Home [171–180] << 181 182 183 184 185 186 187 188 189 190 >> [191–200]
List View
 | 
Citations
 | 
Details
   web
Records
Author Fernando Vilariño; Dimosthenis Karatzas; Alberto Valcarce
Title Libraries as New Innovation Hubs: The Library Living Lab Type Conference Article
Year 2018 Publication 30th ISPIM Innovation Conference Abbreviated Journal
Volume Issue Pages
Keywords (down)
Abstract Libraries are in deep transformation both in EU and around the world, and they are thriving within a great window of opportunity for innovation. In this paper, we show how the Library Living Lab in Barcelona participated of this changing scenario and contributed to create the Bibliolab program, where more than 200 public libraries give voice to their users in a global user-centric innovation initiative, using technology as enabling factor. The Library Living Lab is a real 4-helix implementation where Universities, Research Centers, Public Administration, Companies and the Neighbors are joint together to explore how technology transforms the cultural experience of people. This case is an example of scalability and provides reference tools for policy making, sustainability, user engage methodologies and governance. We provide specific examples of new prototypes and services that help to understand how to redefine the role of the Library as a real hub for social innovation.
Address Stockholm; May 2018
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 ISPIM
Notes DAG; MV; 600.097; 600.121; 600.129;SIAI Approved no
Call Number Admin @ si @ VKV2018b Serial 3154
Permanent link to this record
 
 
Author Abel Gonzalez-Garcia; Joost Van de Weijer; Yoshua Bengio
Title Image-to-image translation for cross-domain disentanglement Type Conference Article
Year 2018 Publication 32nd Annual Conference on Neural Information Processing Systems Abbreviated Journal
Volume Issue Pages
Keywords (down)
Abstract
Address Montreal; Canada; December 2018
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 NIPS
Notes LAMP; 600.120 Approved no
Call Number Admin @ si @ GWB2018 Serial 3155
Permanent link to this record
 
 
Author Marc Masana; Idoia Ruiz; Joan Serrat; Joost Van de Weijer; Antonio Lopez
Title Metric Learning for Novelty and Anomaly Detection Type Conference Article
Year 2018 Publication 29th British Machine Vision Conference Abbreviated Journal
Volume Issue Pages
Keywords (down)
Abstract When neural networks process images which do not resemble the distribution seen during training, so called out-of-distribution images, they often make wrong predictions, and do so too confidently. The capability to detect out-of-distribution images is therefore crucial for many real-world applications. We divide out-of-distribution detection between novelty detection ---images of classes which are not in the training set but are related to those---, and anomaly detection ---images with classes which are unrelated to the training set. By related we mean they contain the same type of objects, like digits in MNIST and SVHN. Most existing work has focused on anomaly detection, and has addressed this problem considering networks trained with the cross-entropy loss. Differently from them, we propose to use metric learning which does not have the drawback of the softmax layer (inherent to cross-entropy methods), which forces the network to divide its prediction power over the learned classes. We perform extensive experiments and evaluate both novelty and anomaly detection, even in a relevant application such as traffic sign recognition, obtaining comparable or better results than previous works.
Address Newcastle; uk; September 2018
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 LAMP; ADAS; 601.305; 600.124; 600.106; 602.200; 600.120; 600.118 Approved no
Call Number Admin @ si @ MRS2018 Serial 3156
Permanent link to this record
 
 
Author Xialei Liu; Marc Masana; Luis Herranz; Joost Van de Weijer; Antonio Lopez; Andrew Bagdanov
Title Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting Type Conference Article
Year 2018 Publication 24th International Conference on Pattern Recognition Abbreviated Journal
Volume Issue Pages 2262-2268
Keywords (down)
Abstract In this paper we propose an approach to avoiding catastrophic forgetting in sequential task learning scenarios. Our technique is based on a network reparameterization that approximately diagonalizes the Fisher Information Matrix of the network parameters. This reparameterization takes the form of
a factorized rotation of parameter space which, when used in conjunction with Elastic Weight Consolidation (which assumes a diagonal Fisher Information Matrix), leads to significantly better performance on lifelong learning of sequential tasks. Experimental results on the MNIST, CIFAR-100, CUB-200 and
Stanford-40 datasets demonstrate that we significantly improve the results of standard elastic weight consolidation, and that we obtain competitive results when compared to the state-of-the-art in lifelong learning without forgetting.
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 ICPR
Notes LAMP; ADAS; 601.305; 601.109; 600.124; 600.106; 602.200; 600.120; 600.118 Approved no
Call Number Admin @ si @ LMH2018 Serial 3160
Permanent link to this record
 
 
Author Cristina Sanchez Montes; F. Javier Sanchez; Jorge Bernal; Henry Cordova; Maria Lopez Ceron; Miriam Cuatrecasas; Cristina Rodriguez de Miguel; Ana Garcia Rodriguez; Rodrigo Garces Duran; Maria Pellise; Josep Llach; Gloria Fernandez Esparrach
Title Computer-aided Prediction of Polyp Histology on White-Light Colonoscopy using Surface Pattern Analysis Type Journal Article
Year 2019 Publication Endoscopy Abbreviated Journal END
Volume 51 Issue 3 Pages 261-265
Keywords (down)
Abstract Background and study aims: To evaluate a new computational histology prediction system based on colorectal polyp textural surface patterns using high definition white light images.
Patients and methods: Textural elements (textons) were characterized according to their contrast with respect to the surface, shape and number of bifurcations, assuming that dysplastic polyps are associated with highly contrasted, large tubular patterns with some degree of bifurcation. Computer-aided diagnosis (CAD) was compared with pathological diagnosis and the diagnosis by the endoscopists using Kudo and NICE classification.
Results: Images of 225 polyps were evaluated (142 dysplastic and 83 non-dysplastic). CAD system correctly classified 205 (91.1%) polyps, 131/142 (92.3%) dysplastic and 74/83 (89.2%) non-dysplastic. For the subgroup of 100 diminutive (<5 mm) polyps, CAD correctly classified 87 (87%) polyps, 43/50 (86%) dysplastic and 44/50 (88%) non-dysplastic. There were not statistically significant differences in polyp histology prediction based on CAD system and on endoscopist assessment.
Conclusion: A computer vision system based on the characterization of the polyp surface in the white light accurately predicts colorectal polyp histology.
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 MV; 600.096; 600.119; 600.075 Approved no
Call Number Admin @ si @ SSB2019 Serial 3164
Permanent link to this record
 
 
Author Lei Kang; Juan Ignacio Toledo; Pau Riba; Mauricio Villegas; Alicia Fornes; Marçal Rusiñol
Title Convolve, Attend and Spell: An Attention-based Sequence-to-Sequence Model for Handwritten Word Recognition Type Conference Article
Year 2018 Publication 40th German Conference on Pattern Recognition Abbreviated Journal
Volume Issue Pages 459-472
Keywords (down)
Abstract This paper proposes Convolve, Attend and Spell, an attention based sequence-to-sequence model for handwritten word recognition. The proposed architecture has three main parts: an encoder, consisting of a CNN and a bi-directional GRU, an attention mechanism devoted to focus on the pertinent features and a decoder formed by a one-directional GRU, able to spell the corresponding word, character by character. Compared with the recent state-of-the-art, our model achieves competitive results on the IAM dataset without needing any pre-processing step, predefined lexicon nor language model. Code and additional results are available in https://github.com/omni-us/research-seq2seq-HTR.
Address Stuttgart; Germany; October 2018
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 GCPR
Notes DAG; 600.097; 603.057; 302.065; 601.302; 600.084; 600.121; 600.129 Approved no
Call Number Admin @ si @ KTR2018 Serial 3167
Permanent link to this record
 
 
Author Alicia Fornes; Bart Lamiroy
Title Graphics Recognition, Current Trends and Evolutions Type Book Whole
Year 2018 Publication Graphics Recognition, Current Trends and Evolutions Abbreviated Journal
Volume 11009 Issue Pages
Keywords (down)
Abstract This book constitutes the thoroughly refereed post-conference proceedings of the 12th International Workshop on Graphics Recognition, GREC 2017, held in Kyoto, Japan, in November 2017.
The 10 revised full papers presented were carefully reviewed and selected from 14 initial submissions. They contain both classical and emerging topics of graphics rcognition, namely analysis and detection of diagrams, search and classification, optical music recognition, interpretation of engineering drawings and maps.
Address
Corporate Author Thesis
Publisher Springer International Publishing Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN ISBN 978-3-030-02283-9 Medium
Area Expedition Conference
Notes DAG; 600.121 Approved no
Call Number Admin @ si @ FoL2018 Serial 3171
Permanent link to this record
 
 
Author Raul Gomez; Lluis Gomez; Jaume Gibert; Dimosthenis Karatzas
Title Learning from# Barcelona Instagram data what Locals and Tourists post about its Neighbourhoods Type Conference Article
Year 2018 Publication 15th European Conference on Computer Vision Workshops Abbreviated Journal
Volume 11134 Issue Pages 530-544
Keywords (down)
Abstract Massive tourism is becoming a big problem for some cities, such as Barcelona, due to its concentration in some neighborhoods. In this work we gather Instagram data related to Barcelona consisting on images-captions pairs and, using the text as a supervisory signal, we learn relations between images, words and neighborhoods. Our goal is to learn which visual elements appear in photos when people is posting about each neighborhood. We perform a language separate treatment of the data and show that it can be extrapolated to a tourists and locals separate analysis, and that tourism is reflected in Social Media at a neighborhood level. The presented pipeline allows analyzing the differences between the images that tourists and locals associate to the different neighborhoods. The proposed method, which can be extended to other cities or subjects, proves that Instagram data can be used to train multi-modal (image and text) machine learning models that are useful to analyze publications about a city at a neighborhood level. We publish the collected dataset, InstaBarcelona and the code used in the analysis.
Address Munich; Alemanya; September 2018
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 ECCVW
Notes DAG; 600.129; 601.338; 600.121 Approved no
Call Number Admin @ si @ GGG2018b Serial 3176
Permanent link to this record
 
 
Author Y. Patel; Lluis Gomez; Raul Gomez; Marçal Rusiñol; Dimosthenis Karatzas; C.V. Jawahar
Title TextTopicNet-Self-Supervised Learning of Visual Features Through Embedding Images on Semantic Text Spaces Type Miscellaneous
Year 2018 Publication Arxiv Abbreviated Journal
Volume Issue Pages
Keywords (down)
Abstract The immense success of deep learning based methods in computer vision heavily relies on large scale training datasets. These richly annotated datasets help the network learn discriminative visual features. Collecting and annotating such datasets requires a tremendous amount of human effort and annotations are limited to popular set of classes. As an alternative, learning visual features by designing auxiliary tasks which make use of freely available self-supervision has become increasingly popular in the computer vision community.
In this paper, we put forward an idea to take advantage of multi-modal context to provide self-supervision for the training of computer vision algorithms. We show that adequate visual features can be learned efficiently by training a CNN to predict the semantic textual context in which a particular image is more probable to appear as an illustration. More specifically we use popular text embedding techniques to provide the self-supervision for the training of deep CNN.
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; 601.338; 600.121 Approved no
Call Number Admin @ si @ PGG2018 Serial 3177
Permanent link to this record
 
 
Author Anguelos Nicolaou; Sounak Dey; V.Christlein; A.Maier; Dimosthenis Karatzas
Title Non-deterministic Behavior of Ranking-based Metrics when Evaluating Embeddings Type Conference Article
Year 2018 Publication International Workshop on Reproducible Research in Pattern Recognition Abbreviated Journal
Volume 11455 Issue Pages 71-82
Keywords (down)
Abstract Embedding data into vector spaces is a very popular strategy of pattern recognition methods. When distances between embeddings are quantized, performance metrics become ambiguous. In this paper, we present an analysis of the ambiguity quantized distances introduce and provide bounds on the effect. We demonstrate that it can have a measurable effect in empirical data in state-of-the-art systems. We also approach the phenomenon from a computer security perspective and demonstrate how someone being evaluated by a third party can exploit this ambiguity and greatly outperform a random predictor without even access to the input data. We also suggest a simple solution making the performance metrics, which rely on ranking, totally deterministic and impervious to such exploits.
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 DAG; 600.121; 600.129 Approved no
Call Number Admin @ si @ NDC2018 Serial 3178
Permanent link to this record
 
 
Author Dena Bazazian; Dimosthenis Karatzas; Andrew Bagdanov
Title Word Spotting in Scene Images based on Character Recognition Type Conference Article
Year 2018 Publication IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops Abbreviated Journal
Volume Issue Pages 1872-1874
Keywords (down)
Abstract In this paper we address the problem of unconstrained Word Spotting in scene images. We train a Fully Convolutional Network to produce heatmaps of all the character classes. Then, we employ the Text Proposals approach and, via a rectangle classifier, detect the most likely rectangle for each query word based on the character attribute maps. We evaluate the proposed method on ICDAR2015 and show that it is capable of identifying and recognizing query words in natural scene images.
Address Salt Lake City; USA; June 2018
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 DAG; 600.129; 600.121 Approved no
Call Number BKB2018a Serial 3179
Permanent link to this record
 
 
Author Adrien Gaidon; Antonio Lopez; Florent Perronnin
Title The Reasonable Effectiveness of Synthetic Visual Data Type Journal Article
Year 2018 Publication International Journal of Computer Vision Abbreviated Journal IJCV
Volume 126 Issue 9 Pages 899–901
Keywords (down)
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; 600.118 Approved no
Call Number Admin @ si @ GLP2018 Serial 3180
Permanent link to this record
 
 
Author Zhijie Fang; Antonio Lopez
Title Is the Pedestrian going to Cross? Answering by 2D Pose Estimation Type Conference Article
Year 2018 Publication IEEE Intelligent Vehicles Symposium Abbreviated Journal
Volume Issue Pages 1271 - 1276
Keywords (down)
Abstract Our recent work suggests that, thanks to nowadays powerful CNNs, image-based 2D pose estimation is a promising cue for determining pedestrian intentions such as crossing the road in the path of the ego-vehicle, stopping before entering the road, and starting to walk or bending towards the road. This statement is based on the results obtained on non-naturalistic sequences (Daimler dataset), i.e. in sequences choreographed specifically for performing the study. Fortunately, a new publicly available dataset (JAAD) has appeared recently to allow developing methods for detecting pedestrian intentions in naturalistic driving conditions; more specifically, for addressing the relevant question is the pedestrian going to cross? Accordingly, in this paper we use JAAD to assess the usefulness of 2D pose estimation for answering such a question. We combine CNN-based pedestrian detection, tracking and pose estimation to predict the crossing action from monocular images. Overall, the proposed pipeline provides new state-ofthe-art results.
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 IV
Notes ADAS; 600.124; 600.116; 600.118 Approved no
Call Number Admin @ si @ FaL2018 Serial 3181
Permanent link to this record
 
 
Author Jiaolong Xu; Peng Wang; Heng Yang; Antonio Lopez
Title Training a Binary Weight Object Detector by Knowledge Transfer for Autonomous Driving Type Conference Article
Year 2019 Publication IEEE International Conference on Robotics and Automation Abbreviated Journal
Volume Issue Pages 2379-2384
Keywords (down)
Abstract Autonomous driving has harsh requirements of small model size and energy efficiency, in order to enable the embedded system to achieve real-time on-board object detection. Recent deep convolutional neural network based object detectors have achieved state-of-the-art accuracy. However, such models are trained with numerous parameters and their high computational costs and large storage prohibit the deployment to memory and computation resource limited systems. Low-precision neural networks are popular techniques for reducing the computation requirements and memory footprint. Among them, binary weight neural network (BWN) is the extreme case which quantizes the float-point into just bit. BWNs are difficult to train and suffer from accuracy deprecation due to the extreme low-bit representation. To address this problem, we propose a knowledge transfer (KT) method to aid the training of BWN using a full-precision teacher network. We built DarkNet-and MobileNet-based binary weight YOLO-v2 detectors and conduct experiments on KITTI benchmark for car, pedestrian and cyclist detection. The experimental results show that the proposed method maintains high detection accuracy while reducing the model size of DarkNet-YOLO from 257 MB to 8.8 MB and MobileNet-YOLO from 193 MB to 7.9 MB.
Address Montreal; Canada; May 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 Medium
Area Expedition Conference ICRA
Notes ADAS; 600.124; 600.116; 600.118 Approved no
Call Number Admin @ si @ XWY2018 Serial 3182
Permanent link to this record
 
 
Author Akhil Gurram; Onay Urfalioglu; Ibrahim Halfaoui; Fahd Bouzaraa; Antonio Lopez
Title Monocular Depth Estimation by Learning from Heterogeneous Datasets Type Conference Article
Year 2018 Publication IEEE Intelligent Vehicles Symposium Abbreviated Journal
Volume Issue Pages 2176 - 2181
Keywords (down)
Abstract Depth estimation provides essential information to perform autonomous driving and driver assistance. Especially, Monocular Depth Estimation is interesting from a practical point of view, since using a single camera is cheaper than many other options and avoids the need for continuous calibration strategies as required by stereo-vision approaches. State-of-the-art methods for Monocular Depth Estimation are based on Convolutional Neural Networks (CNNs). A promising line of work consists of introducing additional semantic information about the traffic scene when training CNNs for depth estimation. In practice, this means that the depth data used for CNN training is complemented with images having pixel-wise semantic labels, which usually are difficult to annotate (eg crowded urban images). Moreover, so far it is common practice to assume that the same raw training data is associated with both types of ground truth, ie, depth and semantic labels. The main contribution of this paper is to show that this hard constraint can be circumvented, ie, that we can train CNNs for depth estimation by leveraging the depth and semantic information coming from heterogeneous datasets. In order to illustrate the benefits of our approach, we combine KITTI depth and Cityscapes semantic segmentation datasets, outperforming state-of-the-art results on Monocular Depth Estimation.
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 IV
Notes ADAS; 600.124; 600.116; 600.118 Approved no
Call Number Admin @ si @ GUH2018 Serial 3183
Permanent link to this record