toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
  Records Links
Author Felipe Lumbreras; Xavier Roca; Daniel Ponsa; Robert Benavente; J. Martinez; Silvia Sanchez; Coen Antens; Juan J. Villanueva edit  openurl
  Title Visual Inspection of Safety Belts Type Conference Article
  Year 2001 Publication International Conference on Quality Control by Artificial Vision Abbreviated Journal  
  Volume 2 Issue Pages 526–531  
  Keywords  
  Abstract  
  Address France  
  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 QCAV  
  Notes ADAS;ISE;CIC Approved no  
  Call Number (down) ADAS @ adas @ LRP2001 Serial 122  
Permanent link to this record
 

 
Author Antonio Lopez; J. Hilgenstock; A. Busse; Ramon Baldrich; Felipe Lumbreras; Joan Serrat edit   pdf
openurl 
  Title Nightime Vehicle Detecion for Intelligent Headlight Control Type Conference Article
  Year 2008 Publication Advanced Concepts for Intelligent Vision Systems, 10th International Conference, Proceedings, Abbreviated Journal  
  Volume 5259 Issue Pages 113–124  
  Keywords Intelligent Headlights; vehicle detection  
  Abstract  
  Address Juan-les-Pins, France  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ACIVS  
  Notes ADAS;CIC Approved no  
  Call Number (down) ADAS @ adas @ LHB2008a Serial 1098  
Permanent link to this record
 

 
Author Carme Julia; Angel Sappa; Felipe Lumbreras; Joan Serrat; Antonio Lopez edit   pdf
openurl 
  Title An Adapted Alternation Approach for Recommender Systems Type Conference Article
  Year 2008 Publication IEEE International Conference on e–Business Engineering, Abbreviated Journal  
  Volume Issue Pages 128–135  
  Keywords  
  Abstract This paper presents an adaptation of the alternation technique to tackle the prediction task in recommender systems. These systems are widely considered in electronic commerce to help customers to find products they will probably like or dislike. As the SVD-based approaches, the proposed adapted alternation technique uses all the information stored in the system to find the predictions. The main advantage of this technique with respect to the SVD-based ones is that it can deal with missing data. Furthermore, it has a smaller computational cost. Experimental results with public data sets are provided in order to show the viability of the proposed adapted alternation approach.  
  Address Xi’an (Xina)  
  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 ADAS Approved no  
  Call Number (down) ADAS @ adas @ JSL2008e Serial 1044  
Permanent link to this record
 

 
Author Carme Julia; Angel Sappa; Felipe Lumbreras; Joan Serrat edit  openurl
  Title Photometric Stereo through and Adapted Alternation Approach Type Conference Article
  Year 2008 Publication IEEE International Conference on Image Processing, Abbreviated Journal  
  Volume Issue Pages 1500–1503  
  Keywords  
  Abstract  
  Address San Diego; 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 Medium  
  Area Expedition Conference  
  Notes ADAS Approved no  
  Call Number (down) ADAS @ adas @ JSL2008d Serial 1016  
Permanent link to this record
 

 
Author Carme Julia; Angel Sappa; Felipe Lumbreras; Antonio Lopez edit   pdf
openurl 
  Title Recovery of Surface Normals and Reflectance from Different Lighting Conditions Type Conference Article
  Year 2008 Publication 5th International Conference on Image Analysis and Recognition Abbreviated Journal  
  Volume 5112 Issue Pages 315–325  
  Keywords  
  Abstract  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes ADAS Approved no  
  Call Number (down) ADAS @ adas @ JSL2008c Serial 1014  
Permanent link to this record
 

 
Author Carme Julia; Angel Sappa; Felipe Lumbreras; Joan Serrat; Antonio Lopez edit   pdf
openurl 
  Title Motion Segmentation from Feature Trajectories with Missing Data Type Conference Article
  Year 2007 Publication 3rd. Iberian Conference on Pattern Recognition and Image Analysis Abbreviated Journal IbPRIA 2007  
  Volume LNCS 4477 Issue Pages 483–490  
  Keywords  
  Abstract  
  Address Girona (Spain)  
  Corporate Author Thesis  
  Publisher Place of Publication Editor J. Marti et al. (Eds.)  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes ADAS Approved no  
  Call Number (down) ADAS @ adas @ JSL2007a Serial 814  
Permanent link to this record
 

 
Author Carme Julia; Angel Sappa; Felipe Lumbreras; Joan Serrat; Antonio Lopez edit   pdf
openurl 
  Title An Iterative Multiresolution Scheme for SFM Type Conference Article
  Year 2006 Publication International Conference on Image Analysis and Recognition Abbreviated Journal ICIAR 2006  
  Volume LNCS 4141 Issue 1 Pages 804–815  
  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 ADAS Approved no  
  Call Number (down) ADAS @ adas @ JSL2006c Serial 704  
Permanent link to this record
 

 
Author Carme Julia; Angel Sappa; Felipe Lumbreras; Joan Serrat; Antonio Lopez edit   pdf
url  openurl
  Title Factorization with Missing and Noisy Data Type Conference Article
  Year 2006 Publication 6th International Conference on Computational Science Abbreviated Journal ICCS´06  
  Volume LNCS 3991 Issue Pages 555–562  
  Keywords  
  Abstract  
  Address Reading (United Kingdom)  
  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 ADAS Approved no  
  Call Number (down) ADAS @ adas @ JSL2006b Serial 653  
Permanent link to this record
 

 
Author Simon Jégou; Michal Drozdzal; David Vazquez; Adriana Romero; Yoshua Bengio edit   pdf
url  doi
openurl 
  Title The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation Type Conference Article
  Year 2017 Publication IEEE Conference on Computer Vision and Pattern Recognition Workshops Abbreviated Journal  
  Volume Issue Pages  
  Keywords Semantic Segmentation  
  Abstract State-of-the-art approaches for semantic image segmentation are built on Convolutional Neural Networks (CNNs). The typical segmentation architecture is composed of (a) a downsampling path responsible for extracting coarse semantic features, followed by (b) an upsampling path trained to recover the input image resolution at the output of the model and, optionally, (c) a post-processing module (e.g. Conditional Random Fields) to refine the model predictions.

Recently, a new CNN architecture, Densely Connected Convolutional Networks (DenseNets), has shown excellent results on image classification tasks. The idea of DenseNets is based on the observation that if each layer is directly connected to every other layer in a feed-forward fashion then the network will be more accurate and easier to train.

In this paper, we extend DenseNets to deal with the problem of semantic segmentation. We achieve state-of-the-art results on urban scene benchmark datasets such as CamVid and Gatech, without any further post-processing module nor pretraining. Moreover, due to smart construction of the model, our approach has much less parameters than currently published best entries for these datasets.
 
  Address Honolulu; USA; July 2017  
  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; ADAS; 600.076; 600.085; 601.281 Approved no  
  Call Number (down) ADAS @ adas @ JDV2016 Serial 2866  
Permanent link to this record
 

 
Author Daniel Hernandez; Lukas Schneider; Antonio Espinosa; David Vazquez; Antonio Lopez; Uwe Franke; Marc Pollefeys; Juan C. Moure edit   pdf
openurl 
  Title Slanted Stixels: Representing San Francisco's Steepest Streets} Type Conference Article
  Year 2017 Publication 28th British Machine Vision Conference Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract In this work we present a novel compact scene representation based on Stixels that infers geometric and semantic information. Our approach overcomes the previous rather restrictive geometric assumptions for Stixels by introducing a novel depth model to account for non-flat roads and slanted objects. Both semantic and depth cues are used jointly to infer the scene representation in a sound global energy minimization formulation. Furthermore, a novel approximation scheme is introduced that uses an extremely efficient over-segmentation. In doing so, the computational complexity of the Stixel inference algorithm is reduced significantly, achieving real-time computation capabilities with only a slight drop in accuracy. We evaluate the proposed approach in terms of semantic and geometric accuracy as well as run-time on four publicly available benchmark datasets. Our approach maintains accuracy on flat road scene datasets while improving substantially on a novel non-flat road dataset.  
  Address London; uk; September 2017  
  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 BMVC  
  Notes ADAS; 600.118 Approved no  
  Call Number (down) ADAS @ adas @ HSE2017a Serial 2945  
Permanent link to this record
Select All    Deselect All
 |   | 
Details

Save Citations:
Export Records: