Publications

Here is the list of my publications (sorted by year)

Journals

  • Melacci, S., Gori, M.: Learning with Box Kernels. IEEE Transactions on Pattern Analysis and Machine Intelligence (preprint online) (2013)
  • Gori, M., Melacci, S.: Constraint Verification with Kernel Machines. IEEE Transactions on Neural Networks and Learning Systems, Volume 24(5): 825-831 (2013)
  • Ferroni, S., Borracchini, A., Melacci, S., Doldo, T.: Aesthetical Standards and New Technologies: a Comparison. Virtual Journal of Orthodontics, Issue 9.4: 10-24 (2012)
  • Melacci, S., Gori, M.: Unsupervised Learning by Minimal Entropy Encoding. IEEE Transactions on Neural Networks and Learning Systems, Volume 23 (12):1849-1861 (2012)
  • Gnecco, G., Gori, M., Melacci, S., Sanguineti, M.: A theoretical framework for supervised learning from regions. Neurocomputing, 2012, Elsevier (accepted for publication)
  • Maggini, M., Melacci, S., Sarti, L.: Learning from pairwise constraints by Similarity Neural Networks. Neural Networks, Volume 26, February 2012, 141-158, Elsevier (2012)
  • Melacci, S., Belkin, M.: Training a Laplacian Support Vector Machine in the Primal. The Journal of Machine Learning Research, Volume 12 (March), 1149-1184, JMLR.org (2011) [CODE]
  • Melacci, S., Sarti, L., Maggini, M., Gori, M.: A template-based approach to automatic face enhancement. Pattern Analysis \& Applications, Volume 13 (3), ISSN 1433-7541, Springer-Verlag (2010), 289-300

International Conferences

  • Frandina, S., Gori, M., Lippi, M., Maggini, M., Melacci, S.: Variational Foundations of Online Backpropagation. To appear in Proceedings of the 23rd International Conference on Artificial Neural Networks (ICANN 2013)
  • Frandina, S., Lippi, M., Maggini, M., Melacci, S.: On-line Laplacian One-Class Support Vector Machines. To appear in Proceedings of the 23rd International Conference on Artificial Neural Networks (ICANN 2013)
  • Gnecco, G., Gori, M., Melacci, S., Sanguineti, M.: Learning with hard constraints. To appear in Proceedings of the 23rd International Conference on Artificial Neural Networks (ICANN 2013)
  • Melacci, S., Lippi, M., S., Gori, M., Maggini, M.: Information-based learning of deep architectures for feature extraction. To appear in Proceedings of the 17th International Conference on Image Analysis and Processing (ICIAP 2013)
  • Frandina, S., Gori, M., Lippi, M., Maggini, M., Melacci, S.: Inference, Learning, and Laws of Nature. In 23rd International Joint Conference on Artiļ¬cial Intelligence, Proceedings of the 9th International Workshop on Neural-Symbolic Learning and Reasoning (2013), 20-23
  • Gori, M., Melacci, S., Lippi, M., Maggini, M.: Information Theoretic Learning for Pixel-based Visual Agents. In Proceedings of the 12th European Conference on Computer Vision, Lecture Notes in Computer Science, LNCS 7577, Springer (2012), 864-875 (6)
  • Melacci, S., Gori, M.: Kernel Methods for Minimum Entropy Encoding. In Proceedings of the 10th International Conference on Machine Learning and Applications, IEEE (2011)
  • Melacci, S., Gori, M.: Learning with Box Kernels. In Proceedings of the International Conference on Neural Information Processing, Lecture Notes in Computer Science, LNCS 7064, Springer (2011), 519-528 (2)
  • Gori, M., Melacci, S.: Support Constraint Machines. In Proceedings of the International Conference on Neural Information Processing, Lecture Notes in Computer Science, LNCS 7064, Springer (2011), 28-37 (1)
  • Melacci, S., Gori, M.: Semi-Supervised Multiclass Kernel Machines with Probabilistic Constraints. In Proceedings of the 12th International Conference on Advances in Artificial Intelligence - AI*IA 2011. Lecture Notes in Computer Science LNCS 6934, Springer (2011), 21--32
  • Gori, M., Melacci, S.: Learning with convex constraints. Artificial Neural Networks - ICANN 2010. Lecture Notes in Computer Science LNCS 6354, Springer-Verlag (2010), 315--320
  • Melacci, S., Gori, M., Maggini, M.: Semi-supervised learning with constraints for multi-view object recognition. Artificial Neural Networks - ICANN 2009. Lecture Notes in Computer Science LNCS 5769, Springer-Verlag (2009), 653--662.
    *** BEST STUDENT PAPER AWARD ***
  • Melacci, S., Maggini, M., Sarti, L.: Semi-supervised Clustering using Similarity Neural Networks. In Proceedings of the International Joint Conference on Neural Networks, IEEE (2009), 2065--2072
  • Castelli, I., Maggini, M., Melacci, S., Sarti, L.: Auto Associative Neural Network based Active Shape Models. In Proceedings of the 8th IEEE International Conference on Automatic Face and Gesture Recognition, IEEE (2008), 1--6
  • Maggini, M., Melacci, S., Sarti, L.: Learning similarity measures from pairwise constraints with neural networks. Artificial Neural Networks - ICANN 2008. Lecture Notes in Computer Science LNCS 5164, Springer-Verlag (2008), 81--90
  • Melacci, S., Sarti, L., Maggini, M., Bianchini, M.: A neural network approach to similarity learning. Artificial Neural Networks in Pattern Recognition, ANNPR 2008. Lecture Notes in Artificial Intelligence LNAI 5064, Springer-Verlag (2008), 133--136
  • Maggini, M., Melacci, S., Sarti, L.: Representation of Facial Features by Catmull-Rom Splines. Computer Analysis of Images and Patterns, CAIP 2007. Lecture Notes in Computer Science LNCS 4673, Springer-Verlag (2007), 408--415

Technical Reports

  • Melacci, S., Belkin, M.: Training a Laplacian Support Vector Machine in the PrimalarXiv:0909.5422v1 [stat.ML] 29 September, (2009)
  • Maggini, M., Melacci, S., Sarti, L.: Approximation capabilities of Similarity Neural Networks. Department of Information Engineering, University of Siena. TechRep #3, (2008)

Theses

  • Melacci, S.: Learning with Pairwise Constraints. PhD Thesis (advisor: Prof. Marco Maggini), Department of Information Engineering, University of Siena, 9 April 2010
  • Melacci, S.: Generazione Automatica di Caricature: Image Warping (advisor: Prof. Marco Maggini), Master Thesis, Informatic Engineering Faculty (curriculum: Multimedial Information Systems), University of Siena, 25 September 2006
  • Melacci, S.: Gestione del processo di creazione di un Learning Set per l'addestramento di un Classificatore di Documenti attraverso un'Interfaccia Web Multi-Utente (advisor: Prof. Marco Maggini), Bachelor Thesis, Informatic Engineering Faculty (curriculum: Networks and Multimedial Information Systems), University of Siena, 11 October 2004