Search For:

Displaying 1-40 out of 40 total
Temporal Poselets for Collective Activity Detection and Recognition
Found in: 2013 IEEE International Conference on Computer Vision Workshops (ICCVW)
By Moin Nabi,Alessio Del Bue,Vittorio Murino
Issue Date:December 2013
pp. 500-507
Detection and recognition of collective human activities are important modules of any system devoted to high level social behavior analysis. In this paper, we present a novel semantic-based spatio-temporal descriptor which can cope with several interacting...
 
Trusting Skype: Learning the Way People Chat for Fast User Recognition and Verification
Found in: 2013 IEEE International Conference on Computer Vision Workshops (ICCVW)
By Giorgio Roffo,Marco Cristani,Loris Bazzani,Ha Quang Minh,Vittorio Murino
Issue Date:December 2013
pp. 748-754
Identity safekeeping on chats has recently become an important problem on social networks. One of the most important issues is identity theft, where impostors steal the identity of a person, substituting her in the chats, in order to have access to private...
 
Dirichlet Process Mixtures of Multinomials for Data Mining in Mice Behaviour Analysis
Found in: 2013 IEEE International Conference on Computer Vision Workshops (ICCVW)
By Matteo Zanotto,Diego Sona,Vittorio Murino,Francesco Papaleo
Issue Date:December 2013
pp. 197-202
Automatic analysis of rodents behaviour has received growing attention in recent years as rodents are the reference species for large scale pharmacological and genetic screenings. In this paper we propose a new method to identify prototypical high-level be...
 
Heterogeneous Auto-similarities of Characteristics (HASC): Exploiting Relational Information for Classification
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Marco San,Marco Crocco,Marco Cristani,Samuele Martelli,Vittorio Murino
Issue Date:December 2013
pp. 809-816
Capturing the essential characteristics of visual objects by considering how their features are inter-related is a recent philosophy of object classification. In this paper, we embed this principle in a novel image descriptor, dubbed Heterogeneous Auto-Sim...
 
Multi-view Photometric Stereo Using Semi-isometric Mappings
Found in: 2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT)
By Reza Sabzevari,Alessio Del Bue,Vittorio Murino
Issue Date:October 2012
pp. 547-554
Classical uncalibrated Photometric Stereo approaches are moslty constrained to the static view assumption that enforces the camera to be fixed in front of an object illuminated by different light sources. Attempts to extend PS to multi-views has delivered ...
 
Stereo-Based Framework for Pedestrian Detection with Partial Occlusion Handling
Found in: 2012 9th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
By Samuele Martelli,Marco Cristani,Vittorio Murino
Issue Date:September 2012
pp. 25-30
The pedestrian detection literature has been recently extended by the availability of large-scale multisensory datasets, able to capture complementary aspects of the objects of interest, namely, appearance, motion, and depth. In this paper, we exploit this...
 
Biomarker Evaluation by Multiple Kernel Learning for Schizophrenia Detection
Found in: 2012 2nd International Workshop on Pattern Recognition in NeuroImaging (PRNI)
By Aydin Ulas,Umberto Castellani,Vittorio Murino,Marcella Bellani,Michele Tansella,Paolo Brambilla
Issue Date:July 2012
pp. 89-92
In this paper, we use the promising paradigm of Multiple Kernel Learning (MKL) to challenge the problem of biomarker evaluation for schizophrenia detection. We use eight different Regions of Interest (ROIs) extracted from Magnetic Resonance Images (MRIs). ...
 
Free Energy Score Spaces: Using Generative Information in Discriminative Classifiers
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Alessandro Perina,Marco Cristani,Umberto Castellani,Vittorio Murino,Nebojsa Jojic
Issue Date:July 2012
pp. 1249-1262
A score function induced by a generative model of the data can provide a feature vector of a fixed dimension for each data sample. Data samples themselves may be of differing lengths (e.g., speech segments or other sequential data), but as a score function...
 
Statistical 3D Shape Analysis by Local Generative Descriptors
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Umberto Castellani,Marco Cristani,Vittorio Murino
Issue Date:December 2011
pp. 2555-2560
In this paper, we propose a new approach for surface representation. Generative models are exploited for encoding the variations of local geometric properties of 3D shapes. Surfaces are locally modeled as a stochastic process which spans a neighborhood are...
 
Multiple-Shot Person Re-identification by HPE Signature
Found in: Pattern Recognition, International Conference on
By Loris Bazzani, Marco Cristani, Alessandro Perina, Michela Farenzena, Vittorio Murino
Issue Date:August 2010
pp. 1413-1416
In this paper, we propose a novel appearance-based method for person re-identification, that condenses a set of frames of the same individual into a highly informative signature, called Histogram Plus Epitome, HPE. It incorporates complementary global and ...
 
2D Shape Recognition Using Information Theoretic Kernels
Found in: Pattern Recognition, International Conference on
By Manuele Bicego, André Filipe Torres Martins, Vittorio Murino, Pedro M.Q. Aguiar, Mário A.T. Figueiredo
Issue Date:August 2010
pp. 25-28
In this paper, a novel approach for contour based 2D shape recognition is proposed, using a class of information theoretic kernels recently introduced. This kind of kernels, based on a non-extensive generalization of the classical Shannon information theor...
 
Nonlinear Mappings for Generative Kernels on Latent Variable Models
Found in: Pattern Recognition, International Conference on
By Anna Carli, Manuele Bicego, Sisto Baldo, Vittorio Murino
Issue Date:August 2010
pp. 2134-2137
Generative kernels have emerged in the last years as an effective method for mixing discriminative and generative approaches. In particular, in this paper, we focus on kernels defined on generative models with latent variables (e.g. the states in a Hidden ...
 
2LDA: Segmentation for Recognition
Found in: Pattern Recognition, International Conference on
By Alessandro Perina, Marco Cristani, Vittorio Murino
Issue Date:August 2010
pp. 995-998
Following the trend of “segmentation for recognition”, we present 2LDA, a novel generative model to automatically segment an image in 2 segments, background and foreground, while inferring a latent Dirichlet allocation (LDA) topic distribution on both segm...
 
A Re-evaluation of Pedestrian Detection on Riemannian Manifolds
Found in: Pattern Recognition, International Conference on
By Diego Tosato, Michela Farenzena, Marco Cistani, Vittorio Murino
Issue Date:August 2010
pp. 3308-3311
Boosting covariance data on Riemannian manifolds has proven to be a convenient strategy in a pedestrian detection context. In this paper we show that the detection performances of the state-of-the-art approach of Tuzel et al. [7] can be greatly improved, f...
 
An FPGA-based Classification Architecture on Riemannian Manifolds
Found in: Database and Expert Systems Applications, International Workshop on
By Samuele Martelli, Diego Tosato, Michela Farenzena, Marco Cristani, Vittorio Murino
Issue Date:September 2010
pp. 215-220
In Computer Vision and Pattern Recognition, the object detection problem is a fundamental task, but only a few systems are thought to be realized on an embedded architecture. To this end, we propose an effective, low-latency, affordable classification arch...
 
Sparseness Achievement in Hidden Markov Models
Found in: Image Analysis and Processing, International Conference on
By Manuele Bicego, Marco Cristani, Vittorio Murino
Issue Date:September 2007
pp. 67-72
In this paper, a novel learning algorithm for Hidden Markov Models (HMMs) has been devised. The key issue is the achievement of a sparse model, i.e., a model in which all irrelevant parameters are set exactly to zero. Alternatively to standard Maximum Like...
 
Video Objects Segmentation by Robust Background Modeling
Found in: Image Analysis and Processing, International Conference on
By Andrea Colombari, Andrea Fusiello, Vittorio Murino
Issue Date:September 2007
pp. 155-164
This paper deals with the problem of segmenting a video shot into a background (still) mosaic and one or more foreground moving objects. The method is based on ego-motion compensation and background estimation. In order to be able to cope with sequences wh...
 
Adaptive Feature Integration for Segmentation of 3D Data by Unsupervised Density Estimation
Found in: Pattern Recognition, International Conference on
By Marco Cristani, Umberto Castellani, Vittorio Murino
Issue Date:August 2006
pp. 21-24
In this paper, a novel unsupervised approach for the segmentation of unorganized 3D points sets is proposed. The method derives by the mean shift clustering paradigm devoted to separate the modes of a multimodal density by using a kernel-based technique. H...
 
Audio-Visual Foreground Extraction for Event Characterization
Found in: Computer Vision and Pattern Recognition Workshop
By Marco Cristani, Manuele Bicego, Vittorio Murino
Issue Date:June 2006
pp. 116
This paper presents a new method able to integrate audio and visual information for scene analysis in a typical surveillance scenario, using only one camera and one monaural microphone. Visual information is analyzed by a standard visual background/foregro...
 
Background Initialization in Cluttered Sequences
Found in: Computer Vision and Pattern Recognition Workshop
By Andrea Colombari, Andrea Fusiello, Vittorio Murino
Issue Date:June 2006
pp. 197
In this paper we propose a technique to robustly estimate the background in a cluttered sequence, i.e., a sequence where occluding objects persist in the same position for a considerable portion of time. As pixel-level heuristic are not sufficient in this ...
 
Augmented Scene Modeling and Visualization by Optical and Acoustic Sensor Integration
Found in: IEEE Transactions on Visualization and Computer Graphics
By Andrea Fusiello, Vittorio Murino
Issue Date:November 2004
pp. 625-636
In this paper, underwater scene modeling from multisensor data is addressed. Acoustic and optical devices aboard an underwater vehicle are used to sense the environment in order to produce an output that is readily understandable even by an inexperienced o...
 
Robust 3D Segmentation for Underwater Acoustic Images
Found in: 3D Data Processing Visualization and Transmission, International Symposium on
By Linmi Tao, Umberto Castellani, Vittorio Murino
Issue Date:September 2004
pp. 813-819
In this paper, a new technique for 3D acoustic image segmentation and modelling is proposed. Especially, in the underwater environment, in which optical sensors suffer from visibility problems, the acoustical devices may provide efficient solutions, but, o...
 
On-Line Adaptive Background Modelling for Audio Surveillance
Found in: Pattern Recognition, International Conference on
By Marco Cristani, Manuele Bicego, Vittorio Murino
Issue Date:August 2004
pp. 399-402
In this paper, we investigate the problem of automatic audio surveillance. This aspect of the surveillance, which extends the more investigated area of video surveillance, can be very informative to solve many problems in real situations. Similarly to vide...
 
Statistical Classification of Raw Textile Defects
Found in: Pattern Recognition, International Conference on
By Vittorio Murino, Manuele Bicego, Ivan A. Rossi
Issue Date:August 2004
pp. 311-314
In this paper, the problem of classification of defects occurring in a textile manufacture is addressed. A new classification scheme is devised in which different features, extracted from the gray level histogram, the shape, and co-occurrence matrices, are...
 
High Resolution Video Mosaicing with Global Alignment
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Roberto Marzotto, Andrea Fusiello, Vittorio Murino
Issue Date:July 2004
pp. 692-698
Image composition (or mosaicing) has attracted a growing attention in recent years as one of the main elements in video analysis and representation. In this paper we deal with the problem of global alignment and super-resolution. We also propose to evaluat...
 
Investigating Hidden Markov Models' Capabilities in 2D Shape Classification
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Manuele Bicego, Vittorio Murino
Issue Date:January 2004
pp. 281-286
<p><b>Abstract</b>—In this paper, Hidden Markov Models (HMMs) are investigated for the purpose of classifying planar shapes represented by their curvature coefficients. In the training phase, special attention is devoted to the initializa...
 
A Tensor Voting Approach for the Hierarchical Segmentation of 3-D Acoustic Images
Found in: 3D Data Processing Visualization and Transmission, International Symposium on
By Linmi Tao, Vittorio Murino, Gérard Medioni
Issue Date:June 2002
pp. 126
We present a hierarchical and robust algorithm addressing the problem of filtering and segmentation of three-dimensional acoustic images. This algorithm is based on the tensor voting approach — a unified computational framework for the inference of multipl...
 
2D Shape Recognition by Hidden Markov Models
Found in: Image Analysis and Processing, International Conference on
By Manuele Bicego, Vittorio Murino
Issue Date:September 2001
pp. 0020
Abstract: In Computer Vision, two-dimensional shape classification is a complex and well studied topic, often basic for three-dimensional object recognition. Object contours are a widely chosen feature for representing objects, useful in many respects for ...
 
Model Tracking for Video-Based Virtual Reality
Found in: Image Analysis and Processing, International Conference on
By Alberto Valinetti, Andrea Fusiello, Vittorio Murino
Issue Date:September 2001
pp. 0372
Abstract: This paper presents a technique for tracking complex objects (both polyhedral and smooth boundaries) in a monocular sequence. Our aim is to use this model tracking method in an Augmented Reality context to compute the pose of a real object to be ...
 
3D Mosaicing for Environment Reconstruction
Found in: Pattern Recognition, International Conference on
By Vittorio Murino, Andrea Fusiello, Nicola Iuretigh, Enrico Puppo
Issue Date:September 2000
pp. 3362
This paper proposes a technique for the three-dimensional reconstruction of an underwater environment from multiple range views. The final target of the work lies in improving the understanding of a human operator guiding an underwater remotely operated ve...
 
Augmented Representation of Underwater Scenes by Segmentation and Reconstruction of 3D Acoustic Images
Found in: Multimedia Computing and Systems, International Conference on
By Riccardo Giannitrapani, Vittorio Murino
Issue Date:June 1999
pp. 1036
In this paper, a system aimed at the augmented representation of underwater scenes is presented. The system operates on three-dimensional acoustic images and is composed of several modules devoted to noise filtering, segmentation in pipe-shaped structures,...
 
A Probabilistic Approach to the Coupled Reconstruction and Restoration of Underwater Acoustic Images
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Vittorio Murino, Andrea Trucco, Carlo S. Regazzoni
Issue Date:January 1998
pp. 9-22
<p><b>Abstract</b>—This paper describes a probabilistic technique for the coupled reconstruction and restoration of underwater acoustic images. The technique is founded on the physics of the image-formation process. Beamforming, a method ...
 
Information theoretic sensor management for multi-target tracking with a single pan-tilt-zoom camera
Found in: 2014 IEEE Winter Conference on Applications of Computer Vision (WACV)
By Pietro Salvagnini,Federico Pernici,Marco Cristani,Giuseppe Lisanti,Iacopo Masi,Alberto Del Bimbo,Vittorio Murino
Issue Date:March 2014
pp. 893-900
Automatic multiple target tracking with pan-tilt-zoom (PTZ) cameras is a hard task, with few approaches in the literature, most of them proposing simplistic scenarios. In this paper, we present a PTZ camera management framework which lies on information th...
   
Reading between the turns: Statistical modeling for identity recognition and verification in chats
Found in: 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
By Giorgio Roffo,Cristina Segalin,Alessandro Vinciarelli,Vittorio Murino,Marco Cristani
Issue Date:August 2013
pp. 99-104
Identity safekeeping has recently become an important problem for the social web: as a case study, we focus here on instant messaging platforms, proposing novel soft-biometric cues for user recognition and verification. Specifically, we design a set of fea...
   
Semi-supervised multi-feature learning for person re-identification
Found in: 2013 10th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
By Dario Figueira,Loris Bazzani,Ha Quang Minh,Marco Cristani,Alexandre Bernardino,Vittorio Murino
Issue Date:August 2013
pp. 111-116
Person re-identification is probably the open challenge for low-level video surveillance in the presence of a camera network with non-overlapped fields of view. A large number of direct approaches has emerged in the last five years, often proposing novel v...
   
Automatic Tractography Analysis through Sparse Networks in Case-Control Studies
Found in: 2012 2nd International Workshop on Pattern Recognition in NeuroImaging (PRNI)
By Luca Giancardo,Diego Sona,Alessadro Gozzi,Angelo Bifone,Vittorio Murino,Sara Migliarini,Giulia Pacini,Barbara Pelosi,Massimo Pasqualetti
Issue Date:July 2012
pp. 77-80
Magnetic Resonance Diffusion Tensor Imaging (DTI) has opened the way to a variety of white matter analysis approaches which leverage the axon networks in the brain. Even if tractography algorithms are widely used to reconstruct these networks, their topolo...
 
Investigating Topic Models' Capabilities in Expression Microarray Data Classification
Found in: IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
By Alessandro Perina, Annalisa Polverari, Manuele Bicego, Marianna Fasoli, Mario Pezzotti, Massimo Delledonne, Pietro Lovato, Vittorio Murino
Issue Date:November 2012
pp. 1831-1836
In recent years a particular class of probabilistic graphical models—called topic models—has proven to represent an useful and interpretable tool for understanding and mining microarray data. In this context, such models have been almost only...
     
Pervasive video analysis: workshop overview
Found in: Proceedings of the international conference on Multimedia (MM '10)
By Hamid Aghajan, Marco Cristani, Nicu Sebe, Vittorio Murino
Issue Date:October 2010
pp. 1753-1754
This workshop aims at tackling the novel challenging scenarios in pervasive video analysis which require not only to address specific problems (e.g., tracking, recognition) on a single view, but to deal with a set of distributed observations, eventually in...
     
Content visualization and management of geo-located image databases
Found in: CHI '08 extended abstracts on Human factors in computing systems (CHI '08)
By Alessandro Perina, Marco Cristani, Umberto Castellani, Vittorio Murino
Issue Date:April 2008
pp. 49-54
In the last years, several algorithms and platforms for photo sharing have been developed. Usually, in order to index huge quantities of images for a fast and intuitive retrieval, additional textual tags attached to the pictures are considered. In this pap...
     
Distilling information with super-resolution for video surveillance
Found in: Proceedings of the ACM 2nd international workshop on Video surveillance & sensor networks (VSSN '04)
By Donato Pannullo, Dong Seon Cheng, Marco Cristani, Vittorio Murino
Issue Date:October 2004
pp. 2-11
A video surveillance sequence generally contains a lot of scattered information regarding several objects in cluttered scenes. Especially in case of use of digital hand-held cameras, the overall quality is very low due to the unstable motion and the low re...
     
 1