Publicacions CVC -- Query Results

	Publicacions CVC Home \| Show All \| Simple Search \| Advanced Search \| Add Record \| Import	Login Quick Search: Field: contains: ...
	46–60 of 202 records found matching your query (RSS \| history):

Search & Display Options

Select All Deselect All

<< 1 2 3 4 5 6 7 8 9 10 >> [11–14]

List View

Citations

Details

	Records
	Author	Antonio Hernandez; Nadezhda Zlateva; Alexander Marinov; Miguel Reyes; Petia Radeva; Dimo Dimov; Sergio Escalera
	Title	Graph Cuts Optimization for Multi-Limb Human Segmentation in Depth Maps			Type	Conference Article
	Year	2012	Publication	25th IEEE Conference on Computer Vision and Pattern Recognition	Abbreviated Journal
	Volume		Issue		Pages	726-732
	Keywords
	Abstract	We present a generic framework for object segmentation using depth maps based on Random Forest and Graph-cuts theory, and apply it to the segmentation of human limbs in depth maps. First, from a set of random depth features, Random Forest is used to infer a set of label probabilities for each data sample. This vector of probabilities is used as unary term in α-β swap Graph-cuts algorithm. Moreover, depth of spatio-temporal neighboring data points are used as boundary potentials. Results on a new multi-label human depth data set show high performance in terms of segmentation overlapping of the novel methodology compared to classical approaches.
	Address	Portland; Oregon; June 2013
	Corporate Author				Thesis
	Publisher	IEEE Xplore	Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN	1063-6919	ISBN	978-1-4673-1226-4	Medium
	Area		Expedition		Conference	CVPR
	Notes	MILAB;HuPBA			Approved	no
	Call Number	Admin @ si @ HZM2012b			Serial	2046
Permanent link to this record



	Author	Volkmar Frinken; Francisco Zamora; Salvador España; Maria Jose Castro; Andreas Fischer; Horst Bunke
	Title	Long-Short Term Memory Neural Networks Language Modeling for Handwriting Recognition			Type	Conference Article
	Year	2012	Publication	21st International Conference on Pattern Recognition	Abbreviated Journal
	Volume		Issue		Pages	701-704
	Keywords
	Abstract	Unconstrained handwritten text recognition systems maximize the combination of two separate probability scores. The first one is the observation probability that indicates how well the returned word sequence matches the input image. The second score is the probability that reflects how likely a word sequence is according to a language model. Current state-of-the-art recognition systems use statistical language models in form of bigram word probabilities. This paper proposes to model the target language by means of a recurrent neural network with long-short term memory cells. Because the network is recurrent, the considered context is not limited to a fixed size especially as the memory cells are designed to deal with long-term dependencies. In a set of experiments conducted on the IAM off-line database we show the superiority of the proposed language model over statistical n-gram models.
	Address	Tsukuba Science City, Japan
	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	1051-4651	ISBN	978-1-4673-2216-4	Medium
	Area		Expedition		Conference	ICPR
	Notes	DAG			Approved	no
	Call Number	Admin @ si @ FZE2012			Serial	2052
Permanent link to this record



	Author	Arjan Gijsenij; R. Lu; Theo Gevers; De Xu
	Title	Color Constancy for Multiple Light Source			Type	Journal Article
	Year	2012	Publication	IEEE Transactions on Image Processing	Abbreviated Journal	TIP
	Volume	21	Issue	2	Pages	697-707
	Keywords
	Abstract	Impact factor 2010: 2.92 Impact factor 2011/2012?: 3.32 Color constancy algorithms are generally based on the simplifying assumption that the spectral distribution of a light source is uniform across scenes. However, in reality, this assumption is often violated due to the presence of multiple light sources. In this paper, we will address more realistic scenarios where the uniform light-source assumption is too restrictive. First, a methodology is proposed to extend existing algorithms by applying color constancy locally to image patches, rather than globally to the entire image. After local (patch-based) illuminant estimation, these estimates are combined into more robust estimations, and a local correction is applied based on a modified diagonal model. Quantitative and qualitative experiments on spectral and real images show that the proposed methodology reduces the influence of two light sources simultaneously present in one scene. If the chromatic difference between these two illuminants is more than 1° , the proposed framework outperforms algorithms based on the uniform light-source assumption (with error-reduction up to approximately 30%). Otherwise, when the chromatic difference is less than 1° and the scene can be considered to contain one (approximately) uniform light source, the performance of the proposed method framework is similar to global color constancy methods.
	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	1057-7149	ISBN		Medium
	Area		Expedition		Conference
	Notes	ALTRES;ISE			Approved	no
	Call Number	Admin @ si @ GLG2012a			Serial	1852
Permanent link to this record



	Author	Marina Alberti; Simone Balocco; Xavier Carrillo; J. Mauri; Petia Radeva
	Title	Automatic Non-Rigid Temporal Alignment of IVUS Sequences			Type	Conference Article
	Year	2012	Publication	15th International Conference on Medical Image Computing and Computer Assisted Intervention	Abbreviated Journal
	Volume	1	Issue		Pages	642-650
	Keywords
	Abstract	Clinical studies on atherosclerosis regression/progression performed by Intravascular Ultrasound analysis require the alignment of pullbacks of the same patient before and after clinical interventions. In this paper, a methodology for the automatic alignment of IVUS sequences based on the Dynamic Time Warping technique is proposed. The method is adapted to the specific IVUS alignment task by applying the non-rigid alignment technique to multidimensional morphological signals, and by introducing a sliding window approach together with a regularization term. To show the effectiveness of our method, an extensive validation is performed both on synthetic data and in-vivo IVUS sequences. The proposed method is robust to stent deployment and post dilation surgery and reaches an alignment error of approximately 0.7 mm for in-vivo data, which is comparable to the inter-observer variability.
	Address	Nice, France
	Corporate Author				Thesis
	Publisher	Springer-Verlag Berlin, Heidelberg	Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN	978-3-642-33414-6	Medium
	Area		Expedition		Conference	MICCAI
	Notes	MILAB			Approved	no
	Call Number	Admin @ si @ ABC2012			Serial	2168
Permanent link to this record



	Author	Naila Murray; Sandra Skaff; Luca Marchesotti; Florent Perronnin
	Title	Towards automatic and flexible concept transfer			Type	Journal Article
	Year	2012	Publication	Computers and Graphics	Abbreviated Journal	CG
	Volume	36	Issue	6	Pages	622–634
	Keywords
	Abstract	This paper introduces a novel approach to automatic, yet flexible, image concepttransfer; examples of concepts are “romantic”, “earthy”, and “luscious”. The presented method modifies the color content of an input image given only a concept specified by a user in natural language, thereby requiring minimal user input. This method is particularly useful for users who are aware of the message they wish to convey in the transferred image while being unsure of the color combination needed to achieve the corresponding transfer. Our framework is flexible for two reasons. First, the user may select one of two modalities to map input image chromaticities to target concept chromaticities depending on the level of photo-realism required. Second, the user may adjust the intensity level of the concepttransfer to his/her liking with a single parameter. The proposed method uses a convex clustering algorithm, with a novel pruning mechanism, to automatically set the complexity of models of chromatic content. Results show that our approach yields transferred images which effectively represent concepts as confirmed by a user study.
	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	0097-8493	ISBN		Medium
	Area		Expedition		Conference
	Notes	CIC			Approved	no
	Call Number	Admin @ si @ MSM2012			Serial	2002
Permanent link to this record



	Author	Volkmar Frinken; Alicia Fornes; Josep Llados; Jean-Marc Ogier
	Title	Bidirectional Language Model for Handwriting Recognition			Type	Conference Article
	Year	2012	Publication	Structural, Syntactic, and Statistical Pattern Recognition, Joint IAPR International Workshop	Abbreviated Journal
	Volume	7626	Issue		Pages	611-619
	Keywords
	Abstract	In order to improve the results of automatically recognized handwritten text, information about the language is commonly included in the recognition process. A common approach is to represent a text line as a sequence. It is processed in one direction and the language information via n-grams is directly included in the decoding. This approach, however, only uses context on one side to estimate a word’s probability. Therefore, we propose a bidirectional recognition in this paper, using distinct forward and a backward language models. By combining decoding hypotheses from both directions, we achieve a significant increase in recognition accuracy for the off-line writer independent handwriting recognition task. Both language models are of the same type and can be estimated on the same corpus. Hence, the increase in recognition accuracy comes without any additional need for training data or language modeling complexity.
	Address	Japan
	Corporate Author				Thesis
	Publisher	Springer Berlin Heidelberg	Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title	LNCS
	Series Volume		Series Issue		Edition
	ISSN	0302-9743	ISBN	978-3-642-34165-6	Medium
	Area		Expedition		Conference	SSPR&SPR
	Notes	DAG			Approved	no
	Call Number	Admin @ si @ FFL2012			Serial	2057
Permanent link to this record



	Author	Jose Carlos Rubio; Joan Serrat; Antonio Lopez; Daniel Ponsa
	Title	Multiple target tracking for intelligent headlights control			Type	Journal Article
	Year	2012	Publication	IEEE Transactions on Intelligent Transportation Systems	Abbreviated Journal	TITS
	Volume	13	Issue	2	Pages	594-605
	Keywords	Intelligent Headlights
	Abstract	Intelligent vehicle lighting systems aim at automatically regulating the headlights' beam to illuminate as much of the road ahead as possible while avoiding dazzling other drivers. A key component of such a system is computer vision software that is able to distinguish blobs due to vehicles' headlights and rear lights from those due to road lamps and reflective elements such as poles and traffic signs. In a previous work, we have devised a set of specialized supervised classifiers to make such decisions based on blob features related to its intensity and shape. Despite the overall good performance, there remain challenging that have yet to be solved: notably, faint and tiny blobs corresponding to quite distant vehicles. In fact, for such distant blobs, classification decisions can be taken after observing them during a few frames. Hence, incorporating tracking could improve the overall lighting system performance by enforcing the temporal consistency of the classifier decision. Accordingly, this paper focuses on the problem of constructing blob tracks, which is actually one of multiple-target tracking (MTT), but under two special conditions: We have to deal with frequent occlusions, as well as blob splits and merges. We approach it in a novel way by formulating the problem as a maximum a posteriori inference on a Markov random field. The qualitative (in video form) and quantitative evaluation of our new MTT method shows good tracking results. In addition, we will also see that the classification performance of the problematic blobs improves due to the proposed MTT 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	1524-9050	ISBN		Medium
	Area		Expedition		Conference
	Notes	ADAS			Approved	no
	Call Number	Admin @ si @ RLP2012; ADAS @ adas @ rsl2012g			Serial	1877
Permanent link to this record



	Author	Laura Igual; Joan Carles Soliva; Sergio Escalera; Roger Gimeno; Oscar Vilarroya; Petia Radeva
	Title	Automatic Brain Caudate Nuclei Segmentation and Classification in Diagnostic of Attention-Deficit/Hyperactivity Disorder			Type	Journal Article
	Year	2012	Publication	Computerized Medical Imaging and Graphics	Abbreviated Journal	CMIG
	Volume	36	Issue	8	Pages	591-600
	Keywords	Automatic caudate segmentation; Attention-Deficit/Hyperactivity Disorder; Diagnostic test; Machine learning; Decision stumps; Dissociated dipoles
	Abstract	We present a fully automatic diagnostic imaging test for Attention-Deficit/Hyperactivity Disorder diagnosis assistance based on previously found evidences of caudate nucleus volumetric abnormalities. The proposed method consists of different steps: a new automatic method for external and internal segmentation of caudate based on Machine Learning methodologies; the definition of a set of new volume relation features, 3D Dissociated Dipoles, used for caudate representation and classification. We separately validate the contributions using real data from a pediatric population and show precise internal caudate segmentation and discrimination power of the diagnostic test, showing significant performance improvements in comparison to other state-of-the-art methods.
	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	OR; HuPBA; MILAB			Approved	no
	Call Number	Admin @ si @ ISE2012			Serial	2143
Permanent link to this record



	Author	Jose Manuel Alvarez; Y. LeCun; Theo Gevers; Antonio Lopez
	Title	Semantic Road Segmentation via Multi-Scale Ensembles of Learned Features			Type	Conference Article
	Year	2012	Publication	12th European Conference on Computer Vision – Workshops and Demonstrations	Abbreviated Journal
	Volume	7584	Issue		Pages	586-595
	Keywords	road detection
	Abstract	Semantic segmentation refers to the process of assigning an object label (e.g., building, road, sidewalk, car, pedestrian) to every pixel in an image. Common approaches formulate the task as a random field labeling problem modeling the interactions between labels by combining local and contextual features such as color, depth, edges, SIFT or HoG. These models are trained to maximize the likelihood of the correct classification given a training set. However, these approaches rely on hand–designed features (e.g., texture, SIFT or HoG) and a higher computational time required in the inference process. Therefore, in this paper, we focus on estimating the unary potentials of a conditional random field via ensembles of learned features. We propose an algorithm based on convolutional neural networks to learn local features from training data at different scales and resolutions. Then, diversification between these features is exploited using a weighted linear combination. Experiments on a publicly available database show the effectiveness of the proposed method to perform semantic road scene segmentation in still images. The algorithm outperforms appearance based methods and its performance is similar compared to state–of–the–art methods using other sources of information such as depth, motion or stereo.
	Address
	Corporate Author				Thesis
	Publisher	Springer Berlin Heidelberg	Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title	LNCS
	Series Volume		Series Issue		Edition
	ISSN	0302-9743	ISBN	978-3-642-33867-0	Medium
	Area		Expedition		Conference	ECCVW
	Notes	ADAS;ISE			Approved	no
	Call Number	Admin @ si @ ALG2012; ADAS @ adas			Serial	2187
Permanent link to this record



	Author	Fadi Dornaika; A.Assoum; Bogdan Raducanu
	Title	Automatic Dimensionality Estimation for Manifold Learning through Optimal Feature Selection			Type	Conference Article
	Year	2012	Publication	Structural, Syntactic, and Statistical Pattern Recognition, Joint IAPR International Workshop	Abbreviated Journal
	Volume	7626	Issue		Pages	575-583
	Keywords
	Abstract	A very important aspect in manifold learning is represented by automatic estimation of the intrinsic dimensionality. Unfortunately, this problem has received few attention in the literature of manifold learning. In this paper, we argue that feature selection paradigm can be used to the problem of automatic dimensionality estimation. Besides this, it also leads to improved recognition rates. Our approach for optimal feature selection is based on a Genetic Algorithm. As a case study for manifold learning, we have considered Laplacian Eigenmaps (LE) and Locally Linear Embedding (LLE). The effectiveness of the proposed framework was tested on the face recognition problem. Extensive experiments carried out on ORL, UMIST, Yale, and Extended Yale face data sets confirmed our hypothesis.
	Address
	Corporate Author				Thesis
	Publisher	Springer Berlin Heidelberg	Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title	LNCS
	Series Volume		Series Issue		Edition
	ISSN	0302-9743	ISBN	978-3-642-34165-6	Medium
	Area		Expedition		Conference	SSPR&SPR
	Notes	OR;MV			Approved	no
	Call Number	Admin @ si @ DAR2012			Serial	2174
Permanent link to this record



	Author	Bogdan Raducanu; Fadi Dornaika
	Title	Pose-Invariant Face Recognition in Videos for Human-Machine Interaction			Type	Conference Article
	Year	2012	Publication	12th European Conference on Computer Vision	Abbreviated Journal
	Volume	7584	Issue		Pages	566.575
	Keywords
	Abstract	Human-machine interaction is a hot topic nowadays in the communities of computer vision and robotics. In this context, face recognition algorithms (used as primary cue for a person’s identity assessment) work well under controlled conditions but degrade significantly when tested in real-world environments. This is mostly due to the difficulty of simultaneously handling variations in illumination, pose, and occlusions. In this paper, we propose a novel approach for robust pose-invariant face recognition for human-robot interaction based on the real-time fitting of a 3D deformable model to input images taken from video sequences. More concrete, our approach generates a rectified face image irrespective with the actual head-pose orientation. Experimental results performed on Honda video database, using several manifold learning techniques, show a distinct advantage of the proposed method over the standard 2D appearance-based snapshot approach.
	Address
	Corporate Author				Thesis
	Publisher	Springer Berlin Heidelberg	Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title	LNCS
	Series Volume		Series Issue		Edition
	ISSN	0302-9743	ISBN	978-3-642-33867-0	Medium
	Area		Expedition		Conference	ECCVW
	Notes	OR;MV			Approved	no
	Call Number	Admin @ si @ RaD2012e			Serial	2182
Permanent link to this record



	Author	Pierluigi Casale; Oriol Pujol; Petia Radeva
	Title	Personalization and User Verification in Wearable Systems using Biometric Walking Patterns			Type	Journal Article
	Year	2012	Publication	Personal and Ubiquitous Computing	Abbreviated Journal	PUC
	Volume	16	Issue	5	Pages	563-580
	Keywords
	Abstract	In this article, a novel technique for user’s authentication and verification using gait as a biometric unobtrusive pattern is proposed. The method is based on a two stages pipeline. First, a general activity recognition classifier is personalized for an specific user using a small sample of her/his walking pattern. As a result, the system is much more selective with respect to the new walking pattern. A second stage verifies whether the user is an authorized one or not. This stage is defined as a one-class classification problem. In order to solve this problem, a four-layer architecture is built around the geometric concept of convex hull. This architecture allows to improve robustness to outliers, modeling non-convex shapes, and to take into account temporal coherence information. Two different scenarios are proposed as validation with two different wearable systems. First, a custom high-performance wearable system is built and used in a free environment. A second dataset is acquired from an Android-based commercial device in a ‘wild’ scenario with rough terrains, adversarial conditions, crowded places and obstacles. Results on both systems and datasets are very promising, reducing the verification error rates by an order of magnitude with respect to the state-of-the-art technologies.
	Address
	Corporate Author				Thesis
	Publisher	Springer-Verlag	Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN	1617-4909	ISBN		Medium
	Area		Expedition		Conference
	Notes	MILAB;HuPBA			Approved	no
	Call Number	Admin @ si @ CPR2012			Serial	1706
Permanent link to this record



	Author	Michael Holte; Bhaskar Chakraborty; Jordi Gonzalez; Thomas B. Moeslund
	Title	A Local 3D Motion Descriptor for Multi-View Human Action Recognition from 4D Spatio-Temporal Interest Points			Type	Journal Article
	Year	2012	Publication	IEEE Journal of Selected Topics in Signal Processing	Abbreviated Journal	J-STSP
	Volume	6	Issue	5	Pages	553-565
	Keywords
	Abstract	In this paper, we address the problem of human action recognition in reconstructed 3-D data acquired by multi-camera systems. We contribute to this field by introducing a novel 3-D action recognition approach based on detection of 4-D (3-D space $+$ time) spatio-temporal interest points (STIPs) and local description of 3-D motion features. STIPs are detected in multi-view images and extended to 4-D using 3-D reconstructions of the actors and pixel-to-vertex correspondences of the multi-camera setup. Local 3-D motion descriptors, histogram of optical 3-D flow (HOF3D), are extracted from estimated 3-D optical flow in the neighborhood of each 4-D STIP and made view-invariant. The local HOF3D descriptors are divided using 3-D spatial pyramids to capture and improve the discrimination between arm- and leg-based actions. Based on these pyramids of HOF3D descriptors we build a bag-of-words (BoW) vocabulary of human actions, which is compressed and classified using agglomerative information bottleneck (AIB) and support vector machines (SVMs), respectively. Experiments on the publicly available i3DPost and IXMAS datasets show promising state-of-the-art results and validate the performance and view-invariance of the 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	1932-4553	ISBN		Medium
	Area		Expedition		Conference
	Notes	ISE			Approved	no
	Call Number	Admin @ si @ HCG2012			Serial	1994
Permanent link to this record



	Author	Antonio Hernandez; Nadezhda Zlateva; Alexander Marinov; Miguel Reyes; Petia Radeva; Dimo Dimov; Sergio Escalera
	Title	Human Limb Segmentation in Depth Maps based on Spatio-Temporal Graph Cuts Optimization			Type	Journal Article
	Year	2012	Publication	Journal of Ambient Intelligence and Smart Environments	Abbreviated Journal	JAISE
	Volume	4	Issue	6	Pages	535-546
	Keywords	Multi-modal vision processing; Random Forest; Graph-cuts; multi-label segmentation; human body segmentation
	Abstract	We present a framework for object segmentation using depth maps based on Random Forest and Graph-cuts theory, and apply it to the segmentation of human limbs. First, from a set of random depth features, Random Forest is used to infer a set of label probabilities for each data sample. This vector of probabilities is used as unary term in α−β swap Graph-cuts algorithm. Moreover, depth values of spatio-temporal neighboring data points are used as boundary potentials. Results on a new multi-label human depth data set show high performance in terms of segmentation overlapping of the novel methodology compared to classical approaches.
	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	1876-1364	ISBN		Medium
	Area		Expedition		Conference
	Notes	MILAB;HuPBA			Approved	no
	Call Number	Admin @ si @ HZM2012a			Serial	2006
Permanent link to this record



	Author	Klaus Broelemann; Anjan Dutta; Xiaoyi Jiang; Josep Llados
	Title	Hierarchical graph representation for symbol spotting in graphical document images			Type	Conference Article
	Year	2012	Publication	Structural, Syntactic, and Statistical Pattern Recognition, Joint IAPR International Workshop	Abbreviated Journal
	Volume	7626	Issue		Pages	529-538
	Keywords
	Abstract	Symbol spotting can be defined as locating given query symbol in a large collection of graphical documents. In this paper we present a hierarchical graph representation for symbols. This representation allows graph matching methods to deal with low-level vectorization errors and, thus, to perform a robust symbol spotting. To show the potential of this approach, we conduct an experiment with the SESYD dataset.
	Address	Miyajima-Itsukushima, Hiroshima
	Corporate Author				Thesis
	Publisher	Springer Berlin Heidelberg	Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title	LNCS
	Series Volume		Series Issue		Edition
	ISSN	0302-9743	ISBN	978-3-642-34165-6	Medium
	Area		Expedition		Conference	SSPR&SPR
	Notes	DAG			Approved	no
	Call Number	Admin @ si @ BDJ2012			Serial	2126
Permanent link to this record