1,720,977 research outputs found
Generative models for non-vectorial data
No full textIn questa tesi presentiamo diversi approcci per la costruzione di modelli generativi utilizzati sia su grafi sia su modelli. Il problema principale su cui questo lavoro verte riguarda il problema di processare dati che vengono definiti in spazi non vettoriali in modo da poterli utilizzare in operazioni di clustering e classificazione.
Nella prima parte di questa tesi introduciamo due modelli generativi per la classificazione di forme. Entrambi i metodi presentati utilizzano descrittori spettrali. Tuttavia, nel primo approccio non assumiamo che la corrispondenza tra i vertici sia nota. Nel secondo invece, studiamo la variazione di una metrica definita in una varietà speciale e gestiamo il problema della mancanza delle corrispondenze proiettandolo in un problema di matching bipartito. Infine, presentiamo una tecnica basata sulle corrispondenze funzionali che calcola la mappa iniettiva tra due superfici.
Nella seconda parte della tesi affrontiamo il problema dell’embedding dei dati rappresentati da grafi relazionali. In particolare, il primo metodo proposto è basato sulle componenti spettrali di un grafo che vengono utilizzate per definire un modello generativo. In un altro lavoro, eliminiamo l’assunzione di spazio intrinseco comune generalizzando un kernel basato sulla divergenza di Jensen-Shannon. Infine, investighiamo l’utilizzo di tecniche di matching multi-grafo nel contesto di kernel sui grafi e come è possibile trasformare un qualsiasi algoritmo per il matching in un algoritmo per il matching multi-grafo transitivo
A Statistical Model of Riemannian Metric Variation for Deformable Shape Analysis
Get PDFThe analysis of deformable 3D shape is often cast in terms of the shape's intrinsic geometry due to its invariance to a wide range of non-rigid deformations. However, object's plasticity in non-rigid transformation often result in transformations that are not completely isometric in the surface's geometry and whose mode of deviation from isometry is an identifiable characteristic of the shape and its deformation modes. In this paper, we propose a novel generative model of the variations of the intrinsic metric of de formable shapes, based on the spectral decomposition of the Laplace-Beltrami operator. To this end, we assume two independent models for the eigenvectors and the eigenvalues of the graph-Laplacian of a 3D mesh which are learned in a supervised way from a set of shapes belonging to the same class. We show how this model can be efficiently learned given a set of 3D meshes, and evaluate the performance of the resulting generative model in shape classification and retrieval tasks. Comparison with state-of-the-art solutions for these problems confirm the validity of the approach
Adaptive Albedo Compensation for Accurate Phase-Shift Coding
No full textAmong 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
Non-parametric Spectral Model for Shape Retrieval
No full textNon-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 non-parametrically. 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
A Non-parametric Spectral Model for Graph Classification
No full textGraph-based representations have been used with considerable success in computer vision in the abstraction and recognition of object shape and scene structure. Despite this, the methodology available for learning structural representations from sets of training examples is relatively limited. In this paper we take a simple yet effective spectral approach to graph learning. In particular, we define a novel model of structural representation based on the spectral decomposition of graph Laplacian of a set of graphs, but which make away with the need of one-to-one node-correspondences at the base of several previous approaches, and handles directly a set of other invariants of the representation which are often neglected. An experimental evaluation shows that the approach significantly improves over the state of the art.Graph-based representations have been used with considerable success in computer vision in the abstraction and recognition of object shape and scene structure. Despite this, the methodology available for learning structural representations from sets of training examples is relatively limited. In this paper we take a simple yet effective spectral approach to graph learning. In particular, we define a novel model of structural representation based on the spectral decomposition of graph Laplacian of a set of graphs, but which make away with the need of one-to-one node-correspondences at the base of several previous approaches, and handles directly a set of other invariants of the representation which are often neglected. An experimental evaluation shows that the approach significantly improves over the state of the ar
A survey on text classification: Practical perspectives on the Italian language
Get PDFText 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 a real-world practical scenario, we apply a number of representative methods to custom-tailored multilabel classification datasets in Italian, French, and English. We conclude by discussing results, future challenges, and research directions from a linguistically inclusive perspective
Non-rigid dense bijective maps
No full textWe 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
Objective and Subjective Metrics for 3D Display Perception Evaluation
No full textMany modern professional 3D display systems adopt stereo vision and viewer-dependent rendering in order to offer an immersive experience and to enable complex interaction models. Within these scenarios, the ability of the user to effectively perform a task depends both on the correct rendering of the scene and on his ability to perceive it. These factors, in turn, are affected by several error sources, such as accuracy of the user position estimation or lags between tracking and rendering. With this paper, we introduce a practical and sound method to quantitatively assess the accuracy of any view-dependent display approach and the effects of the different error sources. This is obtained by defining a number of metrics that can be used to analyze the results of a set of experiments specially crafted to tickle different aspects of the system. This fills a clear shortcoming of the evaluation methods for 3D displays found in literature, that are, for the most part, qualitative.Many modern professional 3D display systems adopt stereo vision and viewer-dependent rendering in order to offer an immersive experience and to enable complex interaction models. Within these scenarios, the ability of the user to effectively perform a task depends both on the correct rendering of the scene and on his ability to perceive it. These factors, in turn, are affected by several error sources, such as accuracy of the user position estimation or lags between tracking and rendering. With this paper, we introduce a practical and sound method to quantitatively assess the accuracy of any view-dependent display approach and the effects of the different error sources. This is obtained by defining a number of metrics that can be used to analyze the results of a set of experiments specially crafted to tickle different aspects of the system. This fills a clear shortcoming of the evaluation methods for 3D displays found in literature, that are, for the most part, qualitative
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
- …
