Text Classification methods have been improving at an unparalleled speed in the last decade thank... more Text Classification methods have been improving at an unparalleled speed in the last decade thanks to the success brought about by deep learning. Historically, state-of-the-art approaches have been developed for and benchmarked against English datasets, while other languages have had to catch up and deal with inevitable linguistic challenges. This paper offers a survey with practical and linguistic connotations, showcasing the complications and challenges tied to the application of modern Text Classification algorithms to languages other than English. We engage this subject from the perspective of the Italian language, and we discuss in detail issues related to the scarcity of task-specific datasets, as well as the issues posed by the computational expensiveness of modern approaches. We substantiate this by providing an extensively researched list of available datasets in Italian, comparing it with a similarly sought list for French, which we use for comparison. In order to simulate...
In recent years, the exponential growth of digital documents has been met by rapid progress in te... more In recent years, the exponential growth of digital documents has been met by rapid progress in text classification techniques. Newly proposed machine learning algorithms leverage the latest advancements in deep learning methods, allowing for the automatic extraction of expressive features. The swift development of these methods has led to a plethora of strategies to encode natural language into machine-interpretable data. The latest language modelling algorithms are used in conjunction with ad hoc preprocessing procedures, of which the description is often omitted in favour of a more detailed explanation of the classification step. This paper offers a concise review of recent text classification models, with emphasis on the flow of data, from raw text to output labels. We highlight the differences between earlier methods and more recent, deep learning-based methods in both their functioning and in how they transform input data. To give a better perspective on the text classification...
2018 24th International Conference on Pattern Recognition (ICPR), 2018
Among structured light strategies, the ones based on phase shift are considered to be the most ad... more Among structured light strategies, the ones based on phase shift are considered to be the most adaptive with respect to the features of the objects to be captured. Inter alia, the theoretical invariance to signal strength and the absence of discontinuities in intensity, make phase shift an ideal candidate to deal with complex surfaces of unknown geometry, color and texture. However, in practical scenarios, unexpected artifacts could still result due to the characteristics of real cameras. This is the case, for instance, with high contrast areas resulting from abrupt changes in the albedo of the captured objects. In fact, the not negligible size of pixels and the presence of blur can produce a mix of signal integration from adjacent areas with different albedo. This, in turn, would result in a bias in the phase recovery and, consequentially, in an inaccurate 3D reconstruction of the surface. While this problem affects most structure light methods based on phase shift or derived techniques, little effort has been put in addressing it. With this paper we propose a model for the phase corruption and a theoretically sound correction step to be adopted to compensate the bias. The practical effectiveness of our approach is well demonstrated by a complete set of experimental evaluations.
2017 International Conference on 3D Vision (3DV), 2017
Functional representation is a well-established approach to represent dense correspondences betwe... more Functional representation is a well-established approach to represent dense correspondences between deformable shapes. The approach provides an efficient low rank representation of a continuous mapping between two shapes, however under that framework the correspondences are only intrinsically captured, which implies that the induced map is not guaranteed to map the whole surface, much less to form a continuous mapping. In this work, we define a novel approach to the computation of a continuous bijective map between two surfaces moving from the low rank spectral representation to a sparse spatial representation. Key to this is the observation that continuity and smoothness of the optimal map induces structure both on the spectral and the spatial domain, the former providing effective low rank approximations, while the latter exhibiting strong sparsity and locality that can be used in the solution of large-scale problems. We cast our approach in terms of the functional transfer through a fuzzy map between shapes satisfying infinitesimal mass transportation at each point. The result is that, not only the spatial map induces a sub-vertex correspondence between the surfaces, but also the transportation of the whole surface, and thus the bijectivity of the induced map is assured. The performance of the proposed method is assessed on several popular benchmarks.
In this thesis we present several different approaches for constructing generative models to be u... more In this thesis we present several different approaches for constructing generative models to be used in both graphs and shapes. The central problem that we address in this work is how data that are defined in a non-vectorial space can be processed in order to tackle problem like data clustering and classification. While there exists a huge framework of techniques that deal with classification and regression with real-valued data which can be embedded into the Euclidean vector space, dealing with data that lay in different spaces is another matter. As an example, relational graphs represent a convenient way to represent real world data. However, working with graphs presents two problems: firstly, the order over the vertices of a graph is arbitrary. Secondly, the number of vertices may vary among different graphs. This leads to several practical problems when it comes to define statistical quantities like mean and variance of the data. Working with shapes brings similar issues. Method...
Partial similarity problems arise in numerous applications that involve real data acquisition by ... more Partial similarity problems arise in numerous applications that involve real data acquisition by 3D sensors, inevitably leading to missing parts due to occlusions and partial views. In this setting, the shapes to be retrieved may undergo a variety of transformations simultaneously, such as non-rigid deformations (changes in pose), topological noise, and missing parts - a combination of nuisance factors that renders the retrieval process extremely challenging. With this benchmark, we aim to evaluate the state of the art in deformable shape retrieval under such kind of transformations. The benchmark is organized in two sub-challenges exemplifying different data modalities (3D vs. 2.5D). A total of 15 retrieval algorithms were evaluated in the contest; this paper presents the details of the dataset, and shows thorough comparisons among all competing methods.
2016 23rd International Conference on Pattern Recognition (ICPR), 2016
We present a novel approach to the computation of dense correspondence maps between shapes in a n... more We present a novel approach to the computation of dense correspondence maps between shapes in a non-rigid setting. The problem is defined in terms of functional correspondences. We deal with the non-injectivity of the solution of the functional map framework due to the under-determinedness of the original problem. Key to our approach is the injectivity constraint plugged directly into the problem to optimize, achieved casting it as an assignment problem. This leads to an iterative process which yields a high quality bijective map between the shapes. In the experimental section we present both quantitative and qualitative results, showing that the proposed approach is competitive with the current state-of-the-art on quasi-isometric shape matching benchmarks.
Kernel methods provide a convenient way to apply a wide range of learning techniques to complex a... more Kernel methods provide a convenient way to apply a wide range of learning techniques to complex and structured data by shifting the representational problem from one of finding an embedding of the data to that of defining a positive semi-definite kernel. One problem with the most widely used kernels is that they neglect the locational information within the structures, resulting in less discrimination. Correspondence-based kernels, on the other hand, are in general more discriminating, at the cost of sacrificing positive-definiteness due to their inability to guarantee transitivity of the correspondences between multiple graphs. In this paper we adopt a general framework for the projection of (relaxed) correspondences onto the space of transitive correspondences, thus transforming any given matching algorithm onto a transitive multi-graph matching approach. The resulting transitive correspondences can then be used to provide a kernel that both maintains locational information and is guaranteed to be positive-definite. Experimental evaluation validates the effectiveness of the kernel for several structural classification tasks.
Non-rigid 3D shape retrieval is an active and important research topic in content based object re... more Non-rigid 3D shape retrieval is an active and important research topic in content based object retrieval. This problem is often cast in terms of the shapes intrinsic geometry due to its invariance to a wide range of non-rigid deformations. In this paper, we devise a novel generative model for shape retrieval based on the spectral representation of the Laplacian of a mesh. Contrary to common use, our approach avoids the ubiquitous correspondence problem by transforming the eigenvectors of the Laplacian to a density in the spectral-embedding space which is estimated nonparametrically. We show that this model can efficiently be learned from a set of 3D meshes. The experimental results on the SHREC'14 benchmark show the effectiveness of the approach compared to the state-of-the-art.
Text Classification methods have been improving at an unparalleled speed in the last decade thank... more Text Classification methods have been improving at an unparalleled speed in the last decade thanks to the success brought about by deep learning. Historically, state-of-the-art approaches have been developed for and benchmarked against English datasets, while other languages have had to catch up and deal with inevitable linguistic challenges. This paper offers a survey with practical and linguistic connotations, showcasing the complications and challenges tied to the application of modern Text Classification algorithms to languages other than English. We engage this subject from the perspective of the Italian language, and we discuss in detail issues related to the scarcity of task-specific datasets, as well as the issues posed by the computational expensiveness of modern approaches. We substantiate this by providing an extensively researched list of available datasets in Italian, comparing it with a similarly sought list for French, which we use for comparison. In order to simulate...
In recent years, the exponential growth of digital documents has been met by rapid progress in te... more In recent years, the exponential growth of digital documents has been met by rapid progress in text classification techniques. Newly proposed machine learning algorithms leverage the latest advancements in deep learning methods, allowing for the automatic extraction of expressive features. The swift development of these methods has led to a plethora of strategies to encode natural language into machine-interpretable data. The latest language modelling algorithms are used in conjunction with ad hoc preprocessing procedures, of which the description is often omitted in favour of a more detailed explanation of the classification step. This paper offers a concise review of recent text classification models, with emphasis on the flow of data, from raw text to output labels. We highlight the differences between earlier methods and more recent, deep learning-based methods in both their functioning and in how they transform input data. To give a better perspective on the text classification...
2018 24th International Conference on Pattern Recognition (ICPR), 2018
Among structured light strategies, the ones based on phase shift are considered to be the most ad... more Among structured light strategies, the ones based on phase shift are considered to be the most adaptive with respect to the features of the objects to be captured. Inter alia, the theoretical invariance to signal strength and the absence of discontinuities in intensity, make phase shift an ideal candidate to deal with complex surfaces of unknown geometry, color and texture. However, in practical scenarios, unexpected artifacts could still result due to the characteristics of real cameras. This is the case, for instance, with high contrast areas resulting from abrupt changes in the albedo of the captured objects. In fact, the not negligible size of pixels and the presence of blur can produce a mix of signal integration from adjacent areas with different albedo. This, in turn, would result in a bias in the phase recovery and, consequentially, in an inaccurate 3D reconstruction of the surface. While this problem affects most structure light methods based on phase shift or derived techniques, little effort has been put in addressing it. With this paper we propose a model for the phase corruption and a theoretically sound correction step to be adopted to compensate the bias. The practical effectiveness of our approach is well demonstrated by a complete set of experimental evaluations.
2017 International Conference on 3D Vision (3DV), 2017
Functional representation is a well-established approach to represent dense correspondences betwe... more Functional representation is a well-established approach to represent dense correspondences between deformable shapes. The approach provides an efficient low rank representation of a continuous mapping between two shapes, however under that framework the correspondences are only intrinsically captured, which implies that the induced map is not guaranteed to map the whole surface, much less to form a continuous mapping. In this work, we define a novel approach to the computation of a continuous bijective map between two surfaces moving from the low rank spectral representation to a sparse spatial representation. Key to this is the observation that continuity and smoothness of the optimal map induces structure both on the spectral and the spatial domain, the former providing effective low rank approximations, while the latter exhibiting strong sparsity and locality that can be used in the solution of large-scale problems. We cast our approach in terms of the functional transfer through a fuzzy map between shapes satisfying infinitesimal mass transportation at each point. The result is that, not only the spatial map induces a sub-vertex correspondence between the surfaces, but also the transportation of the whole surface, and thus the bijectivity of the induced map is assured. The performance of the proposed method is assessed on several popular benchmarks.
In this thesis we present several different approaches for constructing generative models to be u... more In this thesis we present several different approaches for constructing generative models to be used in both graphs and shapes. The central problem that we address in this work is how data that are defined in a non-vectorial space can be processed in order to tackle problem like data clustering and classification. While there exists a huge framework of techniques that deal with classification and regression with real-valued data which can be embedded into the Euclidean vector space, dealing with data that lay in different spaces is another matter. As an example, relational graphs represent a convenient way to represent real world data. However, working with graphs presents two problems: firstly, the order over the vertices of a graph is arbitrary. Secondly, the number of vertices may vary among different graphs. This leads to several practical problems when it comes to define statistical quantities like mean and variance of the data. Working with shapes brings similar issues. Method...
Partial similarity problems arise in numerous applications that involve real data acquisition by ... more Partial similarity problems arise in numerous applications that involve real data acquisition by 3D sensors, inevitably leading to missing parts due to occlusions and partial views. In this setting, the shapes to be retrieved may undergo a variety of transformations simultaneously, such as non-rigid deformations (changes in pose), topological noise, and missing parts - a combination of nuisance factors that renders the retrieval process extremely challenging. With this benchmark, we aim to evaluate the state of the art in deformable shape retrieval under such kind of transformations. The benchmark is organized in two sub-challenges exemplifying different data modalities (3D vs. 2.5D). A total of 15 retrieval algorithms were evaluated in the contest; this paper presents the details of the dataset, and shows thorough comparisons among all competing methods.
2016 23rd International Conference on Pattern Recognition (ICPR), 2016
We present a novel approach to the computation of dense correspondence maps between shapes in a n... more We present a novel approach to the computation of dense correspondence maps between shapes in a non-rigid setting. The problem is defined in terms of functional correspondences. We deal with the non-injectivity of the solution of the functional map framework due to the under-determinedness of the original problem. Key to our approach is the injectivity constraint plugged directly into the problem to optimize, achieved casting it as an assignment problem. This leads to an iterative process which yields a high quality bijective map between the shapes. In the experimental section we present both quantitative and qualitative results, showing that the proposed approach is competitive with the current state-of-the-art on quasi-isometric shape matching benchmarks.
Kernel methods provide a convenient way to apply a wide range of learning techniques to complex a... more Kernel methods provide a convenient way to apply a wide range of learning techniques to complex and structured data by shifting the representational problem from one of finding an embedding of the data to that of defining a positive semi-definite kernel. One problem with the most widely used kernels is that they neglect the locational information within the structures, resulting in less discrimination. Correspondence-based kernels, on the other hand, are in general more discriminating, at the cost of sacrificing positive-definiteness due to their inability to guarantee transitivity of the correspondences between multiple graphs. In this paper we adopt a general framework for the projection of (relaxed) correspondences onto the space of transitive correspondences, thus transforming any given matching algorithm onto a transitive multi-graph matching approach. The resulting transitive correspondences can then be used to provide a kernel that both maintains locational information and is guaranteed to be positive-definite. Experimental evaluation validates the effectiveness of the kernel for several structural classification tasks.
Non-rigid 3D shape retrieval is an active and important research topic in content based object re... more Non-rigid 3D shape retrieval is an active and important research topic in content based object retrieval. This problem is often cast in terms of the shapes intrinsic geometry due to its invariance to a wide range of non-rigid deformations. In this paper, we devise a novel generative model for shape retrieval based on the spectral representation of the Laplacian of a mesh. Contrary to common use, our approach avoids the ubiquitous correspondence problem by transforming the eigenvectors of the Laplacian to a density in the spectral-embedding space which is estimated nonparametrically. We show that this model can efficiently be learned from a set of 3D meshes. The experimental results on the SHREC'14 benchmark show the effectiveness of the approach compared to the state-of-the-art.
Uploads
Papers by Andrea Gasparetto