toggle visibility Search & Display Options
Select All    Deselect All << 1 2 3 4 5 6 7 8 9 10 >> [11–20]
List View
 | 
Citations
 | 
Details
  Records Links
Author Jose Carlos Rubio; Joan Serrat; Antonio Lopez edit   pdf
doi  isbn
openurl 
  Title Video Co-segmentation Type Conference Article
  Year 2012 Publication 11th Asian Conference on Computer Vision Abbreviated Journal  
  Volume 7725 Issue Pages 13-24  
  Keywords  
  Abstract Segmentation of a single image is in general a highly underconstrained problem. A frequent approach to solve it is to somehow provide prior knowledge or constraints on how the objects of interest look like (in terms of their shape, size, color, location or structure). Image co-segmentation trades the need for such knowledge for something much easier to obtain, namely, additional images showing the object from other viewpoints. Now the segmentation problem is posed as one of differentiating the similar object regions in all the images from the more varying background. In this paper, for the first time, we extend this approach to video segmentation: given two or more video sequences showing the same object (or objects belonging to the same class) moving in a similar manner, we aim to outline its region in all the frames. In addition, the method works in an unsupervised manner, by learning to segment at testing time. We compare favorably with two state-of-the-art methods on video segmentation and report results on benchmark videos.  
  Address Daejeon, Korea  
  Corporate Author Thesis  
  Publisher Springer Berlin Heidelberg Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title (down) LNCS  
  Series Volume Series Issue Edition  
  ISSN 0302-9743 ISBN 978-3-642-37443-2 Medium  
  Area Expedition Conference ACCV  
  Notes ADAS Approved no  
  Call Number Admin @ si @ RSL2012d Serial 2153  
Permanent link to this record
 
 
Author Monica Piñol; Angel Sappa; Ricardo Toledo edit   pdf
doi  isbn
openurl 
  Title MultiTable Reinforcement for Visual Object Recognition Type Conference Article
  Year 2012 Publication 4th International Conference on Signal and Image Processing Abbreviated Journal  
  Volume 221 Issue Pages 469-480  
  Keywords  
  Abstract This paper presents a bag of feature based method for visual object recognition. Our contribution is focussed on the selection of the best feature descriptor. It is implemented by using a novel multi-table reinforcement learning method that selects among five of classical descriptors (i.e., Spin, SIFT, SURF, C-SIFT and PHOW) the one that best describes each image. Experimental results and comparisons are provided showing the improvements achieved with the proposed approach.  
  Address Coimbatore, India  
  Corporate Author Thesis  
  Publisher Springer India Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title (down) LNCS  
  Series Volume Series Issue Edition  
  ISSN 1876-1100 ISBN 978-81-322-0996-6 Medium  
  Area Expedition Conference ICSIP  
  Notes ADAS Approved no  
  Call Number Admin @ si @ PST2012 Serial 2157  
Permanent link to this record
 
 
Author Mohammad Rouhani; Angel Sappa edit  doi
isbn  openurl
  Title Non-Rigid Shape Registration: A Single Linear Least Squares Framework Type Conference Article
  Year 2012 Publication 12th European Conference on Computer Vision Abbreviated Journal  
  Volume 7578 Issue Pages 264-277  
  Keywords  
  Abstract This paper proposes a non-rigid registration formulation capturing both global and local deformations in a single framework. This formulation is based on a quadratic estimation of the registration distance together with a quadratic regularization term. Hence, the optimal transformation parameters are easily obtained by solving a liner system of equations, which guarantee a fast convergence. Experimental results with challenging 2D and 3D shapes are presented to show the validity of the proposed framework. Furthermore, comparisons with the most relevant approaches are provided.  
  Address Florencia  
  Corporate Author Thesis  
  Publisher Springer Berlin Heidelberg Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title (down) LNCS  
  Series Volume Series Issue Edition  
  ISSN 0302-9743 ISBN 978-3-642-33785-7 Medium  
  Area Expedition Conference ECCV  
  Notes ADAS Approved no  
  Call Number Admin @ si @ RoS2012a Serial 2158  
Permanent link to this record
 
 
Author Jose Manuel Alvarez; Y. LeCun; Theo Gevers; Antonio Lopez edit   pdf
doi  isbn
openurl 
  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 (down) 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 Patricia Marquez; Debora Gil; Aura Hernandez-Sabate; Daniel Kondermann edit   pdf
url  doi
isbn  openurl
  Title When Is A Confidence Measure Good Enough? Type Conference Article
  Year 2013 Publication 9th International Conference on Computer Vision Systems Abbreviated Journal  
  Volume 7963 Issue Pages 344-353  
  Keywords Optical flow, confidence measure, performance evaluation  
  Abstract Confidence estimation has recently become a hot topic in image processing and computer vision.Yet, several definitions exist of the term “confidence” which are sometimes used interchangeably. This is a position paper, in which we aim to give an overview on existing definitions,
thereby clarifying the meaning of the used terms to facilitate further research in this field. Based on these clarifications, we develop a theory to compare confidence measures with respect to their quality.		  
  Address St Petersburg; Russia; July 2013  
  Corporate Author Thesis  
  Publisher Springer Link Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title (down) LNCS  
  Series Volume Series Issue Edition  
  ISSN 0302-9743 ISBN 978-3-642-39401-0 Medium  
  Area Expedition Conference ICVS  
  Notes IAM;ADAS; 600.044; 600.057; 600.060; 601.145 Approved no  
  Call Number IAM @ iam @ MGH2013a Serial 2218  
Permanent link to this record
 
 
Author Katerine Diaz; Francesc J. Ferri; W. Diaz edit  doi
isbn  openurl
  Title Fast Approximated Discriminative Common Vectors using rank-one SVD updates Type Conference Article
  Year 2013 Publication 20th International Conference On Neural Information Processing Abbreviated Journal  
  Volume 8228 Issue III Pages 368-375  
  Keywords  
  Abstract An efficient incremental approach to the discriminative common vector (DCV) method for dimensionality reduction and classification is presented. The proposal consists of a rank-one update along with an adaptive restriction on the rank of the null space which leads to an approximate but convenient solution. The algorithm can be implemented very efficiently in terms of matrix operations and space complexity, which enables its use in large-scale dynamic application domains. Deep comparative experimentation using publicly available high dimensional image datasets has been carried out in order to properly assess the proposed algorithm against several recent incremental formulations.
K. Diaz-Chito, F.J. Ferri, W. Diaz		  
  Address Daegu; Korea; November 2013  
  Corporate Author Thesis  
  Publisher Springer Berlin Heidelberg Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title (down) LNCS  
  Series Volume Series Issue Edition  
  ISSN 0302-9743 ISBN 978-3-642-42050-4 Medium  
  Area Expedition Conference ICONIP  
  Notes ADAS Approved no  
  Call Number Admin @ si @ DFD2013 Serial 2439  
Permanent link to this record
 
 
Author Patricia Marquez; H. Kause; A. Fuster; Aura Hernandez-Sabate; L. Florack; Debora Gil; Hans van Assen edit   pdf
doi  isbn
openurl 
  Title Factors Affecting Optical Flow Performance in Tagging Magnetic Resonance Imaging Type Conference Article
  Year 2014 Publication 17th International Conference on Medical Image Computing and Computer Assisted Intervention Abbreviated Journal  
  Volume 8896 Issue Pages 231-238  
  Keywords Optical flow; Performance Evaluation; Synthetic Database; ANOVA; Tagging Magnetic Resonance Imaging  
  Abstract Changes in cardiac deformation patterns are correlated with cardiac pathologies. Deformation can be extracted from tagging Magnetic Resonance Imaging (tMRI) using Optical Flow (OF) techniques. For applications of OF in a clinical setting it is important to assess to what extent the performance of a particular OF method is stable across di erent clinical acquisition artifacts. This paper presents a statistical validation framework, based on ANOVA, to assess the motion and appearance factors that have the largest in uence on OF accuracy drop.
In order to validate this framework, we created a database of simulated tMRI data including the most common artifacts of MRI and test three di erent OF methods, including HARP.		  
  Address Boston; USA; September 2014  
  Corporate Author Thesis  
  Publisher Springer International Publishing Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title (down) LNCS  
  Series Volume Series Issue Edition  
  ISSN 0302-9743 ISBN 978-3-319-14677-5 Medium  
  Area Expedition Conference STACOM  
  Notes IAM; ADAS; 600.060; 601.145; 600.076; 600.075 Approved no  
  Call Number Admin @ si @ MKF2014 Serial 2495  
Permanent link to this record
 
 
Author Marcelo D. Pistarelli; Angel Sappa; Ricardo Toledo edit  doi
isbn  openurl
  Title Multispectral Stereo Image Correspondence Type Conference Article
  Year 2013 Publication 15th International Conference on Computer Analysis of Images and Patterns Abbreviated Journal  
  Volume 8048 Issue Pages 217-224  
  Keywords  
  Abstract This paper presents a novel multispectral stereo image correspondence approach. It is evaluated using a stereo rig constructed with a visible spectrum camera and a long wave infrared spectrum camera. The novelty of the proposed approach lies on the usage of Hough space as a correspondence search domain. In this way it avoids searching for correspondence in the original multispectral image domains, where information is low correlated, and a common domain is used. The proposed approach is intended to be used in outdoor urban scenarios, where images contain large amount of edges. These edges are used as distinctive characteristics for the matching in the Hough space. Experimental results are provided showing the validity of the proposed approach.  
  Address York; uk; August 2013  
  Corporate Author Thesis  
  Publisher Springer Berlin Heidelberg Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title (down) LNCS  
  Series Volume Series Issue Edition  
  ISSN 0302-9743 ISBN 978-3-642-40245-6 Medium  
  Area Expedition Conference CAIP  
  Notes ADAS; 600.055 Approved no  
  Call Number Admin @ si @ PST2013 Serial 2561  
Permanent link to this record
 
 
Author Gioacchino Vino; Angel Sappa edit  doi
isbn  openurl
  Title Revisiting Harris Corner Detector Algorithm: a Gradual Thresholding Approach Type Conference Article
  Year 2013 Publication 10th International Conference on Image Analysis and Recognition Abbreviated Journal  
  Volume 7950 Issue Pages 354-363  
  Keywords  
  Abstract This paper presents an adaptive thresholding approach intended to increase the number of detected corners, while reducing the amount of those ones corresponding to noisy data. The proposed approach works by using the classical Harris corner detector algorithm and overcome the difficulty in finding a general threshold that work well for all the images in a given data set by proposing a novel adaptive thresholding scheme. Initially, two thresholds are used to discern between strong corners and flat regions. Then, a region based criteria is used to discriminate between weak corners and noisy points in the midway interval. Experimental results show that the proposed approach has a better capability to reject false corners and, at the same time, to detect weak ones. Comparisons with the state of the art are provided showing the validity of the proposed approach.  
  Address Póvoa de Varzim; 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 (down) LNCS  
  Series Volume Series Issue Edition  
  ISSN 0302-9743 ISBN 978-3-642-39093-7 Medium  
  Area Expedition Conference ICIAR  
  Notes ADAS; 600.055 Approved no  
  Call Number Admin @ si @ ViS2013 Serial 2562  
Permanent link to this record
 
 
Author Dennis G.Romero; Anselmo Frizera; Angel Sappa; Boris X. Vintimilla; Teodiano F.Bastos edit   pdf
url  doi
isbn  openurl
  Title A predictive model for human activity recognition by observing actions and context Type Conference Article
  Year 2015 Publication Advanced Concepts for Intelligent Vision Systems, Proceedings of 16th International Conference, ACIVS 2015 Abbreviated Journal  
  Volume 9386 Issue Pages 323-333  
  Keywords  
  Abstract This paper presents a novel model to estimate human activities — a human activity is defined by a set of human actions. The proposed approach is based on the usage of Recurrent Neural Networks (RNN) and Bayesian inference through the continuous monitoring of human actions and its surrounding environment. In the current work human activities are inferred considering not only visual analysis but also additional resources; external sources of information, such as context information, are incorporated to contribute to the activity estimation. The novelty of the proposed approach lies in the way the information is encoded, so that it can be later associated according to a predefined semantic structure. Hence, a pattern representing a given activity can be defined by a set of actions, plus contextual information or other kind of information that could be relevant to describe the activity. Experimental results with real data are provided showing the validity of the proposed approach.  
  Address Catania; Italy; October 2015  
  Corporate Author Thesis  
  Publisher Springer International Publishing Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title (down) LNCS  
  Series Volume Series Issue Edition  
  ISSN 0302-9743 ISBN 978-3-319-25902-4 Medium  
  Area Expedition Conference ACIVS  
  Notes ADAS; 600.076 Approved no  
  Call Number Admin @ si @ RFS2015 Serial 2661  
Permanent link to this record
Select All    Deselect All << 1 2 3 4 5 6 7 8 9 10 >> [11–20]
List View
 | 
Citations
 | 
Details
toggle visibility
Save Citations:
Export Records: