toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
   print
  Records Links
Author Arnau Ramisa; Adriana Tapus; Ramon Lopez de Mantaras; Ricardo Toledo edit  openurl
  Title Mobile Robot Localization using Panoramic Vision and Combination of Feature Region Detectors Type Conference Article
  Year 2008 Publication IEEE International Conference on Robotics and Automation, Abbreviated Journal  
  Volume Issue Pages 538–543  
  Keywords  
  Abstract  
  Address Pasadena; CA; USA  
  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 (up) Medium  
  Area Expedition Conference ICRA  
  Notes RV;ADAS Approved no  
  Call Number Admin @ si @ RTL2008 Serial 1144  
Permanent link to this record
 

 
Author Nicola Bellotto; Eric Sommerlade; Ben Benfold; Charles Bibby; I. Reid; Daniel Roth; Luc Van Gool; Carles Fernandez; Jordi Gonzalez edit   pdf
doi  openurl
  Title A Distributed Camera System for Multi-Resolution Surveillance Type Conference Article
  Year 2009 Publication 3rd ACM/IEEE International Conference on Distributed Smart Cameras Abbreviated Journal  
  Volume Issue Pages  
  Keywords 10.1109/ICDSC.2009.5289413  
  Abstract We describe an architecture for a multi-camera, multi-resolution surveillance system. The aim is to support a set of distributed static and pan-tilt-zoom (PTZ) cameras and visual tracking algorithms, together with a central supervisor unit. Each camera (and possibly pan-tilt device) has a dedicated process and processor. Asynchronous interprocess communications and archiving of data are achieved in a simple and effective way via a central repository, implemented using an SQL database. Visual tracking data from static views are stored dynamically into tables in the database via client calls to the SQL server. A supervisor process running on the SQL server determines if active zoom cameras should be dispatched to observe a particular target, and this message is effected via writing demands into another database table. We show results from a real implementation of the system comprising one static camera overviewing the environment under consideration and a PTZ camera operating under closed-loop velocity control, which uses a fast and robust level-set-based region tracker. Experiments demonstrate the effectiveness of our approach and its feasibility to multi-camera systems for intelligent surveillance.  
  Address Como, Italy  
  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 (up) Medium  
  Area Expedition Conference ICDSC  
  Notes Approved no  
  Call Number ISE @ ise @ BSB2009 Serial 1205  
Permanent link to this record
 

 
Author Gemma Roig; Xavier Boix; Fernando De la Torre edit  openurl
  Title Optimal Feature Selection for Subspace Image Matching Type Conference Article
  Year 2009 Publication 2nd IEEE International Workshop on Subspace Methods in conjunction Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Image matching has been a central research topic in computer vision over the last decades. Typical approaches to correspondence involve matching feature points between images. In this paper, we present a novel problem for establishing correspondences between a sparse set of image features and a previously learned subspace model. We formulate the matching task as an energy minimization, and jointly optimize over all possible feature assignments and parameters of the subspace model. This problem is in general NP-hard. We propose a convex relaxation approximation, and develop two optimization strategies: naïve gradient-descent and quadratic programming. Alternatively, we reformulate the optimization criterion as a sparse eigenvalue problem, and solve it using a recently proposed backward greedy algorithm. Experimental results on facial feature detection show that the quadratic programming solution provides better selection mechanism for relevant features.  
  Address Kyoto, 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 ISBN (up) Medium  
  Area Expedition Conference ICCV  
  Notes Approved no  
  Call Number Admin @ si @ RBT2009 Serial 1233  
Permanent link to this record
 

 
Author Anjan Dutta; Zeynep Akata edit   pdf
url  doi
openurl 
  Title Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-based Image Retrieval Type Conference Article
  Year 2019 Publication 32nd IEEE Conference on Computer Vision and Pattern Recognition Abbreviated Journal  
  Volume Issue Pages 5089-5098  
  Keywords  
  Abstract Zero-shot sketch-based image retrieval (SBIR) is an emerging task in computer vision, allowing to retrieve natural images relevant to sketch queries that might not been seen in the training phase. Existing works either require aligned sketch-image pairs or inefficient memory fusion layer for mapping the visual information to a semantic space. In this work, we propose a semantically aligned paired cycle-consistent generative (SEM-PCYC) model for zero-shot SBIR, where each branch maps the visual information to a common semantic space via an adversarial training. Each of these branches maintains a cycle consistency that only requires supervision at category levels, and avoids the need of highly-priced aligned sketch-image pairs. A classification criteria on the generators' outputs ensures the visual to semantic space mapping to be discriminating. Furthermore, we propose to combine textual and hierarchical side information via a feature selection auto-encoder that selects discriminating side information within a same end-to-end model. Our results demonstrate a significant boost in zero-shot SBIR performance over the state-of-the-art on the challenging Sketchy and TU-Berlin datasets.  
  Address Long beach; California; USA; June 2019  
  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 (up) Medium  
  Area Expedition Conference CVPR  
  Notes DAG; 600.141; 600.121 Approved no  
  Call Number Admin @ si @ DuA2019 Serial 3268  
Permanent link to this record
 

 
Author Xavier Boix; Josep M. Gonfaus; Fahad Shahbaz Khan; Joost Van de Weijer; Andrew Bagdanov; Marco Pedersoli; Jordi Gonzalez; Joan Serrat edit  openurl
  Title Combining local and global bag-of-word representations for semantic segmentation Type Conference Article
  Year 2009 Publication Workshop on The PASCAL Visual Object Classes Challenge Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Kyoto (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 ISBN (up) Medium  
  Area Expedition Conference ICCV  
  Notes ADAS;ISE Approved no  
  Call Number ADAS @ adas @ BGS2009 Serial 1273  
Permanent link to this record
 

 
Author Partha Pratim Roy; Umapada Pal; Josep Llados edit  url
doi  openurl
  Title Seal Object Detection in Document Images using GHT of Local Component Shapes Type Conference Article
  Year 2010 Publication 10th ACM Symposium On Applied Computing Abbreviated Journal  
  Volume Issue Pages 23–27  
  Keywords  
  Abstract Due to noise, overlapped text/signature and multi-oriented nature, seal (stamp) object detection involves a difficult challenge. This paper deals with automatic detection of seal from documents with cluttered background. Here, a seal object is characterized by scale and rotation invariant spatial feature descriptors (distance and angular position) computed from recognition result of individual connected components (characters). Recognition of multi-scale and multi-oriented component is done using Support Vector Machine classifier. Generalized Hough Transform (GHT) is used to detect the seal and a voting is casted for finding possible location of the seal object in a document based on these spatial feature descriptor of components pairs. The peak of votes in GHT accumulator validates the hypothesis to locate the seal object in a document. Experimental results show that, the method is efficient to locate seal instance of arbitrary shape and orientation in documents.  
  Address Sierre, Switzerland  
  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 (up) Medium  
  Area Expedition Conference SAC  
  Notes DAG Approved no  
  Call Number DAG @ dag @ RPL2010a Serial 1291  
Permanent link to this record
 

 
Author Muhammad Muzzamil Luqman; Thierry Brouard; Jean-Yves Ramel; Josep Llados edit  openurl
  Title Vers une approche foue of encapsulation de graphes: application a la reconnaissance de symboles Type Conference Article
  Year 2010 Publication Colloque International Francophone sur l'Écrit et le Document Abbreviated Journal  
  Volume Issue Pages 169-184  
  Keywords Fuzzy interval; Graph embedding; Bayesian network; Symbol recognition  
  Abstract We present a new methodology for symbol recognition, by employing a structural approach for representing visual associations in symbols and a statistical classifier for recognition. A graphic symbol is vectorized, its topological and geometrical details are encoded by an attributed relational graph and a signature is computed for it. Data adapted fuzzy intervals have been introduced for addressing the sensitivity of structural representations to noise. The joint probability distribution of signatures is encoded by a Bayesian network, which serves as a mechanism for pruning irrelevant features and choosing a subset of interesting features from structural signatures of underlying symbol set, and is deployed in a supervised learning scenario for recognizing query symbols. Experimental results on pre-segmented 2D linear architectural and electronic symbols from GREC databases are presented.  
  Address Sousse, Tunisia  
  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 (up) Medium  
  Area Expedition Conference CIFED  
  Notes DAG Approved no  
  Call Number DAG @ dag @ LBR2010a Serial 1293  
Permanent link to this record
 

 
Author Naila Murray; Eduard Vazquez edit   pdf
openurl 
  Title Lacuna Restoration: How to choose a neutral colour? Type Conference Article
  Year 2010 Publication Proceedings of The CREATE 2010 Conference Abbreviated Journal  
  Volume Issue Pages 248–252  
  Keywords  
  Abstract Painting restoration which involves filling in material loss (called lacuna) is a complex process. Several standard techniques exist to tackle lacuna restoration,
and this article focuses on those techniques that employ a “neutral” colour to mask the defect. Restoration experts often disagree on the choice of such a colour and in fact, the concept of a neutral colour is controversial. We posit that a neutral colour is one that attracts relatively little visual attention for a specific lacuna. We conducted an eye tracking experiment to compare two common neutral
colour selection methods, specifically the most common local colour and the mean local colour. Results obtained demonstrate that the most common local colour triggers less visual attention in general. Notwithstanding, we have observed instances in which the most common colour triggers a significant amount of attention when subjects spent time resolving their confusion about whether or not a lacuna was part of the painting.
 
  Address Gjovik, Norway  
  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 (up) Medium  
  Area Expedition Conference CREATE  
  Notes CIC Approved no  
  Call Number Admin @ si @ MuV2010 Serial 1297  
Permanent link to this record
 

 
Author Marta Teres; Eduard Vazquez edit  openurl
  Title Museums, spaces and museographical resources. Current state and proposals for a multidisciplinary framework to open new perspectives Type Conference Article
  Year 2010 Publication Proceedings of The CREATE 2010 Conference Abbreviated Journal  
  Volume Issue Pages 319–323  
  Keywords  
  Abstract Two of the main aims of a museum are to communicate its heritage and to make enjoy its visitors. This communication can be done through the pieces itself and the museographical resources but also through the building, the interior design, the light and the colour. Art museums, in opposition with other museums, lack on the application of these additional resources. Such a work necessarily requires a multidisciplinary point of view for a holistic vision of all what a museum implies and to use all its potential as a tool of knowledge and culture for all the visitors.  
  Address Gjovik, Norway  
  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 (up) Medium  
  Area Expedition Conference CREATE  
  Notes Approved no  
  Call Number Admin @ si @ TeV2010 Serial 1298  
Permanent link to this record
 

 
Author Eduard Vazquez; Ramon Baldrich edit  openurl
  Title Non-supervised goodness measure for image segmentation Type Conference Article
  Year 2010 Publication Proceedings of The CREATE 2010 Conference Abbreviated Journal  
  Volume Issue Pages 334–335  
  Keywords  
  Abstract  
  Address Gjovik, Norway  
  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 (up) Medium  
  Area Expedition Conference CREATE  
  Notes CIC Approved no  
  Call Number CAT @ cat @ VaB2010 Serial 1299  
Permanent link to this record
 

 
Author Jaime Moreno; Xavier Otazu; Maria Vanrell edit  openurl
  Title Contribution of CIWaM in JPEG2000 Quantization for Color Images Type Conference Article
  Year 2010 Publication Proceedings of The CREATE 2010 Conference Abbreviated Journal  
  Volume Issue Pages 132–136  
  Keywords  
  Abstract The aim of this work is to explain how to apply perceptual concepts to define a perceptual pre-quantizer and to improve JPEG2000 compressor. The approach consists in quantizing wavelet transform coefficients using some of the human visual system behavior properties. Noise is fatal to image compression performance, because it can be both annoying for the observer and consumes excessive bandwidth when the imagery is transmitted. Perceptual pre-quantization reduces unperceivable details and thus improve both visual impression and transmission properties. The comparison between JPEG2000 without and with perceptual pre-quantization shows that the latter is not favorable in PSNR, but the recovered image is more compressed at the same or even better visual quality measured with a weighted PSNR. Perceptual criteria were taken from the CIWaM(ChromaticInductionWaveletModel).  
  Address Gjovik (Norway)  
  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 (up) Medium  
  Area Expedition Conference CREATE  
  Notes CIC Approved no  
  Call Number CAT @ cat @ MOV2010b Serial 1308  
Permanent link to this record
 

 
Author Javier Vazquez; Maria Vanrell; Robert Benavente edit  openurl
  Title Color names as a constraint for Computer Vision problems Type Conference Article
  Year 2010 Publication Proceedings of The CREATE 2010 Conference Abbreviated Journal  
  Volume Issue Pages 324–328  
  Keywords  
  Abstract Computer Vision Problems are usually ill-posed. Constraining de gamut of possible solutions is then a necessary step. Many constrains for different problems have been developed during years. In this paper, we present a different way of constraining some of these problems: the use of color names. In particular, we will focus on segmentation, representation ans constancy.  
  Address Gjovik (Norway)  
  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 (up) Medium  
  Area Expedition Conference CREATE  
  Notes CIC Approved no  
  Call Number CAT @ cat @ VVB2010 Serial 1328  
Permanent link to this record
 

 
Author Fahad Shahbaz Khan; Joost Van de Weijer; Maria Vanrell edit  openurl
  Title Who Painted this Painting? Type Conference Article
  Year 2010 Publication Proceedings of The CREATE 2010 Conference Abbreviated Journal  
  Volume Issue Pages 329–333  
  Keywords  
  Abstract  
  Address Gjovik (Norway)  
  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 (up) Medium  
  Area Expedition Conference CREATE  
  Notes CIC Approved no  
  Call Number CAT @ cat @ KWV2010 Serial 1329  
Permanent link to this record
 

 
Author Shida Beigpour; Joost Van de Weijer edit   pdf
openurl 
  Title Photo-Realistic Color Alteration for Architecture and Design Type Conference Article
  Year 2010 Publication Proceedings of The CREATE 2010 Conference Abbreviated Journal  
  Volume Issue Pages 84–88  
  Keywords  
  Abstract As color is a strong stimuli we receive from the exterior world, choosing the right color can prove crucial in creating the desired architecture and desing. We propose a framework to apply a realistic color change on both objects and their illuminant lights for snapshots of architectural designs, in order to visualize and choose the right color before actully applying the change in the real world. The proposed framework is based on the laws of physics in order to accomplish realistic and physically plausible results.  
  Address Gjovik (Norway)  
  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 (up) Medium  
  Area Expedition Conference CREATE  
  Notes CIC Approved no  
  Call Number CAT @ cat @ BeW2010 Serial 1330  
Permanent link to this record
 

 
Author Miguel Angel Bautista; Xavier Baro; Oriol Pujol; Petia Radeva; Jordi Vitria; Sergio Escalera edit  openurl
  Title Compact Evolutive Design of Error-Correcting Output Codes Type Conference Article
  Year 2010 Publication Supervised and Unsupervised Ensemble Methods and their Applications in the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases Abbreviated Journal  
  Volume Issue Pages 119-128  
  Keywords Ensemble of Dichotomizers; Error-Correcting Output Codes; Evolutionary optimization  
  Abstract The classi cation of large number of object categories is a challenging trend in the Machine Learning eld. In literature, this is often addressed using an ensemble of classi ers. In this scope, the Error-Correcting Output Codes framework has demonstrated to be a powerful tool for the combination of classi ers. However, most of the state-of-the-art ECOC approaches use a linear or exponential number of classi ers, making the discrimination of a large number of classes unfeasible. In this paper, we explore and propose a minimal design of ECOC in terms of the number of classi ers. Evolutionary computation is used for tuning the parameters of the classi ers and looking for the best Minimal ECOC code con guration. The results over several public UCI data sets and a challenging multi-class Computer Vision problem show that the proposed methodology obtains comparable and even better results than state-of-the-art ECOC methodologies with far less number of dichotomizers.  
  Address 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 (up) Medium  
  Area Expedition Conference SUEMA  
  Notes OR;MILAB;HUPBA;MV Approved no  
  Call Number BCNPCL @ bcnpcl @ BBP2010 Serial 1363  
Permanent link to this record
Select All    Deselect All
 |   | 
Details
   print

Save Citations:
Export Records: