Home [51–60] << 61 62 63 64 65 66 67 68 69 70 >> [71–80]
List View
 | 
Citations
 | 
Details
   web
Records
Author Cristhian Aguilera
Title Local feature description in cross-spectral imagery Type Book Whole
Year (down) 2017 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Over the last few years, the number of consumer computer vision applications has increased dramatically. Today, computer vision solutions can be found in video game consoles, smartphone applications, driving assistance – just to name a few. Ideally, we require the performance of those applications, particularly those that are safety critical to remain constant under any external environment factors, such as changes in illumination or weather conditions. However, this is not always possible or very difficult to obtain by only using visible imagery, due to the inherent limitations of the images from that spectral band. For that reason, the use of images from different or multiple spectral bands is becoming more appealing.
The aforementioned possible advantages of using images from multiples spectral bands on various vision applications make multi-spectral image processing a relevant topic for research and development. Like in visible image processing, multi-spectral image processing needs tools and algorithms to handle information from various spectral bands. Furthermore, traditional tools such as local feature detection, which is the basis of many vision tasks such as visual odometry, image registration, or structure from motion, must be adjusted or reformulated to operate under new conditions. Traditional feature detection, description, and matching methods tend to underperform in multi-spectral settings, in comparison to mono-spectral settings, due to the natural differences between each spectral band.
The work in this thesis is focused on the local feature description problem when cross-spectral images are considered. In this context, this dissertation has three main contributions. Firstly, the work starts by proposing the usage of a combination of frequency and spatial information, in a multi-scale scheme, as feature description. Evaluations of this proposal, based on classical hand-made feature descriptors, and comparisons with state of the art cross-spectral approaches help to find and understand limitations of such strategy. Secondly, different convolutional neural network (CNN) based architectures are evaluated when used to describe cross-spectral image patches. Results showed that CNN-based methods, designed to work with visible monocular images, could be successfully applied to the description of images from two different spectral bands, with just minor modifications. In this framework, a novel CNN-based network model, specifically intended to describe image patches from two different spectral bands, is proposed. This network, referred to as Q-Net, outperforms state of the art in the cross-spectral domain, including both previous hand-made solutions as well as L2 CNN-based architectures. The third contribution of this dissertation is in the cross-spectral feature description application domain. The multispectral odometry problem is tackled showing a real application of cross-spectral descriptors
In addition to the three main contributions mentioned above, in this dissertation, two different multi-spectral datasets are generated and shared with the community to be used as benchmarks for further studies.
Address October 2017
Corporate Author Thesis Ph.D. thesis
Publisher Ediciones Graficas Rey Place of Publication Editor Angel Sappa
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-84-945373-6-3 Medium
Area Expedition Conference
Notes ADAS; 600.118 Approved no
Call Number Admin @ si @ Agu2017 Serial 3020
Permanent link to this record
 
 
Author Alejandro Cartas; Mariella Dimiccoli; Petia Radeva
Title Batch-based activity recognition from egocentric photo-streams Type Conference Article
Year (down) 2017 Publication 1st International workshop on Egocentric Perception, Interaction and Computing Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Activity recognition from long unstructured egocentric photo-streams has several applications in assistive technology such as health monitoring and frailty detection, just to name a few. However, one of its main technical challenges is to deal with the low frame rate of wearable photo-cameras, which causes abrupt appearance changes between consecutive frames. In consequence, important discriminatory low-level features from motion such as optical flow cannot be estimated. In this paper, we present a batch-driven approach for training a deep learning architecture that strongly rely on Long short-term units to tackle this problem. We propose two different implementations of the same approach that process a photo-stream sequence using batches of fixed size with the goal of capturing the temporal evolution of high-level features. The main difference between these implementations is that one explicitly models consecutive batches by overlapping them. Experimental results over a public dataset acquired by three users demonstrate the validity of the proposed architectures to exploit the temporal evolution of convolutional features over time without relying on event boundaries.
Address Venice; Italy; October 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 ICCV - EPIC
Notes MILAB; no menciona Approved no
Call Number Admin @ si @ CDR2017 Serial 3023
Permanent link to this record
 
 
Author Aniol Lidon; Marc Bolaños; Mariella Dimiccoli; Petia Radeva; Maite Garolera; Xavier Giro
Title Semantic Summarization of Egocentric Photo-Stream Events Type Conference Article
Year (down) 2017 Publication 2nd Workshop on Lifelogging Tools and Applications Abbreviated Journal
Volume Issue Pages
Keywords
Abstract
Address San Francisco; USA; October 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 978-1-4503-5503-2 Medium
Area Expedition Conference ACMW (LTA)
Notes MILAB; no proj Approved no
Call Number Admin @ si @ LBD2017 Serial 3024
Permanent link to this record
 
 
Author Maedeh Aghaei; Mariella Dimiccoli; Petia Radeva
Title All the people around me: face clustering in egocentric photo streams Type Conference Article
Year (down) 2017 Publication 24th International Conference on Image Processing Abbreviated Journal
Volume Issue Pages
Keywords face discovery; face clustering; deepmatching; bag-of-tracklets; egocentric photo-streams
Abstract arxiv1703.01790
Given an unconstrained stream of images captured by a wearable photo-camera (2fpm), we propose an unsupervised bottom-up approach for automatic clustering appearing faces into the individual identities present in these data. The problem is challenging since images are acquired under real world conditions; hence the visible appearance of the people in the images undergoes intensive variations. Our proposed pipeline consists of first arranging the photo-stream into events, later, localizing the appearance of multiple people in them, and
finally, grouping various appearances of the same person across different events. Experimental results performed on a dataset acquired by wearing a photo-camera during one month, demonstrate the effectiveness of the proposed approach for the considered purpose.
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 MILAB; no menciona Approved no
Call Number Admin @ si @ EDR2017 Serial 3025
Permanent link to this record
 
 
Author Laura Igual; Santiago Segui
Title Introduction to Data Science – A Python Approach to Concepts, Techniques and Applications. Undergraduate Topics in Computer Science Type Book Whole
Year (down) 2017 Publication Abbreviated Journal
Volume Issue Pages 1-215
Keywords
Abstract
Address
Corporate Author Thesis
Publisher 978-3-319-50016-4 Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN 978-3-319-50016-4 Medium
Area Expedition Conference
Notes MILAB Approved no
Call Number Admin @ si @ IgS2017 Serial 3027
Permanent link to this record
 
 
Author Mireia Forns-Nadal; Federico Sem; Anna Mane; Laura Igual; Dani Guinart; Oscar Vilarroya
Title Increased Nucleus Accumbens Volume in First-Episode Psychosis Type Journal Article
Year (down) 2017 Publication Psychiatry Research-Neuroimaging Abbreviated Journal PRN
Volume 263 Issue Pages 57-60
Keywords
Abstract Nucleus accumbens has been reported as a key structure in the neurobiology of schizophrenia. Studies analyzing structural abnormalities have shown conflicting results, possibly related to confounding factors. We investigated the nucleus accumbens volume using manual delimitation in first-episode psychosis (FEP) controlling for age, cannabis use and medication. Thirty-one FEP subjects who were naive or minimally exposed to antipsychotics and a control group were MRI scanned and clinically assessed from baseline to 6 months of follow-up. FEP showed increased relative and total accumbens volumes. Clinical correlations with negative symptoms, duration of untreated psychosis and cannabis use were not significant.
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 MILAB; no menciona Approved no
Call Number Admin @ si @ FSM2017 Serial 3028
Permanent link to this record
 
 
Author Fernando Vilariño; Dan Norton
Title Using mutimedia tools to spread poetry collections Type Conference Article
Year (down) 2017 Publication Internet librarian International Conference Abbreviated Journal
Volume Issue Pages
Keywords
Abstract
Address London; UK; October 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 ILI
Notes MV; 600.097;SIAI Approved no
Call Number Admin @ si @ ViN2017 Serial 3031
Permanent link to this record
 
 
Author Fernando Vilariño
Title Citizen experience as a powerful communication tool: Open Innovation and the role of Living Labs in EU Type Conference Article
Year (down) 2017 Publication European Conference of Science Journalists Abbreviated Journal
Volume Issue Pages
Keywords
Abstract The Open Innovation 2.0 model spearheaded by the European Commission introduces conceptual changes in how innovation processes should be developed. The notion of an innovation ecosystem, and the active participation of the citizens (and all the different actors of the quadruple helix) in innovation processes, opens up new channels for scientific communication, where the citizens (and all actors) can be naturally reached and facilitate the spread of the scientific message in their communities. Unleashing the power of such mechanisms, while maintaining control over the scientific communication done through such channels presents an opportunity and a challenge at the same time.

This workshop will look into key concepts that the Open Innovation 2.0 EU model introduces, and what new opportunities for communication they bring about. Specifically, we will focus on Living Labs, as a key instrument for implementing this innovation model at the regional level, and their potential in creating scientific dissemination spaces.
Address Copenhagen; 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 ECSJ
Notes MV; 600.097;SIAI Approved no
Call Number Admin @ si @ Vil2017a Serial 3032
Permanent link to this record
 
 
Author Fernando Vilariño
Title Bringing and keeping all the stakeholders together: creating a catalog of models of governance for innovation Type Miscellaneous
Year (down) 2017 Publication Open Living Lab Days Report Abbreviated Journal
Volume Issue Pages
Keywords
Abstract
Address Krakow; August 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
Notes MV; no menciona;SIAI Approved no
Call Number Admin @ si @ Vil2017b Serial 3033
Permanent link to this record
 
 
Author Marc Masana; Joost Van de Weijer; Luis Herranz;Andrew Bagdanov; Jose Manuel Alvarez
Title Domain-adaptive deep network compression Type Conference Article
Year (down) 2017 Publication 17th IEEE International Conference on Computer Vision Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Deep Neural Networks trained on large datasets can be easily transferred to new domains with far fewer labeled examples by a process called fine-tuning. This has the advantage that representations learned in the large source domain can be exploited on smaller target domains. However, networks designed to be optimal for the source task are often prohibitively large for the target task. In this work we address the compression of networks after domain transfer.
We focus on compression algorithms based on low-rank matrix decomposition. Existing methods base compression solely on learned network weights and ignore the statistics of network activations. We show that domain transfer leads to large shifts in network activations and that it is desirable to take this into account when compressing.
We demonstrate that considering activation statistics when compressing weights leads to a rank-constrained regression problem with a closed-form solution. Because our method takes into account the target domain, it can more optimally
remove the redundancy in the weights. Experiments show that our Domain Adaptive Low Rank (DALR) method significantly outperforms existing low-rank compression techniques. With our approach, the fc6 layer of VGG19 can be compressed more than 4x more than using truncated SVD alone – with only a minor or no loss in accuracy. When applied to domain-transferred networks it allows for compression down to only 5-20% of the original number of parameters with only a minor drop in performance.
Address Venice; Italy; October 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 ICCV
Notes LAMP; 601.305; 600.106; 600.120 Approved no
Call Number Admin @ si @ Serial 3034
Permanent link to this record
 
 
Author Xialei Liu; Joost Van de Weijer; Andrew Bagdanov
Title RankIQA: Learning from Rankings for No-reference Image Quality Assessment Type Conference Article
Year (down) 2017 Publication 17th IEEE International Conference on Computer Vision Abbreviated Journal
Volume Issue Pages
Keywords
Abstract We propose a no-reference image quality assessment (NR-IQA) approach that learns from rankings (RankIQA). To address the problem of limited IQA dataset size, we train a Siamese Network to rank images in terms of image quality by using synthetically generated distortions for which relative image quality is known. These ranked image sets can be automatically generated without laborious human labeling. We then use fine-tuning to transfer the knowledge represented in the trained Siamese Network to a traditional CNN that estimates absolute image quality from single images. We demonstrate how our approach can be made significantly more efficient than traditional Siamese Networks by forward propagating a batch of images through a single network and backpropagating gradients derived from all pairs of images in the batch. Experiments on the TID2013 benchmark show that we improve the state-of-the-art by over 5%. Furthermore, on the LIVE benchmark we show that our approach is superior to existing NR-IQA techniques and that we even outperform the state-of-the-art in full-reference IQA (FR-IQA) methods without having to resort to high-quality reference images to infer IQA.
Address Venice; Italy; October 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 ICCV
Notes LAMP; 600.106; 600.109; 600.120 Approved no
Call Number Admin @ si @ LWB2017b Serial 3036
Permanent link to this record
 
 
Author Rada Deeb; Damien Muselet; Mathieu Hebert; Alain Tremeau; Joost Van de Weijer
Title 3D color charts for camera spectral sensitivity estimation Type Conference Article
Year (down) 2017 Publication 28th British Machine Vision Conference Abbreviated Journal
Volume Issue Pages
Keywords
Abstract Estimating spectral data such as camera sensor responses or illuminant spectral power distribution from raw RGB camera outputs is crucial in many computer vision applications.
Usually, 2D color charts with various patches of known spectral reflectance are
used as reference for such purpose. Deducing n-D spectral data (n»3) from 3D RGB inputs is an ill-posed problem that requires a high number of inputs. Unfortunately, most of the natural color surfaces have spectral reflectances that are well described by low-dimensional linear models, i.e. each spectral reflectance can be approximated by a weighted sum of the others. It has been shown that adding patches to color charts does not help in practice, because the information they add is redundant with the information provided by the first set of patches. In this paper, we propose to use spectral data of
higher dimensionality by using 3D color charts that create inter-reflections between the surfaces. These inter-reflections produce multiplications between natural spectral curves and so provide non-linear spectral curves. We show that such data provide enough information for accurate spectral data estimation.
Address London; 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 LAMP; 600.109; 600.120 Approved no
Call Number Admin @ si @ DMH2017b Serial 3037
Permanent link to this record
 
 
Author Muhammad Anwer Rao; Fahad Shahbaz Khan; Joost Van de Weijer; Jorma Laaksonen
Title Tex-Nets: Binary Patterns Encoded Convolutional Neural Networks for Texture Recognition Type Conference Article
Year (down) 2017 Publication 19th International Conference on Multimodal Interaction Abbreviated Journal
Volume Issue Pages
Keywords Convolutional Neural Networks; Texture Recognition; Local Binary Paterns
Abstract Recognizing materials and textures in realistic imaging conditions is a challenging computer vision problem. For many years, local features based orderless representations were a dominant approach for texture recognition. Recently deep local features, extracted from the intermediate layers of a Convolutional Neural Network (CNN), are used as filter banks. These dense local descriptors from a deep model, when encoded with Fisher Vectors, have shown to provide excellent results for texture recognition. The CNN models, employed in such approaches, take RGB patches as input and train on a large amount of labeled images. We show that CNN models, which we call TEX-Nets, trained using mapped coded images with explicit texture information provide complementary information to the standard deep models trained on RGB patches. We further investigate two deep architectures, namely early and late fusion, to combine the texture and color information. Experiments on benchmark texture datasets clearly demonstrate that TEX-Nets provide complementary information to standard RGB deep network. Our approach provides a large gain of 4.8%, 3.5%, 2.6% and 4.1% respectively in accuracy on the DTD, KTH-TIPS-2a, KTH-TIPS-2b and Texture-10 datasets, compared to the standard RGB network of the same architecture. Further, our final combination leads to consistent improvements over the state-of-the-art on all four datasets.
Address Glasgow; Scothland; November 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 ACM
Notes LAMP; 600.109; 600.068; 600.120 Approved no
Call Number Admin @ si @ RKW2017 Serial 3038
Permanent link to this record
 
 
Author Muhammad Anwer Rao; Fahad Shahbaz Khan; Joost Van de Weijer; Jorma Laaksonen
Title Top-Down Deep Appearance Attention for Action Recognition Type Conference Article
Year (down) 2017 Publication 20th Scandinavian Conference on Image Analysis Abbreviated Journal
Volume 10269 Issue Pages 297-309
Keywords Action recognition; CNNs; Feature fusion
Abstract Recognizing human actions in videos is a challenging problem in computer vision. Recently, convolutional neural network based deep features have shown promising results for action recognition. In this paper, we investigate the problem of fusing deep appearance and motion cues for action recognition. We propose a video representation which combines deep appearance and motion based local convolutional features within the bag-of-deep-features framework. Firstly, dense deep appearance and motion based local convolutional features are extracted from spatial (RGB) and temporal (flow) networks, respectively. Both visual cues are processed in parallel by constructing separate visual vocabularies for appearance and motion. A category-specific appearance map is then learned to modulate the weights of the deep motion features. The proposed representation is discriminative and binds the deep local convolutional features to their spatial locations. Experiments are performed on two challenging datasets: JHMDB dataset with 21 action classes and ACT dataset with 43 categories. The results clearly demonstrate that our approach outperforms both standard approaches of early and late feature fusion. Further, our approach is only employing action labels and without exploiting body part information, but achieves competitive performance compared to the state-of-the-art deep features based approaches.
Address Tromso; June 2017
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 SCIA
Notes LAMP; 600.109; 600.068; 600.120 Approved no
Call Number Admin @ si @ RKW2017b Serial 3039
Permanent link to this record
 
 
Author N.Nayef; F.Yin; I.Bizid; H.Choi; Y.Feng; Dimosthenis Karatzas; Z.Luo; Umapada Pal; Christophe Rigaud; J. Chazalon; W.Khlif; Muhammad Muzzamil Luqman; Jean-Christophe Burie; C.L.Liu; Jean-Marc Ogier
Title ICDAR2017 Robust Reading Challenge on Multi-Lingual Scene Text Detection and Script Identification – RRC-MLT Type Conference Article
Year (down) 2017 Publication 14th International Conference on Document Analysis and Recognition Abbreviated Journal
Volume Issue Pages 1454-1459
Keywords
Abstract Text detection and recognition in a natural environment are key components of many applications, ranging from business card digitization to shop indexation in a street. This competition aims at assessing the ability of state-of-the-art methods to detect Multi-Lingual Text (MLT) in scene images, such as in contents gathered from the Internet media and in modern cities where multiple cultures live and communicate together. This competition is an extension of the Robust Reading Competition (RRC) which has been held since 2003 both in ICDAR and in an online context. The proposed competition is presented as a new challenge of the RRC. The dataset built for this challenge largely extends the previous RRC editions in many aspects: the multi-lingual text, the size of the dataset, the multi-oriented text, the wide variety of scenes. The dataset is comprised of 18,000 images which contain text belonging to 9 languages. The challenge is comprised of three tasks related to text detection and script classification. We have received a total of 16 participations from the research and industrial communities. This paper presents the dataset, the tasks and the findings of this RRC-MLT challenge.
Address Kyoto; Japan; November 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 978-1-5386-3586-5 Medium
Area Expedition Conference ICDAR
Notes DAG; 600.121 Approved no
Call Number Admin @ si @ NYB2017 Serial 3097
Permanent link to this record