toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
   print
  Records Links
Author Yaxing Wang; L. Zhang; Joost Van de Weijer edit   pdf
openurl 
  Title (down) Ensembles of generative adversarial networks Type Conference Article
  Year 2016 Publication 30th Annual Conference on Neural Information Processing Systems Worshops Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Ensembles are a popular way to improve results of discriminative CNNs. The
combination of several networks trained starting from different initializations
improves results significantly. In this paper we investigate the usage of ensembles of GANs. The specific nature of GANs opens up several new ways to construct ensembles. The first one is based on the fact that in the minimax game which is played to optimize the GAN objective the generator network keeps on changing even after the network can be considered optimal. As such ensembles of GANs can be constructed based on the same network initialization but just taking models which have different amount of iterations. These so-called self ensembles are much faster to train than traditional ensembles. The second method, called cascade GANs, redirects part of the training data which is badly modeled by the first GAN to another GAN. In experiments on the CIFAR10 dataset we show that ensembles of GANs obtain model probability distributions which better model the data distribution. In addition, we show that these improved results can be obtained at little additional computational cost.
 
  Address Barcelona; Spain; December 2016  
  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 NIPSW  
  Notes LAMP; 600.068 Approved no  
  Call Number Admin @ si @ WZW2016 Serial 2905  
Permanent link to this record
 

 
Author Daniel Hernandez; Alejandro Chacon; Antonio Espinosa; David Vazquez; Juan Carlos Moure; Antonio Lopez edit   pdf
url  openurl
  Title (down) Embedded real-time stereo estimation via Semi-Global Matching on the GPU Type Conference Article
  Year 2016 Publication 16th International Conference on Computational Science Abbreviated Journal  
  Volume 80 Issue Pages 143-153  
  Keywords Autonomous Driving; Stereo; CUDA; 3d reconstruction  
  Abstract Dense, robust and real-time computation of depth information from stereo-camera systems is a computationally demanding requirement for robotics, advanced driver assistance systems (ADAS) and autonomous vehicles. Semi-Global Matching (SGM) is a widely used algorithm that propagates consistency constraints along several paths across the image. This work presents a real-time system producing reliable disparity estimation results on the new embedded energy-efficient GPU devices. Our design runs on a Tegra X1 at 41 frames per second for an image size of 640x480, 128 disparity levels, and using 4 path directions for the SGM method.  
  Address San Diego; CA; USA; June 2016  
  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 ICCS  
  Notes ADAS; 600.085; 600.082; 600.076 Approved no  
  Call Number ADAS @ adas @ HCE2016a Serial 2740  
Permanent link to this record
 

 
Author Juan Ignacio Toledo; Alicia Fornes; Jordi Cucurull; Josep Llados edit   pdf
doi  openurl
  Title (down) Election Tally Sheets Processing System Type Conference Article
  Year 2016 Publication 12th IAPR Workshop on Document Analysis Systems Abbreviated Journal  
  Volume Issue Pages 364-368  
  Keywords  
  Abstract In paper based elections, manual tallies at polling station level produce myriads of documents. These documents share a common form-like structure and a reduced vocabulary worldwide. On the other hand, each tally sheet is filled by a different writer and on different countries, different scripts are used. We present a complete document analysis system for electoral tally sheet processing combining state of the art techniques with a new handwriting recognition subprocess based on unsupervised feature discovery with Variational Autoencoders and sequence classification with BLSTM neural networks. The whole system is designed to be script independent and allows a fast and reliable results consolidation process with reduced operational cost.  
  Address Santorini; Greece; April 2016  
  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 DAS  
  Notes DAG; 602.006; 600.061; 601.225; 600.077; 600.097 Approved no  
  Call Number TFC2016 Serial 2752  
Permanent link to this record
 

 
Author G. de Oliveira; Mariella Dimiccoli; Petia Radeva edit  openurl
  Title (down) Egocentric Image Retrieval With Deep Convolutional Neural Networks Type Conference Article
  Year 2016 Publication 19th International Conference of the Catalan Association for Artificial Intelligence Abbreviated Journal  
  Volume Issue Pages 71-76  
  Keywords  
  Abstract  
  Address Barcelona; Spain; October 2016  
  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 CCIA  
  Notes MILAB Approved no  
  Call Number Admin @ si @ODR2016 Serial 2790  
Permanent link to this record
 

 
Author Arash Akbarinia; C. Alejandro Parraga edit  openurl
  Title (down) Dynamically Adjusted Surround Contrast Enhances Boundary Detection, European Conference on Visual Perception Type Conference Article
  Year 2016 Publication European Conference on Visual Perception Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Barcelona; Spain; August 2016  
  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 ECVP  
  Notes NEUROBIT Approved no  
  Call Number Admin @ si @ AkP2016b Serial 2900  
Permanent link to this record
 

 
Author Y. Patel; Lluis Gomez; Marçal Rusiñol; Dimosthenis Karatzas edit   pdf
openurl 
  Title (down) Dynamic Lexicon Generation for Natural Scene Images Type Conference Article
  Year 2016 Publication 14th European Conference on Computer Vision Workshops Abbreviated Journal  
  Volume Issue Pages 395-410  
  Keywords scene text; photo OCR; scene understanding; lexicon generation; topic modeling; CNN  
  Abstract Many scene text understanding methods approach the endtoend recognition problem from a word-spotting perspective and take huge bene t from using small per-image lexicons. Such customized lexicons are normally assumed as given and their source is rarely discussed.
In this paper we propose a method that generates contextualized lexicons
for scene images using only visual information. For this, we exploit
the correlation between visual and textual information in a dataset consisting
of images and textual content associated with them. Using the topic modeling framework to discover a set of latent topics in such a dataset allows us to re-rank a xed dictionary in a way that prioritizes the words that are more likely to appear in a given image. Moreover, we train a CNN that is able to reproduce those word rankings but using only the image raw pixels as input. We demonstrate that the quality of the automatically obtained custom lexicons is superior to a generic frequency-based baseline.
 
  Address Amsterdam; The Netherlands; October 2016  
  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 ECCVW  
  Notes DAG; 600.084 Approved no  
  Call Number Admin @ si @ PGR2016 Serial 2825  
Permanent link to this record
 

 
Author Ozan Caglayan; Walid Aransa; Yaxing Wang; Marc Masana; Mercedes Garcıa-Martinez; Fethi Bougares; Loic Barrault; Joost Van de Weijer edit   pdf
openurl 
  Title (down) Does Multimodality Help Human and Machine for Translation and Image Captioning? Type Conference Article
  Year 2016 Publication 1st conference on machine translation Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract This paper presents the systems developed by LIUM and CVC for the WMT16 Multimodal Machine Translation challenge. We explored various comparative methods, namely phrase-based systems and attentional recurrent neural networks models trained using monomodal or multimodal data. We also performed a human evaluation in order to estimate theusefulness of multimodal data for human machine translation and image description generation. Our systems obtained the best results for both tasks according to the automatic evaluation metrics BLEU and METEOR.  
  Address Berlin; Germany; August 2016  
  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 WMT  
  Notes LAMP; 600.106 ; 600.068 Approved no  
  Call Number Admin @ si @ CAW2016 Serial 2761  
Permanent link to this record
 

 
Author Fernando Vilariño edit  openurl
  Title (down) Dissemination, creation and education from archives: Case study of the collection of Digitized Visual Poems from Joan Brossa Foundation Type Conference Article
  Year 2016 Publication International Workshop on Poetry: Archives, Poetries and Receptions Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Barcelona; Spain; October 2016  
  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 POETRY  
  Notes MV; 600.097;SIAI Approved no  
  Call Number Admin @ si @Vil2016b Serial 2805  
Permanent link to this record
 

 
Author Marc Sunset Perez; Marc Comino Trinidad; Dimosthenis Karatzas; Antonio Chica Calaf; Pere Pau Vazquez Alcocer edit  url
openurl 
  Title (down) Development of general‐purpose projection‐based augmented reality systems Type Journal
  Year 2016 Publication IADIs international journal on computer science and information systems Abbreviated Journal IADIs  
  Volume 11 Issue 2 Pages 1-18  
  Keywords  
  Abstract Despite the large amount of methods and applications of augmented reality, there is little homogenizatio n on the software platforms that support them. An exception may be the low level control software that is provided by some high profile vendors such as Qualcomm and Metaio. However, these provide fine grain modules for e.g. element tracking. We are more co ncerned on the application framework, that includes the control of the devices working together for the development of the AR experience. In this paper we describe the development of a software framework for AR setups. We concentrate on the modular design of the framework, but also on some hard problems such as the calibration stage, crucial for projection – based AR. The developed framework is suitable and has been tested in AR applications using camera – projector pairs, for both fixed and nomadic setups  
  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 DAG; 600.084 Approved no  
  Call Number Admin @ si @ SCK2016 Serial 2890  
Permanent link to this record
 

 
Author Q. Bao; Marçal Rusiñol; M.Coustaty; Muhammad Muzzamil Luqman; C.D. Tran; Jean-Marc Ogier edit   pdf
doi  openurl
  Title (down) Delaunay triangulation-based features for Camera-based document image retrieval system Type Conference Article
  Year 2016 Publication 12th IAPR Workshop on Document Analysis Systems Abbreviated Journal  
  Volume Issue Pages 1-6  
  Keywords Camera-based Document Image Retrieval; Delaunay Triangulation; Feature descriptors; Indexing  
  Abstract In this paper, we propose a new feature vector, named DElaunay TRIangulation-based Features (DETRIF), for real-time camera-based document image retrieval. DETRIF is computed based on the geometrical constraints from each pair of adjacency triangles in delaunay triangulation which is constructed from centroids of connected components. Besides, we employ a hashing-based indexing system in order to evaluate the performance of DETRIF and to compare it with other systems such as LLAH and SRIF. The experimentation is carried out on two datasets comprising of 400 heterogeneous-content complex linguistic map images (huge size, 9800 X 11768 pixels resolution)and 700 textual document images.  
  Address Santorini; Greece; April 2016  
  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 DAS  
  Notes DAG; 600.061; 600.084; 600.077 Approved no  
  Call Number Admin @ si @ BRC2016 Serial 2757  
Permanent link to this record
 

 
Author Xavier Baro; Sergio Escalera; Isabelle Guyon; Julio C. S. Jacques Junior; Lukasz Romaszko; Lisheng Sun; Sebastien Treguer; Evelyne Viegas edit  openurl
  Title (down) Coompetitions in machine learning: case studies Type Conference Article
  Year 2016 Publication 30th Annual Conference on Neural Information Processing Systems Worshops Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Barcelona; Spain; December 2016  
  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 NIPSW  
  Notes HuPBA Approved no  
  Call Number Admin @ si @ BEG2016 Serial 2911  
Permanent link to this record
 

 
Author Pejman Rasti; Tonis Uiboupin; Sergio Escalera; Gholamreza Anbarjafari edit  openurl
  Title (down) Convolutional Neural Network Super Resolution for Face Recognition in Surveillance Monitoring Type Conference Article
  Year 2016 Publication 9th Conference on Articulated Motion and Deformable Objects Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Palma de Mallorca; Spain; July 2016  
  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 AMDO  
  Notes HuPBA;MILAB Approved no  
  Call Number Admin @ si @ RUE2016 Serial 2846  
Permanent link to this record
 

 
Author Marc Oliu; Ciprian Corneanu; Laszlo A. Jeni; Jeffrey F. Cohn; Takeo Kanade; Sergio Escalera edit   pdf
openurl 
  Title (down) Continuous Supervised Descent Method for Facial Landmark Localisation Type Conference Article
  Year 2016 Publication 13th Asian Conference on Computer Vision Abbreviated Journal  
  Volume 10112 Issue Pages 121-135  
  Keywords  
  Abstract Recent methods for facial landmark location perform well on close-to-frontal faces but have problems in generalising to large head rotations. In order to address this issue we propose a second order linear regression method that is both compact and robust against strong rotations. We provide a closed form solution, making the method fast to train. We test the method’s performance on two challenging datasets. The first has been intensely used by the community. The second has been specially generated from a well known 3D face dataset. It is considerably more challenging, including a high diversity of rotations and more samples than any other existing public dataset. The proposed method is compared against state-of-the-art approaches, including RCPR, CGPRT, LBF, CFSS, and GSDM. Results upon both datasets show that the proposed method offers state-of-the-art performance on near frontal view data, improves state-of-the-art methods on more challenging head rotation problems and keeps a compact model size.  
  Address Taipei; Taiwan; November 2016  
  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 ACCV  
  Notes HuPBA;MILAB; Approved no  
  Call Number Admin @ si @ OCJ2016 Serial 2838  
Permanent link to this record
 

 
Author Carlos David Martinez Hinarejos; Josep Llados; Alicia Fornes; Francisco Casacuberta; Lluis de Las Heras; Joan Mas; Moises Pastor; Oriol Ramos Terrades; Joan Andreu Sanchez; Enrique Vidal; Fernando Vilariño edit   pdf
openurl 
  Title (down) Context, multimodality, and user collaboration in handwritten text processing: the CoMUN-HaT project Type Conference Article
  Year 2016 Publication 3rd IberSPEECH Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Processing of handwritten documents is a task that is of wide interest for many
purposes, such as those related to preserve cultural heritage. Handwritten text recognition techniques have been successfully applied during the last decade to obtain transcriptions of handwritten documents, and keyword spotting techniques have been applied for searching specific terms in image collections of handwritten documents. However, results on transcription and indexing are far from perfect. In this framework, the use of new data sources arises as a new paradigm that will allow for a better transcription and indexing of handwritten documents. Three main different data sources could be considered: context of the document (style, writer, historical time, topics,. . . ), multimodal data (representations of the document in a different modality, such as the speech signal of the dictation of the text), and user feedback (corrections, amendments,. . . ). The CoMUN-HaT project aims at the integration of these different data sources into the transcription and indexing task for handwritten documents: the use of context derived from the analysis of the documents, how multimodality can aid the recognition process to obtain more accurate transcriptions (including transcription in a modern version of the language), and integration into a userin-the-loop assisted text transcription framework. This will be reflected in the construction of a transcription and indexing platform that can be used by both professional and nonprofessional users, contributing to crowd-sourcing activities to preserve cultural heritage and to obtain an accessible version of the involved corpus.
 
  Address Lisboa; Portugal; November 2016  
  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 IberSPEECH  
  Notes DAG; MV; 600.097;SIAI Approved no  
  Call Number Admin @ si @MLF2016 Serial 2813  
Permanent link to this record
 

 
Author Simone Balocco; Maria Zuluaga; Guillaume Zahnd; Su-Lin Lee; Stefanie Demirci edit  isbn
openurl 
  Title (down) Computing and Visualization for Intravascular Imaging and Computer Assisted Stenting Type Book Whole
  Year 2016 Publication Computing and Visualization for Intravascular Imaging and Computer-Assisted Stenting Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address  
  Corporate Author Thesis  
  Publisher Elsevier Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN 9780128110188 Medium  
  Area Expedition Conference  
  Notes MILAB Approved no  
  Call Number Admin @ si @ BZZ2016 Serial 2821  
Permanent link to this record
Select All    Deselect All
 |   | 
Details
   print

Save Citations:
Export Records: