Home | [171–180] << 181 182 183 184 185 186 187 188 189 190 >> [191–200] |
![]() |
Records | |||||
---|---|---|---|---|---|
Author | Jaume Gibert; Ernest Valveny; Horst Bunke | ||||
Title | Vocabulary Selection for Graph of Words Embedding | Type | Conference Article | ||
Year | 2011 | Publication | 5th Iberian Conference on Pattern Recognition and Image Analysis | Abbreviated Journal | |
Volume | 6669 | Issue | Pages | 216-223 | |
Keywords | |||||
Abstract ![]() |
The Graph of Words Embedding consists in mapping every graph in a given dataset to a feature vector by counting unary and binary relations between node attributes of the graph. It has been shown to perform well for graphs with discrete label alphabets. In this paper we extend the methodology to graphs with n-dimensional continuous attributes by selecting node representatives. We propose three different discretization procedures for the attribute space and experimentally evaluate the dependence on both the selector and the number of node representatives. In the context of graph classification, the experimental results reveal that on two out of three public databases the proposed extension achieves superior performance over a standard reference system. | ||||
Address | Las Palmas de Gran Canaria. Spain | ||||
Corporate Author | Thesis | ||||
Publisher | Springer | Place of Publication | Berlin | Editor | Vitria, Jordi; Sanches, João Miguel Raposo; Hernández, Mario |
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | LNCS | ||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | 978-3-642-21256-7 | Medium | ||
Area | Expedition | Conference | IbPRIA | ||
Notes | DAG | Approved | no | ||
Call Number | Admin @ si @ GVB2011b | Serial | 1744 | ||
Permanent link to this record | |||||
Author | Jaume Gibert; Ernest Valveny; Horst Bunke | ||||
Title | Dimensionality Reduction for Graph of Words Embedding | Type | Conference Article | ||
Year | 2011 | Publication | 8th IAPR-TC-15 International Workshop. Graph-Based Representations in Pattern Recognition | Abbreviated Journal | |
Volume | 6658 | Issue | Pages | 22-31 | |
Keywords | |||||
Abstract ![]() |
The Graph of Words Embedding consists in mapping every graph of a given dataset to a feature vector by counting unary and binary relations between node attributes of the graph. While it shows good properties in classification problems, it suffers from high dimensionality and sparsity. These two issues are addressed in this article. Two well-known techniques for dimensionality reduction, kernel principal component analysis (kPCA) and independent component analysis (ICA), are applied to the embedded graphs. We discuss their performance compared to the classification of the original vectors on three different public databases of graphs. | ||||
Address | Münster, Germany | ||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | Xiaoyi Jiang; Miquel Ferrer; Andrea Torsello | ||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | LNCS | ||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | 978-3-642-20843-0 | Medium | ||
Area | Expedition | Conference | GbRPR | ||
Notes | DAG | Approved | no | ||
Call Number | Admin @ si @ GVB2011a | Serial | 1743 | ||
Permanent link to this record | |||||
Author | Xavier Boix; Josep M. Gonfaus; Joost Van de Weijer; Andrew Bagdanov; Joan Serrat; Jordi Gonzalez | ||||
Title | Harmony Potentials: Fusing Global and Local Scale for Semantic Image Segmentation | Type | Journal Article | ||
Year | 2012 | Publication | International Journal of Computer Vision | Abbreviated Journal | IJCV |
Volume | 96 | Issue | 1 | Pages | 83-102 |
Keywords | |||||
Abstract ![]() |
The Hierarchical Conditional Random Field(HCRF) model have been successfully applied to a number of image labeling problems, including image segmentation. However, existing HCRF models of image segmentation do not allow multiple classes to be assigned to a single region, which limits their ability to incorporate contextual information across multiple scales.
At higher scales in the image, this representation yields an oversimplied model since multiple classes can be reasonably expected to appear within large regions. This simplied model particularly limits the impact of information at higher scales. Since class-label information at these scales is usually more reliable than at lower, noisier scales, neglecting this information is undesirable. To address these issues, we propose a new consistency potential for image labeling problems, which we call the harmony potential. It can encode any possible combi- nation of labels, penalizing only unlikely combinations of classes. We also propose an eective sampling strategy over this expanded label set that renders tractable the underlying optimization problem. Our approach obtains state-of-the-art results on two challenging, standard benchmark datasets for semantic image segmentation: PASCAL VOC 2010, and MSRC-21. |
||||
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 | 0920-5691 | ISBN | Medium | ||
Area | Expedition | Conference | |||
Notes | ISE;CIC;ADAS | Approved | no | ||
Call Number | Admin @ si @ BGW2012 | Serial | 1718 | ||
Permanent link to this record | |||||
Author | Xavier Baro; Sergio Escalera; Jordi Vitria; Oriol Pujol; Petia Radeva | ||||
Title | Traffic Sign Recognition Using Evolutionary Adaboost Detection and Forest-ECOC Classification | Type | Journal Article | ||
Year | 2009 | Publication | IEEE Transactions on Intelligent Transportation Systems | Abbreviated Journal | TITS |
Volume | 10 | Issue | 1 | Pages | 113–126 |
Keywords | |||||
Abstract ![]() |
The high variability of sign appearance in uncontrolled environments has made the detection and classification of road signs a challenging problem in computer vision. In this paper, we introduce a novel approach for the detection and classification of traffic signs. Detection is based on a boosted detectors cascade, trained with a novel evolutionary version of Adaboost, which allows the use of large feature spaces. Classification is defined as a multiclass categorization problem. A battery of classifiers is trained to split classes in an Error-Correcting Output Code (ECOC) framework. We propose an ECOC design through a forest of optimal tree structures that are embedded in the ECOC matrix. The novel system offers high performance and better accuracy than the state-of-the-art strategies and is potentially better in terms of noise, affine deformation, partial occlusions, and reduced illumination. | ||||
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 | 1524-9050 | ISBN | Medium | ||
Area | Expedition | Conference | |||
Notes | OR;MILAB;HuPBA;MV | Approved | no | ||
Call Number | BCNPCL @ bcnpcl @ BEV2008 | Serial | 1116 | ||
Permanent link to this record | |||||
Author | Sergio Escalera | ||||
Title | Multi-Modal Human Behaviour Analysis from Visual Data Sources | Type | Journal | ||
Year | 2013 | Publication | ERCIM News journal | Abbreviated Journal | ERCIM |
Volume | 95 | Issue | Pages | 21-22 | |
Keywords | |||||
Abstract ![]() |
The Human Pose Recovery and Behaviour Analysis group (HuPBA), University of Barcelona, is developing a line of research on multi-modal analysis of humans in visual data. The novel technology is being applied in several scenarios with high social impact, including sign language recognition, assisted technology and supported diagnosis for the elderly and people with mental/physical disabilities, fitness conditioning, and Human Computer Interaction. | ||||
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 | 0926-4981 | ISBN | Medium | ||
Area | Expedition | Conference | |||
Notes | HuPBA;MILAB | Approved | no | ||
Call Number | Admin @ si @ Esc2013 | Serial | 2361 | ||
Permanent link to this record | |||||
Author | Arash Akbarinia; Karl R. Gegenfurtner | ||||
Title | Metameric Mismatching in Natural and Artificial Reflectances | Type | Journal Article | ||
Year | 2017 | Publication | Journal of Vision | Abbreviated Journal | JV |
Volume | 17 | Issue | 10 | Pages | 390-390 |
Keywords | Metamer; colour perception; spectral discrimination; photoreceptors | ||||
Abstract ![]() |
The human visual system and most digital cameras sample the continuous spectral power distribution through three classes of receptors. This implies that two distinct spectral reflectances can result in identical tristimulus values under one illuminant and differ under another – the problem of metamer mismatching. It is still debated how frequent this issue arises in the real world, using naturally occurring reflectance functions and common illuminants.
We gathered more than ten thousand spectral reflectance samples from various sources, covering a wide range of environments (e.g., flowers, plants, Munsell chips) and evaluated their responses under a number of natural and artificial source of lights. For each pair of reflectance functions, we estimated the perceived difference using the CIE-defined distance ΔE2000 metric in Lab color space. The degree of metamer mismatching depended on the lower threshold value l when two samples would be considered to lead to equal sensor excitations (ΔE < l), and on the higher threshold value h when they would be considered different. For example, for l=h=1, we found that 43.129 comparisons out of a total of 6×107 pairs would be considered metameric (1 in 104). For l=1 and h=5, this number reduced to 705 metameric pairs (2 in 106). Extreme metamers, for instance l=1 and h=10, were rare (22 pairs or 6 in 108), as were instances where the two members of a metameric pair would be assigned to different color categories. Not unexpectedly, we observed variations among different reflectance databases and illuminant spectra with more frequency under artificial illuminants than natural ones. Overall, our numbers are not very different from those obtained earlier (Foster et al, JOSA A, 2006). However, our results also show that the degree of metamerism is typically not very strong and that category switches hardly ever occur. |
||||
Address | Florida, 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 | |||
Notes | NEUROBIT; no menciona | Approved | no | ||
Call Number | Admin @ si @ AkG2017 | Serial | 2899 | ||
Permanent link to this record | |||||
Author | Monica Piñol | ||||
Title | Reinforcement Learning of Visual Descriptors for Object Recognition | Type | Book Whole | ||
Year | 2014 | Publication | PhD Thesis, Universitat Autonoma de Barcelona-CVC | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract ![]() |
The human visual system is able to recognize the object in an image even if the object is partially occluded, from various points of view, in different colors, or with independence of the distance to the object. To do this, the eye obtains an image and extracts features that are sent to the brain, and then, in the brain the object is recognized. In computer vision, the object recognition branch tries to learns from the human visual system behaviour to achieve its goal. Hence, an algorithm is used to identify representative features of the scene (detection), then another algorithm is used to describe these points (descriptor) and finally the extracted information is used for classifying the object in the scene. The selection of this set of algorithms is a very complicated task and thus, a very active research field. In this thesis we are focused on the selection/learning of the best descriptor for a given image. In the state of the art there are several descriptors but we do not know how to choose the best descriptor because depends on scenes that we will use (dataset) and the algorithm chosen to do the classification. We propose a framework based on reinforcement learning and bag of features to choose the best descriptor according to the given image. The system can analyse the behaviour of different learning algorithms and descriptor sets. Furthermore the proposed framework for improving the classification/recognition ratio can be used with minor changes in other computer vision fields, such as video retrieval. | ||||
Address | |||||
Corporate Author | Thesis | Ph.D. thesis | |||
Publisher | Ediciones Graficas Rey | Place of Publication | Editor | Ricardo Toledo;Angel Sappa | |
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | 978-84-940902-5-7 | Medium | ||
Area | Expedition | Conference | |||
Notes | ADAS; 600.076 | Approved | no | ||
Call Number | Admin @ si @ Piñ2014 | Serial | 2464 | ||
Permanent link to this record | |||||
Author | Xim Cerda-Company; Olivier Penacchio; Xavier Otazu | ||||
Title | Chromatic Induction in Migraine | Type | Journal | ||
Year | 2021 | Publication | VISION | Abbreviated Journal | |
Volume | 5 | Issue | 3 | Pages | 37 |
Keywords | migraine; vision; colour; colour perception; chromatic induction; psychophysics | ||||
Abstract ![]() |
The human visual system is not a colorimeter. The perceived colour of a region does not only depend on its colour spectrum, but also on the colour spectra and geometric arrangement of neighbouring regions, a phenomenon called chromatic induction. Chromatic induction is thought to be driven by lateral interactions: the activity of a central neuron is modified by stimuli outside its classical receptive field through excitatory–inhibitory mechanisms. As there is growing evidence of an excitation/inhibition imbalance in migraine, we compared chromatic induction in migraine and control groups. As hypothesised, we found a difference in the strength of induction between the two groups, with stronger induction effects in migraine. On the other hand, given the increased prevalence of visual phenomena in migraine with aura, we also hypothesised that the difference between migraine and control would be more important in migraine with aura than in migraine without aura. Our experiments did not support this hypothesis. Taken together, our results suggest a link between excitation/inhibition imbalance and increased induction effects. | ||||
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 | NEUROBIT; no proj | Approved | no | ||
Call Number | Admin @ si @ CPO2021 | Serial | 3589 | ||
Permanent link to this record | |||||
Author | Zheng Huang; Kai Chen; Jianhua He; Xiang Bai; Dimosthenis Karatzas; Shijian Lu; CV Jawahar | ||||
Title | ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction | Type | Conference Article | ||
Year | 2019 | Publication | 15th International Conference on Document Analysis and Recognition | Abbreviated Journal | |
Volume | Issue | Pages | 1516-1520 | ||
Keywords | |||||
Abstract ![]() |
The ICDAR 2019 Challenge on “Scanned receipts OCR and key information extraction” (SROIE) covers important aspects related to the automated analysis of scanned receipts. The SROIE tasks play a key role in many document analysis systems and hold significant commercial potential. Although a lot of work has been published over the years on administrative document analysis, the community has advanced relatively slowly, as most datasets have been kept private. One of the key contributions of SROIE to the document analysis community is to offer a first, standardized dataset of 1000 whole scanned receipt images and annotations, as well as an evaluation procedure for such tasks. The Challenge is structured around three tasks, namely Scanned Receipt Text Localization (Task 1), Scanned Receipt OCR (Task 2) and Key Information Extraction from Scanned Receipts (Task 3). The competition opened on 10th February, 2019 and closed on 5th May, 2019. We received 29, 24 and 18 valid submissions received for the three competition tasks, respectively. This report presents the competition datasets, define the tasks and the evaluation protocols, offer detailed submission statistics, as well as an analysis of the submitted performance. While the tasks of text localization and recognition seem to be relatively easy to tackle, it is interesting to observe the variety of ideas and approaches proposed for the information extraction task. According to the submissions' performance we believe there is still margin for improving information extraction performance, although the current dataset would have to grow substantially in following editions. Given the success of the SROIE competition evidenced by the wide interest generated and the healthy number of submissions from academic, research institutes and industry over different countries, we consider that the SROIE competition can evolve into a useful resource for the community, drawing further attention and promoting research and development efforts in this field. | ||||
Address | Sydney; Australia; September 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 | ICDAR | ||
Notes | DAG; 600.129 | Approved | no | ||
Call Number | Admin @ si @ HCH2019 | Serial | 3338 | ||
Permanent link to this record | |||||
Author | Dimosthenis Karatzas; Lluis Gomez; Marçal Rusiñol; Anguelos Nicolaou | ||||
Title | The Robust Reading Competition Annotation and Evaluation Platform | Type | Conference Article | ||
Year | 2018 | Publication | 13th IAPR International Workshop on Document Analysis Systems | Abbreviated Journal | |
Volume | Issue | Pages | 61-66 | ||
Keywords | |||||
Abstract ![]() |
The ICDAR Robust Reading Competition (RRC), initiated in 2003 and reestablished in 2011, has become the defacto evaluation standard for the international community. Concurrent with its second incarnation in 2011, a continuous
effort started to develop an online framework to facilitate the hosting and management of competitions. This short paper briefly outlines the Robust Reading Competition Annotation and Evaluation Platform, the backbone of the Robust Reading Competition, comprising a collection of tools and processes that aim to simplify the management and annotation of data, and to provide online and offline performance evaluation and analysis services. |
||||
Address | Viena; Austria; April 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 | DAS | ||
Notes | DAG; 600.084; 600.121 | Approved | no | ||
Call Number | KGR2018 | Serial | 3103 | ||
Permanent link to this record | |||||
Author | Xavier Soria | ||||
Title | Single sensor multi-spectral imaging | Type | Book Whole | ||
Year | 2019 | Publication | PhD Thesis, Universitat Autonoma de Barcelona-CVC | Abbreviated Journal | |
Volume | Issue | Pages | |||
Keywords | |||||
Abstract ![]() |
The image sensor, nowadays, is rolling the smartphone industry. While some phone brands explore equipping more image sensors, others, like Google, maintain their smartphones with just one sensor; but this sensor is equipped with Deep Learning to enhance the image quality. However, what all brands agree on is the need to research new image sensors; for instance, in 2015 Omnivision and PixelTeq presented new CMOS based image sensors defined as multispectral Single Sensor Camera (SSC), which are capable of capturing multispectral bands. This dissertation presents the benefits of using a multispectral SSCs that, as aforementioned, simultaneously acquires images in the visible and near-infrared (NIR) bands. The principal benefits while addressing problems related to image bands in the spectral range of 400 to 1100 nanometers, there are cost reductions in the hardware and software setup because only one SSC is needed instead of two, and the images alignment are not required any more. Concerning to the NIR spectrum, many works in literature have proven the benefits of working with NIR to enhance RGB images (e.g., image enhancement, remove shadows, dehazing, etc.). In spite of the advantage of using SSC (e.g., low latency), there are some drawback to be solved. One of this drawback corresponds to the nature of the silicon-based sensor, which in addition to capture the RGB image, when the infrared cut off filter is not installed it also acquires NIR information into the visible image. This phenomenon is called RGB and NIR crosstalking. This thesis firstly faces this problem in challenging images and then it shows the benefit of using multispectral images in the edge detection task.
The RGB color restoration from RGBN image is the topic tackled in RGB and NIR crosstalking. Even though in the literature a set of processes have been proposed to face this issue, in this thesis novel approaches, based on DL, are proposed to subtract the additional NIR included in the RGB channel. More precisely, an Artificial Neural Network (NN) and two Convolutional Neural Network (CNN) models are proposed. As the DL based models need a dataset with a large collection of image pairs, a large dataset is collected to address the color restoration. The collected images are from challenging scenes where the sunlight radiation is sufficient to give absorption/reflectance properties to the considered scenes. An extensive evaluation has been conducted on the CNN models, differences from most of the restored images are almost imperceptible to the human eye. The next proposal of the thesis is the validation of the usage of SSC images in the edge detection task. Three methods based on CNN have been proposed. While the first one is based on the most used model, holistically-nested edge detection (HED) termed as multispectral HED (MS-HED), the other two have been proposed observing the drawbacks of MS-HED. These two novel architectures have been designed from scratch (training from scratch); after the first architecture is validated in the visible domain a slight redesign is proposed to tackle the multispectral domain. Again, another dataset is collected to face this problem with SSCs. Even though edge detection is confronted in the multispectral domain, its qualitative and quantitative evaluation demonstrates the generalization in other datasets used for edge detection, improving state-of-the-art results. |
||||
Address | September 2019 | ||||
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 | 978-84-948531-9-7 | Medium | ||
Area | Expedition | Conference | |||
Notes | MSIAU; 600.122 | Approved | no | ||
Call Number | Admin @ si @ Sor2019 | Serial | 3391 | ||
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 | |||||
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 | A.Kesidis; Dimosthenis Karatzas | ||||
Title | Logo and Trademark Recognition | Type | Book Chapter | ||
Year | 2014 | Publication | Handbook of Document Image Processing and Recognition | Abbreviated Journal | |
Volume | D | Issue | Pages | 591-646 | |
Keywords | Logo recognition; Logo removal; Logo spotting; Trademark registration; Trademark retrieval systems | ||||
Abstract ![]() |
The importance of logos and trademarks in nowadays society is indisputable, variably seen under a positive light as a valuable service for consumers or a negative one as a catalyst of ever-increasing consumerism. This chapter discusses the technical approaches for enabling machines to work with logos, looking into the latest methodologies for logo detection, localization, representation, recognition, retrieval, and spotting in a variety of media. This analysis is presented in the context of three different applications covering the complete depth and breadth of state of the art techniques. These are trademark retrieval systems, logo recognition in document images, and logo detection and removal in images and videos. This chapter, due to the very nature of logos and trademarks, brings together various facets of document image analysis spanning graphical and textual content, while it links document image analysis to other computer vision domains, especially when it comes to the analysis of real-scene videos and images. | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Springer London | Place of Publication | Editor | D. Doermann; K. Tombre | |
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | 978-0-85729-858-4 | Medium | ||
Area | Expedition | Conference | |||
Notes | DAG; 600.077 | Approved | no | ||
Call Number | Admin @ si @ KeK2014 | Serial | 2425 | ||
Permanent link to this record | |||||
Author | Ivet Rafegas; Maria Vanrell; Luis A Alexandre; G. Arias | ||||
Title | Understanding trained CNNs by indexing neuron selectivity | Type | Journal Article | ||
Year | 2020 | Publication | Pattern Recognition Letters | Abbreviated Journal | PRL |
Volume | 136 | Issue | Pages | 318-325 | |
Keywords | |||||
Abstract ![]() |
The impressive performance of Convolutional Neural Networks (CNNs) when solving different vision problems is shadowed by their black-box nature and our consequent lack of understanding of the representations they build and how these representations are organized. To help understanding these issues, we propose to describe the activity of individual neurons by their Neuron Feature visualization and quantify their inherent selectivity with two specific properties. We explore selectivity indexes for: an image feature (color); and an image label (class membership). Our contribution is a framework to seek or classify neurons by indexing on these selectivity properties. It helps to find color selective neurons, such as a red-mushroom neuron in layer Conv4 or class selective neurons such as dog-face neurons in layer Conv5 in VGG-M, and establishes a methodology to derive other selectivity properties. Indexing on neuron selectivity can statistically draw how features and classes are represented through layers in a moment when the size of trained nets is growing and automatic tools to index neurons can be helpful. | ||||
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; 600.140; 600.118 | Approved | no | ||
Call Number | Admin @ si @ RVL2019 | Serial | 3310 | ||
Permanent link to this record | |||||
Author | Eduardo Aguilar; Beatriz Remeseiro; Marc Bolaños; Petia Radeva | ||||
Title | Grab, Pay, and Eat: Semantic Food Detection for Smart Restaurants | Type | Journal Article | ||
Year | 2018 | Publication | IEEE Transactions on Multimedia | Abbreviated Journal | |
Volume | 20 | Issue | 12 | Pages | 3266 - 3275 |
Keywords | |||||
Abstract ![]() |
The increase in awareness of people towards their nutritional habits has drawn considerable attention to the field of automatic food analysis. Focusing on self-service restaurants environment, automatic food analysis is not only useful for extracting nutritional information from foods selected by customers, it is also of high interest to speed up the service solving the bottleneck produced at the cashiers in times of high demand. In this paper, we address the problem of automatic food tray analysis in canteens and restaurants environment, which consists in predicting multiple foods placed on a tray image. We propose a new approach for food analysis based on convolutional neural networks, we name Semantic Food Detection, which integrates in the same framework food localization, recognition and segmentation. We demonstrate that our method improves the state of the art food detection by a considerable margin on the public dataset UNIMIB2016 achieving about 90% in terms of F-measure, and thus provides a significant technological advance towards the automatic billing in restaurant environments. | ||||
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 proj | Approved | no | ||
Call Number | Admin @ si @ ARB2018 | Serial | 3236 | ||
Permanent link to this record |