Gallego and J. Calvo-Zaragoza},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

booktitle = {Proc. of the 22nd International Society for Music Information Retrieval Conference},

keywords = {GRE19-04},

pubstate = {published},

tppubtype = {inproceedings}

}

Close

Castellanos, F. J.; Valero-Mas, J. J.; Calvo-Zaragoza, J.

Prototype Generation in the String Space via Approximate Median for Data Reduction in Nearest Neighbor classification Journal Article

In: Soft Computing, vol. 25, 2021, ISSN: 15403-15415.

BibTeX | Tags: GRE19-04, HispaMus

@article{k476,

title = {Prototype Generation in the String Space via Approximate Median for Data Reduction in Nearest Neighbor classification},

author = {F. J. Castellanos and J. J. Valero-Mas and J. Calvo-Zaragoza},

issn = {15403-15415},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

journal = {Soft Computing},

volume = {25},

keywords = {GRE19-04, HispaMus},

pubstate = {published},

tppubtype = {article}

}

Close

Garrido-Munoz, C.; Sánchez-Hernández, A.; Castellanos, F. J.; Calvo-Zaragoza, J.

Domain Adaptation for Document Image Binarization via Domain Classification Proceedings Article

In: Tallón-Ballesteros, A. J. (Ed.): Frontiers in Artificial Intelligence and Applications, pp. 569-582, IOS Press, 2021, ISBN: 978-1-64368-224-2.

BibTeX | Tags: GRE19-04, GV/2020/030

@inproceedings{k480,

title = {Domain Adaptation for Document Image Binarization via Domain Classification},

author = {C. Garrido-Munoz and A. Sánchez-Hernández and F. J. Castellanos and J. Calvo-Zaragoza},

editor = {A. J. Tallón-Ballesteros},

isbn = {978-1-64368-224-2},

year  = {2021},

date = {2021-01-01},

booktitle = {Frontiers in Artificial Intelligence and Applications},

pages = {569-582},

publisher = {IOS Press},

chapter = {-},

keywords = {GRE19-04, GV/2020/030},

pubstate = {published},

tppubtype = {inproceedings}

}

Close

2020

Castellanos, F. J.; Calvo-Zaragoza, J.; Iñesta, J. M.

Two-step neural cross-domain experiments forfull-page recognition of Mensural documents Proceedings Article

In: Proc. of the 13th International Workshop on Machine Learning and Music, pp. 56–60, MML 2020 13th International Workshop on Machine Learning and Music, 2020.

BibTeX | Tags: GRE19-04, HispaMus

@inproceedings{k448,

title = {Two-step neural cross-domain experiments forfull-page recognition of Mensural documents},

author = {F. J. Castellanos and J. Calvo-Zaragoza and J. M. Iñesta},

year  = {2020},

date = {2020-09-01},

booktitle = {Proc. of the 13th International Workshop on Machine Learning and Music},

pages = {56--60},

publisher = {13th International Workshop on Machine Learning and Music},

organization = {MML 2020},

keywords = {GRE19-04, HispaMus},

pubstate = {published},

tppubtype = {inproceedings}

}

Close