Home [151–160] << 161 162 163 164 165 166 167 168 169 170 >> [171–180]
List View
 | 
Citations
 | 
Details
   web
Records
Author Lluis Gomez; Anguelos Nicolaou; Dimosthenis Karatzas
Title Improving patch‐based scene text script identification with ensembles of conjoined networks Type Journal Article
Year (up) 2017 Publication Pattern Recognition Abbreviated Journal PR
Volume 67 Issue Pages 85-96
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 DAG; 600.084; 600.121; 600.129 Approved no
Call Number Admin @ si @ GNK2017 Serial 2887
Permanent link to this record
 
 
Author Lluis Gomez; Y. Patel; Marçal Rusiñol; C.V. Jawahar; Dimosthenis Karatzas
Title Self‐supervised learning of visual features through embedding images into text topic spaces Type Conference Article
Year (up) 2017 Publication 30th IEEE Conference on Computer Vision and Pattern Recognition Abbreviated Journal
Volume Issue Pages
Keywords
Abstract End-to-end training from scratch of current deep architectures for new computer vision problems would require Imagenet-scale datasets, and this is not always possible. In this paper we present a method that is able to take advantage of freely available multi-modal content to train computer vision algorithms without human supervision. We put forward the idea of performing self-supervised learning of visual features by mining a large scale corpus of multi-modal (text and image) documents. We show that discriminative visual features can be learnt efficiently by training a CNN to predict the semantic context in which a particular image is more probable to appear as an illustration. For this we leverage the hidden semantic structures discovered in the text corpus with a well-known topic modeling technique. Our experiments demonstrate state of the art performance in image classification, object detection, and multi-modal retrieval compared to recent self-supervised or natural-supervised approaches.
Address Honolulu; Hawaii; 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 CVPR
Notes DAG; 600.084; 600.121 Approved no
Call Number Admin @ si @ GPR2017 Serial 2889
Permanent link to this record
 
 
Author Ivet Rafegas; Javier Vazquez; Robert Benavente; Maria Vanrell; Susana Alvarez
Title Enhancing spatio-chromatic representation with more-than-three color coding for image description Type Journal Article
Year (up) 2017 Publication Journal of the Optical Society of America A Abbreviated Journal JOSA A
Volume 34 Issue 5 Pages 827-837
Keywords
Abstract Extraction of spatio-chromatic features from color images is usually performed independently on each color channel. Usual 3D color spaces, such as RGB, present a high inter-channel correlation for natural images. This correlation can be reduced using color-opponent representations, but the spatial structure of regions with small color differences is not fully captured in two generic Red-Green and Blue-Yellow channels. To overcome these problems, we propose a new color coding that is adapted to the specific content of each image. Our proposal is based on two steps: (a) setting the number of channels to the number of distinctive colors we find in each image (avoiding the problem of channel correlation), and (b) building a channel representation that maximizes contrast differences within each color channel (avoiding the problem of low local contrast). We call this approach more-than-three color coding (MTT) to enhance the fact that the number of channels is adapted to the image content. The higher color complexity an image has, the more channels can be used to represent it. Here we select distinctive colors as the most predominant in the image, which we call color pivots, and we build the new color coding using these color pivots as a basis. To evaluate the proposed approach we measure its efficiency in an image categorization task. We show how a generic descriptor improves its performance at the description level when applied on the MTT coding.
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 CIC; 600.087 Approved no
Call Number Admin @ si @ RVB2017 Serial 2892
Permanent link to this record
 
 
Author Marçal Rusiñol; Josep Llados
Title Flowchart Recognition in Patent Information Retrieval Type Book Chapter
Year (up) 2017 Publication Current Challenges in Patent Information Retrieval Abbreviated Journal
Volume 37 Issue Pages 351-368
Keywords
Abstract
Address
Corporate Author Thesis
Publisher Springer Berlin Heidelberg Place of Publication Editor M. Lupu; K. Mayer; N. Kando; A.J. Trippe
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; 600.097; 600.121 Approved no
Call Number Admin @ si @ RuL2017 Serial 2896
Permanent link to this record
 
 
Author Victor Vaquero; German Ros; Francesc Moreno-Noguer; Antonio Lopez; Alberto Sanfeliu
Title Joint coarse-and-fine reasoning for deep optical flow Type Conference Article
Year (up) 2017 Publication 24th International Conference on Image Processing Abbreviated Journal
Volume Issue Pages 2558-2562
Keywords
Abstract We propose a novel representation for dense pixel-wise estimation tasks using CNNs that boosts accuracy and reduces training time, by explicitly exploiting joint coarse-and-fine reasoning. The coarse reasoning is performed over a discrete classification space to obtain a general rough solution, while the fine details of the solution are obtained over a continuous regression space. In our approach both components are jointly estimated, which proved to be beneficial for improving estimation accuracy. Additionally, we propose a new network architecture, which combines coarse and fine components by treating the fine estimation as a refinement built on top of the coarse solution, and therefore adding details to the general prediction. We apply our approach to the challenging problem of optical flow estimation and empirically validate it against state-of-the-art CNN-based solutions trained from scratch and tested on large optical flow datasets.
Address Beijing; China; 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 ICIP
Notes ADAS; 600.118 Approved no
Call Number Admin @ si @ VRM2017 Serial 2898
Permanent link to this record
 
 
Author Cristhian A. Aguilera-Carrasco; Angel Sappa; Cristhian Aguilera; Ricardo Toledo
Title Cross-Spectral Local Descriptors via Quadruplet Network Type Journal Article
Year (up) 2017 Publication Sensors Abbreviated Journal SENS
Volume 17 Issue 4 Pages 873
Keywords
Abstract This paper presents a novel CNN-based architecture, referred to as Q-Net, to learn local feature descriptors that are useful for matching image patches from two different spectral bands. Given correctly matched and non-matching cross-spectral image pairs, a quadruplet network is trained to map input image patches to a common Euclidean space, regardless of the input spectral band. Our approach is inspired by the recent success of triplet networks in the visible spectrum, but adapted for cross-spectral scenarios, where, for each matching pair, there are always two possible non-matching patches: one for each spectrum. Experimental evaluations on a public cross-spectral VIS-NIR dataset shows that the proposed approach improves the state-of-the-art. Moreover, the proposed technique can also be used in mono-spectral settings, obtaining a similar performance to triplet network descriptors, but requiring less training data.
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; 600.086; 600.118 Approved no
Call Number Admin @ si @ ASA2017 Serial 2914
Permanent link to this record
 
 
Author Patricia Suarez; Angel Sappa; Boris X. Vintimilla
Title Cross-Spectral Image Patch Similarity using Convolutional Neural Network Type Conference Article
Year (up) 2017 Publication IEEE International Workshop of Electronics, Control, Measurement, Signals and their application to Mechatronics Abbreviated Journal
Volume Issue Pages
Keywords
Abstract The ability to compare image regions (patches) has been the basis of many approaches to core computer vision problems, including object, texture and scene categorization. Hence, developing representations for image patches have been of interest in several works. The current work focuses on learning similarity between cross-spectral image patches with a 2 channel convolutional neural network (CNN) model. The proposed approach is an adaptation of a previous work, trying to obtain similar results than the state of the art but with a lowcost hardware. Hence, obtained results are compared with both
classical approaches, showing improvements, and a state of the art CNN based approach.
Address San Sebastian; Spain; May 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 ECMSM
Notes ADAS; 600.086; 600.118 Approved no
Call Number Admin @ si @ SSV2017a Serial 2916
Permanent link to this record
 
 
Author Angel Valencia; Roger Idrovo; Angel Sappa; Douglas Plaza; Daniel Ochoa
Title A 3D Vision Based Approach for Optimal Grasp of Vacuum Grippers Type Conference Article
Year (up) 2017 Publication IEEE International Workshop of Electronics, Control, Measurement, Signals and their application to Mechatronics Abbreviated Journal
Volume Issue Pages
Keywords
Abstract In general, robot grasping approaches are based on the usage of multi-finger grippers. However, when large size objects need to be manipulated vacuum grippers are preferred, instead of finger based grippers. This paper aims to estimate the best picking place for a two suction cups vacuum gripper,
when planar objects with an unknown size and geometry are considered. The approach is based on the estimation of geometric properties of object’s shape from a partial cloud of points (a single 3D view), in such a way that combine with considerations of a theoretical model to generate an optimal contact point
that minimizes the vacuum force needed to guarantee a grasp.
Experimental results in real scenarios are presented to show the validity of the proposed approach.
Address San Sebastian; Spain; May 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 ECMSM
Notes ADAS; 600.086; 600.118 Approved no
Call Number Admin @ si @ VIS2017 Serial 2917
Permanent link to this record
 
 
Author Cristhian Aguilera; Xavier Soria; Angel Sappa; Ricardo Toledo
Title RGBN Multispectral Images: a Novel Color Restoration Approach Type Conference Article
Year (up) 2017 Publication 15th International Conference on Practical Applications of Agents and Multi-Agent System Abbreviated Journal
Volume Issue Pages
Keywords Multispectral Imaging; Free Sensor Model; Neural Network
Abstract This paper describes a color restoration technique used to remove NIR information from single sensor cameras where color and near-infrared images are simultaneously acquired|referred to in the literature as RGBN images. The proposed approach is based on a neural network architecture that learns the NIR information contained in the RGBN images. The proposed approach is evaluated on real images obtained by using a pair of RGBN cameras. Additionally, qualitative comparisons with a nave color correction technique based on mean square
error minimization are provided.
Address Porto; Portugal; June 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 PAAMS
Notes ADAS; MSIAU; 600.118; 600.122 Approved no
Call Number Admin @ si @ ASS2017 Serial 2918
Permanent link to this record
 
 
Author Patricia Suarez; Angel Sappa; Boris X. Vintimilla
Title Learning to Colorize Infrared Images Type Conference Article
Year (up) 2017 Publication 15th International Conference on Practical Applications of Agents and Multi-Agent System Abbreviated Journal
Volume Issue Pages
Keywords CNN in multispectral imaging; Image colorization
Abstract This paper focuses on near infrared (NIR) image colorization by using a Generative Adversarial Network (GAN) architecture model. The proposed architecture consists of two stages. Firstly, it learns to colorize the given input, resulting in a RGB image. Then, in the second stage, a discriminative model is used to estimate the probability that the generated image came from the training dataset, rather than the image automatically generated. The proposed model starts the learning process from scratch, because our set of images is very di erent from the dataset used in existing pre-trained models, so transfer learning strategies cannot be used. Infrared image colorization is an important problem when human perception need to be considered, e.g, in remote sensing applications. Experimental results with a large set of real images are provided showing the validity of the proposed approach.
Address Porto; Portugal; June 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 PAAMS
Notes ADAS; MSIAU; 600.086; 600.122; 600.118 Approved no
Call Number Admin @ si @ Serial 2919
Permanent link to this record
 
 
Author Patricia Suarez; Angel Sappa; Boris X. Vintimilla
Title Infrared Image Colorization based on a Triplet DCGAN Architecture Type Conference Article
Year (up) 2017 Publication IEEE Conference on Computer Vision and Pattern Recognition Workshops Abbreviated Journal
Volume Issue Pages
Keywords
Abstract This paper proposes a novel approach for colorizing near infrared (NIR) images using Deep Convolutional Generative Adversarial Network (GAN) architectures. The proposed approach is based on the usage of a triplet model for learning each color channel independently, in a more homogeneous way. It allows a fast convergence during the training, obtaining a greater similarity between the given NIR image and the corresponding ground truth. The proposed approach has been evaluated with a large data set of NIR images and compared with a recent approach, which is also based on a GAN architecture but in this case all the
color channels are obtained at the same time.
Address Honolulu; Hawaii; 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 ADAS; 600.086; 600.118 Approved no
Call Number Admin @ si @ SSV2017b Serial 2920
Permanent link to this record
 
 
Author Mikhail Mozerov; Joost Van de Weijer
Title Improved Recursive Geodesic Distance Computation for Edge Preserving Filter Type Journal Article
Year (up) 2017 Publication IEEE Transactions on Image Processing Abbreviated Journal TIP
Volume 26 Issue 8 Pages 3696 - 3706
Keywords Geodesic distance filter; color image filtering; image enhancement
Abstract All known recursive filters based on the geodesic distance affinity are realized by two 1D recursions applied in two orthogonal directions of the image plane. The 2D extension of the filter is not valid and has theoretically drawbacks, which lead to known artifacts. In this paper, a maximum influence propagation method is proposed to approximate the 2D extension for the
geodesic distance-based recursive filter. The method allows to partially overcome the drawbacks of the 1D recursion approach. We show that our improved recursion better approximates the true geodesic distance filter, and the application of this improved filter for image denoising outperforms the existing recursive implementation of the geodesic distance. As an application,
we consider a geodesic distance-based filter for image denoising.
Experimental evaluation of our denoising method demonstrates comparable and for several test images better results, than stateof-the-art approaches, while our algorithm is considerably fasterwith computational complexity O(8P).
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 LAMP; ISE; 600.120; 600.098; 600.119 Approved no
Call Number Admin @ si @ Moz2017 Serial 2921
Permanent link to this record
 
 
Author Hugo Jair Escalante; Isabelle Guyon; Sergio Escalera; Julio C. S. Jacques Junior; Xavier Baro; Evelyne Viegas; Yagmur Gucluturk; Umut Guclu; Marcel A. J. van Gerven; Rob van Lier; Meysam Madadi; Stephane Ayache
Title Design of an Explainable Machine Learning Challenge for Video Interviews Type Conference Article
Year (up) 2017 Publication International Joint Conference on Neural Networks Abbreviated Journal
Volume Issue Pages
Keywords
Abstract This paper reviews and discusses research advances on “explainable machine learning” in computer vision. We focus on a particular area of the “Looking at People” (LAP) thematic domain: first impressions and personality analysis. Our aim is to make the computational intelligence and computer vision communities aware of the importance of developing explanatory mechanisms for computer-assisted decision making applications, such as automating recruitment. Judgments based on personality traits are being made routinely by human resource departments to evaluate the candidates' capacity of social insertion and their potential of career growth. However, inferring personality traits and, in general, the process by which we humans form a first impression of people, is highly subjective and may be biased. Previous studies have demonstrated that learning machines can learn to mimic human decisions. In this paper, we go one step further and formulate the problem of explaining the decisions of the models as a means of identifying what visual aspects are important, understanding how they relate to decisions suggested, and possibly gaining insight into undesirable negative biases. We design a new challenge on explainability of learning machines for first impressions analysis. We describe the setting, scenario, evaluation metrics and preliminary outcomes of the competition. To the best of our knowledge this is the first effort in terms of challenges for explainability in computer vision. In addition our challenge design comprises several other quantitative and qualitative elements of novelty, including a “coopetition” setting, which combines competition and collaboration.
Address Anchorage; Alaska; USA; May 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 IJCNN
Notes HUPBA; no proj Approved no
Call Number Admin @ si @ EGE2017 Serial 2922
Permanent link to this record
 
 
Author Julio C. S. Jacques Junior; Xavier Baro; Sergio Escalera
Title Exploiting feature representations through similarity learning and ranking aggregation for person re-identification Type Conference Article
Year (up) 2017 Publication 12th IEEE International Conference on Automatic Face and Gesture Recognition Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Person re-identification has received special attentionby the human analysis community in the last few years.To address the challenges in this field, many researchers haveproposed different strategies, which basically exploit eithercross-view invariant features or cross-view robust metrics. Inthis work we propose to combine different feature representationsthrough ranking aggregation. Spatial information, whichpotentially benefits the person matching, is represented usinga 2D body model, from which color and texture informationare extracted and combined. We also consider contextualinformation (background and foreground data), automaticallyextracted via Deep Decompositional Network, and the usage ofConvolutional Neural Network (CNN) features. To describe thematching between images we use the polynomial feature map,also taking into account local and global information. Finally,the Stuart ranking aggregation method is employed to combinecomplementary ranking lists obtained from different featurerepresentations. Experimental results demonstrated that weimprove the state-of-the-art on VIPeR and PRID450s datasets,achieving 58.77% and 71.56% on top-1 rank recognitionrate, respectively, as well as obtaining competitive results onCUHK01 dataset.
Address Washington; DC; USA; May 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 FG
Notes HUPBA; 602.143 Approved no
Call Number Admin @ si @ JBE2017 Serial 2923
Permanent link to this record
 
 
Author Iiris Lusi; Julio C. S. Jacques Junior; Jelena Gorbova; Xavier Baro; Sergio Escalera; Hasan Demirel; Juri Allik; Cagri Ozcinar; Gholamreza Anbarjafari
Title Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation: Databases Type Conference Article
Year (up) 2017 Publication 12th IEEE International Conference on Automatic Face and Gesture Recognition Abbreviated Journal
Volume Issue Pages
Keywords
Abstract In this work two databases for the Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation1 are introduced. Head pose estimation paired with and detailed emotion recognition have become very important in relation to human-computer interaction. The 3D head pose database, SASE, is a 3D database acquired with Microsoft Kinect 2 camera, including RGB and depth information of different head poses which is composed by a total of 30000 frames with annotated markers, including 32 male and 18 female subjects. For the dominant and complementary emotion database, iCVMEFED, includes 31250 images with different emotions of 115 subjects whose gender distribution is almost uniform. For each subject there are 5 samples. The emotions are composed by 7 basic emotions plus neutral, being defined as complementary and dominant pairs. The emotion associated to the images were labeled with the support of psychologists.
Address Washington; DC; USA; May 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 FG
Notes HUPBA; no menciona Approved no
Call Number Admin @ si @ LJG2017 Serial 2924
Permanent link to this record