Browsing Tesi di dottorato by Author "Pelillo, Marcello"

DSpace/Manakin Repository

Browsing Tesi di dottorato by Author "Pelillo, Marcello"

Sort by: Order: Results:

  • A game-theoretic framework for similarity-based data clustering 
    Rota Bulò, Samuel <1981> (Università Ca' Foscari Venezia, 2009-03-06)
  • Algorithms for graph compression : theory and experiments 
    Nourbakhsh, Farshad <1979> (Università Ca' Foscari Venezia, 2015-02-13)
    Graphs and networks are everywhere, from social networks to the World Wide Web. Since the last decade, massive graphs has become the center attention of an intense research activity, both industrial and academic research ...
  • Constrained dominant sets and its applications in computer vision 
    Alemu, Leulseged Tesfaye <1991> (Università Ca' Foscari Venezia, 2020-01-31)
    In this thesis, we present new schemes which leverage a constrained clustering method to solve several computer vision tasks ranging from image retrieval, image segmentation and co-segmentation, to person re-identification. ...
  • Evolutionary game theoretic models for natural language processing 
    Tripodi, Rocco <1982> (Università Ca' Foscari Venezia, 2016-02-04)
    This thesis is aimed at discovering new learning algorithms inspired by principles of biological evolution, which are able to exploit relational and contextual information, viewing clustering and classification problems ...
  • Exploiting contextual information with deep neural networks 
    Elezi, Ismail <1991> (Università Ca' Foscari Venezia, 2020-07-29)
    Context matters! Nevertheless, there has not been much research in exploiting contextual information in deep neural networks. For the most part, the entire usage of contextual information has been limited to recurrent ...
  • Extensions of dominant sets and their applications in computer vision 
    Mequanint, Eyasu Zemene <1984> (Università Ca' Foscari Venezia, 2018-03-05)
    Many problems in computer vision can be formulated as a clustering problem, a problem that aims to organize a collection of data objects into groups or clusters, such that objects within a cluster are more “similar” to ...
  • Jigsaw Puzzle Solving as a Consistent Labeling Problem 
    Khoroshiltseva, Marina <1979> (Università Ca' Foscari Venezia, ND)
    The thesis aims to develop a methodology for solving complex puzzle problems. In the first part of the research, we explore the idea of abstracting the jigsaw puzzle problem as a consistent labeling problem, a classical ...
  • Philosophical aspects in pattern recognition research 
    Scantamburlo, Teresa <1981> (Università Ca' Foscari Venezia, 2014-03-18)
    Pattern recognition is the discipline which studies theories and methods to build machines that are able to discover regularities in noisy data. As many of its characterizations suggest, the field is usually considered as ...
  • Regular partitions and their use in structural pattern recognition 
    Fiorucci, Marco <1981> (Università Ca' Foscari Venezia, 2019-03-20)
    The huge amount of data generated everyday by different interrelated entities calls for the development of new effective methods to store, retrieve and understand these massive network data. In this thesis, we tackle this ...
  • Semi-supervised learning and applications : a game-theoretic perspective 
    Vascon, Sebastiano <1982> (Università Ca' Foscari Venezia, 2020-01-31)
    This thesis is focused on semi-supervised learning (SSL) algorithms, a family of methods lying in between supervised and unsupervised learning. The main characteristic of SSL algorithms is that they exploit at the same ...
  • Using Contextual Information In Weakly Supervised Learning: Toward the integration of contextual and deep learningapproaches, to address weakly supervised tasks 
    Torcinovich, Alessandro <1992> (Università Ca' Foscari Venezia, 2021-07-06)
    Come l'attento lettore avrà dedotto dal titolo, questa tesi pone alcune basi empiriche, assieme ad altrettante considerazioni teoriche, verso la definizione di una metodologia finalizzata a migliorare task di weakly ...
  • Vulnerability of Machine Learning: A Study on Poisoning Attacks 
    Cina', Antonio Emanuele <1995> (Università Ca' Foscari Venezia, 2023-01-27)
    Il successo senza precedenti dell'apprendimento automatico (ML) in diverse applicazioni è stato intrinsecamente favorito dalla crescente disponibilità di potenza di calcolo e di grandi insiemi di dati di addestramento, con ...