Publicacions CVC -- Query Results

	Publicacions CVC Home \| Show All \| Simple Search \| Advanced Search \| Add Record \| Import	Login Quick Search: Field: contains: ...
	676–690 of 3413 records found matching your query (RSS \| history):

Search & Display Options

Select All Deselect All

[31–40] << 41 42 43 44 45 46 47 48 49 50 >> [51–60]

List View

Citations

Details

	Records
	Author	Adriana Romero; Carlo Gatta; Gustavo Camps-Valls
	Title	Unsupervised Deep Feature Extraction Of Hyperspectral Images			Type	Conference Article
	Year	2014	Publication	6th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing	Abbreviated Journal
	Volume		Issue		Pages
	Keywords	Convolutional networks; deep learning; sparse learning; feature extraction; hyperspectral image classification
	Abstract	This paper presents an effective unsupervised sparse feature learning algorithm to train deep convolutional networks on hyperspectral images. Deep convolutional hierarchical representations are learned and then used for pixel classification. Features in lower layers present less abstract representations of data, while higher layers represent more abstract and complex characteristics. We successfully illustrate the performance of the extracted representations in a challenging AVIRIS hyperspectral image classification problem, compared to standard dimensionality reduction methods like principal component analysis (PCA) and its kernel counterpart (kPCA). The proposed method largely outperforms the previous state-ofthe-art results on the same experimental setting. Results show that single layer networks can extract powerful discriminative features only when the receptive field accounts for neighboring pixels. Regarding the deep architecture, we can conclude that: (1) additional layers in a deep architecture significantly improve the performance w.r.t. single layer variants; (2) the max-pooling step in each layer is mandatory to achieve satisfactory results; and (3) the performance gain w.r.t. the number of layers is upper bounded, since the spatial resolution is reduced at each pooling, resulting in too spatially coarse output features.
	Address	Lausanne; Switzerland; June 2014
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference	WHISPERS
	Notes	MILAB; LAMP; 600.079			Approved	no
	Call Number	Admin @ si @ RGC2014			Serial	2513
Permanent link to this record



	Author	Petia Radeva; Enric Marti
	Title	Facial Features Segmentation by Model-Based Snakes.			Type	Miscellaneous
	Year	1995	Publication	Trobada de Joves Investigadors, IIIA.	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract
	Address	Bellaterra (Barcelona), Spain
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference
	Notes	MILAB; IAM			Approved	no
	Call Number	BCNPCL @ bcnpcl @ RaM1995a			Serial	130
Permanent link to this record



	Author	Santiago Segui; Oriol Pujol; Jordi Vitria
	Title	Learning to count with deep object features			Type	Conference Article
	Year	2015	Publication	Deep Vision: Deep Learning in Computer Vision, CVPR 2015 Workshop	Abbreviated Journal
	Volume		Issue		Pages	90-96
	Keywords
	Abstract	Learning to count is a learning strategy that has been recently proposed in the literature for dealing with problems where estimating the number of object instances in a scene is the final objective. In this framework, the task of learning to detect and localize individual object instances is seen as a harder task that can be evaded by casting the problem as that of computing a regression value from hand-crafted image features. In this paper we explore the features that are learned when training a counting convolutional neural network in order to understand their underlying representation. To this end we define a counting problem for MNIST data and show that the internal representation of the network is able to classify digits in spite of the fact that no direct supervision was provided for them during training. We also present preliminary results about a deep network that is able to count the number of pedestrians in a scene.
	Address	Boston; USA; June 2015
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference	CVPRW
	Notes	MILAB; HuPBA; OR;MV			Approved	no
	Call Number	Admin @ si @ SPV2015			Serial	2636
Permanent link to this record



	Author	Sergio Escalera; Josep Moya; Laura Igual; Veronica Violant; Maria Teresa Anguera
	Title	Análisis Comportamental Automatizado de TDAH: la Influencia de la Variable Motivación			Type	Conference Article
	Year	2012	Publication	IPSI – Cosmocaixa, Jornadas "Empremtes del present, efectes en la psicoanàlisi, la cultura i la societat	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	Poster
	Address
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference	IPSI
	Notes	MILAB; HuPBA; OR			Approved	no
	Call Number	Admin @ si @ EMI2012b			Serial	2065
Permanent link to this record



	Author	Xavier Perez Sala; Fernando De la Torre; Laura Igual; Sergio Escalera; Cecilio Angulo
	Title	Subspace Procrustes Analysis			Type	Journal Article
	Year	2017	Publication	International Journal of Computer Vision	Abbreviated Journal	IJCV
	Volume	121	Issue	3	Pages	327–343
	Keywords
	Abstract	Procrustes Analysis (PA) has been a popular technique to align and build 2-D statistical models of shapes. Given a set of 2-D shapes PA is applied to remove rigid transformations. Then, a non-rigid 2-D model is computed by modeling (e.g., PCA) the residual. Although PA has been widely used, it has several limitations for modeling 2-D shapes: occluded landmarks and missing data can result in local minima solutions, and there is no guarantee that the 2-D shapes provide a uniform sampling of the 3-D space of rotations for the object. To address previous issues, this paper proposes Subspace PA (SPA). Given several instances of a 3-D object, SPA computes the mean and a 2-D subspace that can simultaneously model all rigid and non-rigid deformations of the 3-D object. We propose a discrete (DSPA) and continuous (CSPA) formulation for SPA, assuming that 3-D samples of an object are provided. DSPA extends the traditional PA, and produces unbiased 2-D models by uniformly sampling different views of the 3-D object. CSPA provides a continuous approach to uniformly sample the space of 3-D rotations, being more efficient in space and time. Experiments using SPA to learn 2-D models of bodies from motion capture data illustrate the benefits of our approach.
	Address
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference
	Notes	MILAB; HuPBA; no proj			Approved	no
	Call Number	Admin @ si @ PTI2017			Serial	2841
Permanent link to this record



	Author	Francesco Ciompi; Rui Hua; Simone Balocco; Marina Alberti; Oriol Pujol; Carles Caus; Josepa Mauri; Petia Radeva
	Title	Learning to Detect Stent Struts in Intravascular Ultrasound			Type	Conference Article
	Year	2013	Publication	6th Iberian Conference on Pattern Recognition and Image Analysis	Abbreviated Journal
	Volume	7887	Issue		Pages	575-583
	Keywords
	Abstract	In this paper we tackle the automatic detection of struts elements (metallic braces of a stent device) in Intravascular Ultrasound (IVUS) sequences. The proposed method is based on context-aware classification of IVUS images, where we use Multi-Class Multi-Scale Stacked Sequential Learning (M2SSL). Additionally, we introduce a novel technique to reduce the amount of required contextual features. The comparison with binary and multi-class learning is also performed, using a dataset of IVUS images with struts manually annotated by an expert. The best performing configuration reaches a F-measure F = 63.97% .
	Address	Madeira; Portugal; June 2013
	Corporate Author				Thesis
	Publisher	Springer Berlin Heidelberg	Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN	0302-9743	ISBN	978-3-642-38627-5	Medium
	Area		Expedition		Conference	IbPRIA
	Notes	MILAB; HuPBA; 605.203; 600.046			Approved	no
	Call Number	Admin @ si @ CHB2013			Serial	2349
Permanent link to this record



	Author	Sergio Escalera
	Title	Fast traffic model matching and recognition on gray-scale images			Type	Report
	Year	2005	Publication	CVC Technical Report #84	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract
	Address	CVC (UAB)
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference
	Notes	MILAB; HuPBA			Approved	no
	Call Number	BCNPCL @ bcnpcl @ Esc2005			Serial	572
Permanent link to this record



	Author	Sergio Escalera
	Title	Coding and Decoding Design of ECOCs for Multi-Class Pattern and Object Recognition			Type	Miscellaneous
	Year	2008	Publication		Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract
	Address
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference
	Notes	MILAB; HuPBA			Approved	no
	Call Number	BCNPCL @ bcnpcl @ Esc2008a			Serial	1106
Permanent link to this record



	Author	Maria Salamo; Sergio Escalera
	Title	Increasing Retrieval Quality in Conversational Recommenders			Type	Journal Article
	Year	2011	Publication	IEEE Transactions on Knowledge and Data Engineering	Abbreviated Journal	TKDE
	Volume	99	Issue		Pages	1-1
	Keywords
	Abstract	IF JCR CCIA 2.286 2009 24/103 JCR Impact Factor 2010: 1.851 A major task of research in conversational recommender systems is personalization. Critiquing is a common and powerful form of feedback, where a user can express her feature preferences by applying a series of directional critiques over the recommendations instead of providing speciﬁc preference values. Incremental Critiquing is a conversational recommender system that uses critiquing as a feedback to efﬁciently personalize products. The expectation is that in each cycle the system retrieves the products that best satisfy the user’s soft product preferences from a minimal information input. In this paper, we present a novel technique that increases retrieval quality based on a combination of compatibility and similarity scores. Under the hypothesis that a user learns Turing the recommendation process, we propose two novel exponential reinforcement learning approaches for compatibility that take into account both the instant at which the user makes a critique and the number of satisﬁed critiques. Moreover, we consider that the impact of features on the similarity differs according to the preferences manifested by the user. We propose a global weighting approach that uses a common weight for nearest cases in order to focus on groups of relevant products. We show that our methodology signiﬁcantly improves recommendation efﬁciency in four data sets of different sizes in terms of session length in comparison with state-of-the-art approaches. Moreover, our recommender shows higher robustness against noisy user data when compared to classical approaches
	Address
	Corporate Author				Thesis
	Publisher	IEEE	Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN	1041-4347	ISBN		Medium
	Area		Expedition		Conference
	Notes	MILAB; HuPBA			Approved	no
	Call Number	Admin @ si @ SaE2011			Serial	1713
Permanent link to this record



	Author	Oscar Amoros; Sergio Escalera; Anna Puig
	Title	Adaboost GPU-based Classifier for Direct Volume Rendering			Type	Conference Article
	Year	2011	Publication	International Conference on Computer Graphics Theory and Applications	Abbreviated Journal
	Volume		Issue		Pages	215-219
	Keywords
	Abstract	In volume visualization, the voxel visibitity and materials are carried out through an interactive editing of Transfer Function. In this paper, we present a two-level GPU-based labeling method that computes in times of rendering a set of labeled structures using the Adaboost machine learning classifier. In a pre-processing step, Adaboost trains a binary classifier from a pre-labeled dataset and, in each sample, takes into account a set of features. This binary classifier is a weighted combination of weak classifiers, which can be expressed as simple decision functions estimated on a single feature values. Then, at the testing stage, each weak classifier is independently applied on the features of a set of unlabeled samples. We propose an alternative representation of these classifiers that allow a GPU-based parallelizated testing stage embedded into the visualization pipeline. The empirical results confirm the OpenCL-based classification of biomedical datasets as a tough problem where an opportunity for further research emerges.
	Address	Algarve, Portugal
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference	GRAPP
	Notes	MILAB; HuPBA			Approved	no
	Call Number	Admin @ si @ AEP2011			Serial	1774
Permanent link to this record



	Author	Sergio Escalera; Ana Puig; Oscar Amoros; Maria Salamo
	Title	Intelligent GPGPU Classification in Volume Visualization: a framework based on Error-Correcting Output Codes			Type	Journal Article
	Year	2011	Publication	Computer Graphics Forum	Abbreviated Journal	CGF
	Volume	30	Issue	7	Pages	2107-2115
	Keywords
	Abstract	IF JCR 1.455 2010 25/99 In volume visualization, the definition of the regions of interest is inherently an iterative trial-and-error process finding out the best parameters to classify and render the final image. Generally, the user requires a lot of expertise to analyze and edit these parameters through multi-dimensional transfer functions. In this paper, we present a framework of intelligent methods to label on-demand multiple regions of interest. These methods can be split into a two-level GPU-based labelling algorithm that computes in time of rendering a set of labelled structures using the Machine Learning Error-Correcting Output Codes (ECOC) framework. In a pre-processing step, ECOC trains a set of Adaboost binary classifiers from a reduced pre-labelled data set. Then, at the testing stage, each classifier is independently applied on the features of a set of unlabelled samples and combined to perform multi-class labelling. We also propose an alternative representation of these classifiers that allows to highly parallelize the testing stage. To exploit that parallelism we implemented the testing stage in GPU-OpenCL. The empirical results on different data sets for several volume structures shows high computational performance and classification accuracy.
	Address
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference
	Notes	MILAB; HuPBA			Approved	no
	Call Number	Admin @ si @ EPA2011			Serial	1881
Permanent link to this record



	Author	Antonio Hernandez; Carlos Primo; Sergio Escalera
	Title	Automatic user interaction correction via Multi-label Graph cuts			Type	Conference Article
	Year	2011	Publication	In ICCV 2011 1st IEEE International Workshop on Human Interaction in Computer Vision HICV	Abbreviated Journal
	Volume		Issue		Pages	1276-1281
	Keywords
	Abstract	Most applications in image segmentation requires from user interaction in order to achieve accurate results. However, user wants to achieve the desired segmentation accuracy reducing effort of manual labelling. In this work, we extend standard multi-label α-expansion Graph Cut algorithm so that it analyzes the interaction of the user in order to modify the object model and improve final segmentation of objects. The approach is inspired in the fact that fast user interactions may introduce some pixel errors confusing object and background. Our results with different degrees of user interaction and input errors show high performance of the proposed approach on a multi-label human limb segmentation problem compared with classical α-expansion algorithm.
	Address
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN	978-1-4673-0062-9	Medium
	Area		Expedition		Conference	HICV
	Notes	MILAB; HuPBA			Approved	no
	Call Number	Admin @ si @ HPE2011			Serial	1892
Permanent link to this record



	Author	Sergio Escalera
	Title	Human Behavior Analysis From Depth Maps			Type	Conference Article
	Year	2012	Publication	7th Conference on Articulated Motion and Deformable Objects	Abbreviated Journal
	Volume	7378	Issue		Pages	282-292
	Keywords
	Abstract	Pose Recovery (PR) and Human Behavior Analysis (HBA) have been a main focus of interest from the beginnings of Computer Vision and Machine Learning. PR and HBA were originally addressed by the analysis of still images and image sequences. More recent strategies consisted of Motion Capture technology (MOCAP), based on the synchronization of multiple cameras in controlled environments; and the analysis of depth maps from Time-of-Flight (ToF) technology, based on range image recording from distance sensor measurements. Recently, with the appearance of the multi-modal RGBD information provided by the low cost Kinect \textsfTM sensor (from RGB and Depth, respectively), classical methods for PR and HBA have been redefined, and new strategies have been proposed. In this paper, the recent contributions and future trends of multi-modal RGBD data analysis for PR and HBA are reviewed and discussed.
	Address	Mallorca
	Corporate Author				Thesis
	Publisher	Springer Heidelberg	Place of Publication		Editor	F.J. Perales; R.B. Fisher; T.B. Moeslund
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN	0302-9743	ISBN	978-3-642-31566-4	Medium
	Area		Expedition		Conference	AMDO
	Notes	MILAB; HuPBA			Approved	no
	Call Number	Admin @ si @ Esc2012			Serial	2040
Permanent link to this record



	Author	Sergio Escalera
	Title	Coding and Decoding Design of ECOCs for Multi-class Pattern and Object Recognition A			Type	Book Whole
	Year	2008	Publication	PhD Thesis, Universitat de Barcelona-CVC	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	Many real problems require multi-class decisions. In the Pattern Recognition field, many techniques have been proposed to deal with the binary problem. However, the extension of many 2-class classifiers to the multi-class case is a hard task. In this sense, Error-Correcting Output Codes (ECOC) demonstrated to be a powerful tool to combine any number of binary classifiers to model multi-class problems. But there are still many open issues about the capabilities of the ECOC framework. In this thesis, the two main stages of an ECOC design are analyzed: the coding and the decoding steps. We present different problem-dependent designs. These designs take advantage of the knowledge of the problem domain to minimize the number of classifiers, obtaining a high classification performance. On the other hand, we analyze the ECOC codification in order to define new decoding rules that take full benefit from the information provided at the coding step. Moreover, as a successful classification requires a rich feature set, new feature detection/extraction techniques are presented and evaluated on the new ECOC designs. The evaluation of the new methodology is performed on different real and synthetic data sets: UCI Machine Learning Repository, handwriting symbols, traffic signs from a Mobile Mapping System, Intravascular Ultrasound images, Caltech Repository data set or Chaga’s disease data set. The results of this thesis show that significant performance improvements are obtained on both traditional coding and decoding ECOC designs when the new coding and decoding rules are taken into account.
	Address
	Corporate Author				Thesis	Ph.D. thesis
	Publisher	Ediciones Graficas Rey	Place of Publication		Editor	Petia Radeva;Oriol Pujol
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN		Medium
	Area		Expedition		Conference
	Notes	MILAB; HuPBA			Approved	no
	Call Number	Admin @ si @ Esc2008b			Serial	2217
Permanent link to this record



	Author	Sergio Escalera; Alicia Fornes; Oriol Pujol; Josep Llados; Petia Radeva
	Title	Multi-class Binary Object Categorization using Blurred Shape Models			Type	Conference Article
	Year	2007	Publication	Progress in Pattern Recognition, Image Analysis and Applications, 12th Iberoamerican Congress on Pattern	Abbreviated Journal
	Volume	4756	Issue		Pages	773–782
	Keywords
	Abstract
	Address
	Corporate Author				Thesis
	Publisher		Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title	LCNS
	Series Volume		Series Issue		Edition
	ISSN		ISBN	978-3-540-76724-4	Medium
	Area		Expedition		Conference	CIARP
	Notes	MILAB; DAG;HuPBA			Approved	no
	Call Number	BCNPCL @ bcnpcl @ EFP2007			Serial	911
Permanent link to this record