Home | [151–160] << 161 162 163 164 165 166 167 168 169 170 >> [171–180] |
![]() |
Records | |||||
---|---|---|---|---|---|
Author | Pau Rodriguez; Josep M. Gonfaus; Guillem Cucurull; Xavier Roca; Jordi Gonzalez | ||||
Title | Attend and Rectify: A Gated Attention Mechanism for Fine-Grained Recovery | Type | Conference Article | ||
Year | 2018 | Publication | 15th European Conference on Computer Vision | Abbreviated Journal | |
Volume | 11212 | Issue | Pages ![]() |
357-372 | |
Keywords | Deep Learning; Convolutional Neural Networks; Attention | ||||
Abstract | We propose a novel attention mechanism to enhance Convolutional Neural Networks for fine-grained recognition. It learns to attend to lower-level feature activations without requiring part annotations and uses these activations to update and rectify the output likelihood distribution. In contrast to other approaches, the proposed mechanism is modular, architecture-independent and efficient both in terms of parameters and computation required. Experiments show that networks augmented with our approach systematically improve their classification accuracy and become more robust to clutter. As a result, Wide Residual Networks augmented with our proposal surpasses the state of the art classification accuracies in CIFAR-10, the Adience gender recognition task, Stanford dogs, and UEC Food-100. | ||||
Address | Munich; 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 | ECCV | ||
Notes | ISE; 600.098; 602.121; 600.119 | Approved | no | ||
Call Number | Admin @ si @ RGC2018 | Serial | 3139 | ||
Permanent link to this record | |||||
Author | Sergi Garcia Bordils; Andres Mafla; Ali Furkan Biten; Oren Nuriel; Aviad Aberdam; Shai Mazor; Ron Litman; Dimosthenis Karatzas | ||||
Title | Out-of-Vocabulary Challenge Report | Type | Conference Article | ||
Year | 2022 | Publication | Proceedings European Conference on Computer Vision Workshops | Abbreviated Journal | |
Volume | 13804 | Issue | Pages ![]() |
359–375 | |
Keywords | |||||
Abstract | This paper presents final results of the Out-Of-Vocabulary 2022 (OOV) challenge. The OOV contest introduces an important aspect that is not commonly studied by Optical Character Recognition (OCR) models, namely, the recognition of unseen scene text instances at training time. The competition compiles a collection of public scene text datasets comprising of 326,385 images with 4,864,405 scene text instances, thus covering a wide range of data distributions. A new and independent validation and test set is formed with scene text instances that are out of vocabulary at training time. The competition was structured in two tasks, end-to-end and cropped scene text recognition respectively. A thorough analysis of results from baselines and different participants is presented. Interestingly, current state-of-the-art models show a significant performance gap under the newly studied setting. We conclude that the OOV dataset proposed in this challenge will be an essential area to be explored in order to develop scene text models that achieve more robust and generalized predictions. | ||||
Address | Tel-Aviv; Israel; October 2022 | ||||
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; 600.155; 302.105; 611.002 | Approved | no | ||
Call Number | Admin @ si @ GMB2022 | Serial | 3771 | ||
Permanent link to this record | |||||
Author | Eduardo Aguilar; Marc Bolaños; Petia Radeva | ||||
Title | Regularized uncertainty-based multi-task learning model for food analysis | Type | Journal Article | ||
Year | 2019 | Publication | Journal of Visual Communication and Image Representation | Abbreviated Journal | JVCIR |
Volume | 60 | Issue | Pages ![]() |
360-370 | |
Keywords | Multi-task models; Uncertainty modeling; Convolutional neural networks; Food image analysis; Food recognition; Food group recognition; Ingredients recognition; Cuisine recognition | ||||
Abstract | Food plays an important role in several aspects of our daily life. Several computer vision approaches have been proposed for tackling food analysis problems, but very little effort has been done in developing methodologies that could take profit of the existent correlation between tasks. In this paper, we propose a new multi-task model that is able to simultaneously predict different food-related tasks, e.g. dish, cuisine and food categories. Here, we extend the homoscedastic uncertainty modeling to allow single-label and multi-label classification and propose a regularization term, which jointly weighs the tasks as well as their correlations. Furthermore, we propose a new Multi-Attribute Food dataset and a new metric, Multi-Task Accuracy. We prove that using both our uncertainty-based loss and the class regularization term, we are able to improve the coherence of outputs between different tasks. Moreover, we outperform the use of task-specific models on classical measures like accuracy or . | ||||
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 @ ABR2019 | Serial | 3298 | ||
Permanent link to this record | |||||
Author | Alberto Hidalgo; Ferran Poveda; Enric Marti;Debora Gil;Albert Andaluz; Francesc Carreras; Manuel Ballester | ||||
Title | Evidence of continuous helical structure of the cardiac ventricular anatomy assessed by diffusion tensor imaging magnetic resonance multiresolution tractography | Type | Journal Article | ||
Year | 2012 | Publication | European Radiology | Abbreviated Journal | ECR |
Volume | 3 | Issue | 1 | Pages ![]() |
361-362 |
Keywords | |||||
Abstract | Deep understanding of myocardial structure linking morphology and func- tion of the heart would unravel crucial knowledge for medical and surgical clinical procedures and studies. Diffusion tensor MRI provides a discrete measurement of the 3D arrangement of myocardial fibres by the observation of local anisotropic
diffusion of water molecules in biological tissues. In this work, we present a multi- scale visualisation technique based on DT-MRI streamlining capable of uncovering additional properties of the architectural organisation of the heart. Methods and Materials: We selected the John Hopkins University (JHU) Canine Heart Dataset, where the long axis cardiac plane is aligned with the scanner’s Z- axis. Their equipment included a 4-element passed array coil emitting a 1.5 T. For DTI acquisition, a 3D-FSE sequence is apply. We used 200 seeds for full-scale tractography, while we applied a MIP mapping technique for simplified tractographic reconstruction. In this case, we reduced each DTI 3D volume dimensions by order- two magnitude before streamlining. Our simplified tractographic reconstruction method keeps the main geometric features of fibres, allowing for an easier identification of their global morphological disposition, including the ventricular basal ring. Moreover, we noticed a clearly visible helical disposition of the myocardial fibres, in line with the helical myocardial band ventricular structure described by Torrent-Guasp. Finally, our simplified visualisation with single tracts identifies the main segments of the helical ventricular architecture. DT-MRI makes possible the identification of a continuous helical architecture of the myocardial fibres, which validates Torrent-Guasp’s helical myocardial band ventricular anatomical model. |
||||
Address | Viena, Austria | ||||
Corporate Author | Thesis | ||||
Publisher | Springer Link | Place of Publication | Editor | ||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | 1869-4101 | ISBN | Medium | ||
Area | Expedition | Conference | |||
Notes | IAM | Approved | no | ||
Call Number | IAM @ iam @ HPM2012 | Serial | 1858 | ||
Permanent link to this record | |||||
Author | Lu Yu; Lichao Zhang; Joost Van de Weijer; Fahad Shahbaz Khan; Yongmei Cheng; C. Alejandro Parraga | ||||
Title | Beyond Eleven Color Names for Image Understanding | Type | Journal Article | ||
Year | 2018 | Publication | Machine Vision and Applications | Abbreviated Journal | MVAP |
Volume | 29 | Issue | 2 | Pages ![]() |
361-373 |
Keywords | Color name; Discriminative descriptors; Image classification; Re-identification; Tracking | ||||
Abstract | Color description is one of the fundamental problems of image understanding. One of the popular ways to represent colors is by means of color names. Most existing work on color names focuses on only the eleven basic color terms of the English language. This could be limiting the discriminative power of these representations, and representations based on more color names are expected to perform better. However, there exists no clear strategy to choose additional color names. We collect a dataset of 28 additional color names. To ensure that the resulting color representation has high discriminative power we propose a method to order the additional color names according to their complementary nature with the basic color names. This allows us to compute color name representations with high discriminative power of arbitrary length. In the experiments we show that these new color name descriptors outperform the existing color name descriptor on the task of visual tracking, person re-identification and image classification. | ||||
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; NEUROBIT; 600.068; 600.109; 600.120 | Approved | no | ||
Call Number | Admin @ si @ YYW2018 | Serial | 3087 | ||
Permanent link to this record | |||||
Author | Sounak Dey; Anguelos Nicolaou; Josep Llados; Umapada Pal | ||||
Title | Evaluation of the Effect of Improper Segmentation on Word Spotting | Type | Journal Article | ||
Year | 2019 | Publication | International Journal on Document Analysis and Recognition | Abbreviated Journal | IJDAR |
Volume | 22 | Issue | Pages ![]() |
361-374 | |
Keywords | |||||
Abstract | Word spotting is an important recognition task in large-scale retrieval of document collections. In most of the cases, methods are developed and evaluated assuming perfect word segmentation. In this paper, we propose an experimental framework to quantify the goodness that word segmentation has on the performance achieved by word spotting methods in identical unbiased conditions. The framework consists of generating systematic distortions on segmentation and retrieving the original queries from the distorted dataset. We have tested our framework on several established and state-of-the-art methods using George Washington and Barcelona Marriage Datasets. The experiments done allow for an estimate of the end-to-end performance of word spotting methods. | ||||
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; 600.097; 600.084; 600.121; 600.140; 600.129 | Approved | no | ||
Call Number | Admin @ si @ DNL2019 | Serial | 3455 | ||
Permanent link to this record | |||||
Author | Josep Llados; Gemma Sanchez | ||||
Title | Indexing Historical Documents by Word Shape Signatures | Type | Conference Article | ||
Year | 2007 | Publication | 9th International Conference on Document Analysis and Recognition | Abbreviated Journal | |
Volume | 1 | Issue | Pages ![]() |
362–366 | |
Keywords | |||||
Abstract | |||||
Address | Curitiba (Brasil) | ||||
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 | Approved | no | ||
Call Number | DAG @ dag @ LlS2007 | Serial | 882 | ||
Permanent link to this record | |||||
Author | Frederic Sampedro; Anna Domenech; Sergio Escalera | ||||
Title | Obtaining quantitative global tumoral state indicators based on whole-body PET/CT scans: A breast cancer case study | Type | Journal Article | ||
Year | 2014 | Publication | Nuclear Medicine Communications | Abbreviated Journal | NMC |
Volume | 35 | Issue | 4 | Pages ![]() |
362-371 |
Keywords | |||||
Abstract | Objectives: In this work we address the need for the computation of quantitative global tumoral state indicators from oncological whole-body PET/computed tomography scans. The combination of such indicators with other oncological information such as tumor markers or biopsy results would prove useful in oncological decision-making scenarios.
Materials and methods: From an ordering of 100 breast cancer patients on the basis of oncological state through visual analysis by a consensus of nuclear medicine specialists, a set of numerical indicators computed from image analysis of the PET/computed tomography scan is presented, which attempts to summarize a patient’s oncological state in a quantitative manner taking into consideration the total tumor volume, aggressiveness, and spread. Results: Results obtained by comparative analysis of the proposed indicators with respect to the experts’ evaluation show up to 87% Pearson’s correlation coefficient when providing expert-guided PET metabolic tumor volume segmentation and 64% correlation when using completely automatic image analysis techniques. Conclusion: Global quantitative tumor information obtained by whole-body PET/CT image analysis can prove useful in clinical nuclear medicine settings and oncological decision-making scenarios. The completely automatic computation of such indicators would improve its impact as time efficiency and specialist independence would be achieved. |
||||
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 | HuPBA;MILAB | Approved | no | ||
Call Number | SDE2014a | Serial | 2444 | ||
Permanent link to this record | |||||
Author | Muhammad Anwer Rao; David Vazquez; Antonio Lopez | ||||
Title | Opponent Colors for Human Detection | Type | Conference Article | ||
Year | 2011 | Publication | 5th Iberian Conference on Pattern Recognition and Image Analysis | Abbreviated Journal | |
Volume | 6669 | Issue | Pages ![]() |
363-370 | |
Keywords | Pedestrian Detection; Color; Part Based Models | ||||
Abstract | Human detection is a key component in fields such as advanced driving assistance and video surveillance. However, even detecting non-occluded standing humans remains a challenge of intensive research. Finding good features to build human models for further detection is probably one of the most important issues to face. Currently, shape, texture and motion features have deserve extensive attention in the literature. However, color-based features, which are important in other domains (e.g., image categorization), have received much less attention. In fact, the use of RGB color space has become a kind of choice by default. The focus has been put in developing first and second order features on top of RGB space (e.g., HOG and co-occurrence matrices, resp.). In this paper we evaluate the opponent colors (OPP) space as a biologically inspired alternative for human detection. In particular, by feeding OPP space in the baseline framework of Dalal et al. for human detection (based on RGB, HOG and linear SVM), we will obtain better detection performance than by using RGB space. This is a relevant result since, up to the best of our knowledge, OPP space has not been previously used for human detection. This suggests that in the future it could be worth to compute co-occurrence matrices, self-similarity features, etc., also on top of OPP space, i.e., as we have done with HOG in this paper. | ||||
Address | Las Palmas de Gran Canaria. Spain | ||||
Corporate Author | Thesis | ||||
Publisher | Springer | Place of Publication | Berlin Heidelberg | Editor | J. Vitria; J.M. Sanches; M. Hernandez |
Language | English | Summary Language | English | Original Title | Opponent Colors for Human Detection |
Series Editor | Series Title | Lecture Notes on Computer Science | Abbreviated Series Title | LNCS | |
Series Volume | Series Issue | Edition | |||
ISSN | 0302-9743 | ISBN | 978-3-642-21256-7 | Medium | |
Area | Expedition | Conference | IbPRIA | ||
Notes | ADAS | Approved | no | ||
Call Number | ADAS @ adas @ RVL2011a | Serial | 1666 | ||
Permanent link to this record | |||||
Author | I. Sorodoc; S. Pezzelle; A. Herbelot; Mariella Dimiccoli; R. Bernardi | ||||
Title | Learning quantification from images: A structured neural architecture | Type | Journal Article | ||
Year | 2018 | Publication | Natural Language Engineering | Abbreviated Journal | NLE |
Volume | 24 | Issue | 3 | Pages ![]() |
363-392 |
Keywords | |||||
Abstract | Major advances have recently been made in merging language and vision representations. Most tasks considered so far have confined themselves to the processing of objects and lexicalised relations amongst objects (content words). We know, however, that humans (even pre-school children) can abstract over raw multimodal data to perform certain types of higher level reasoning, expressed in natural language by function words. A case in point is given by their ability to learn quantifiers, i.e. expressions like few, some and all. From formal semantics and cognitive linguistics, we know that quantifiers are relations over sets which, as a simplification, we can see as proportions. For instance, in most fish are red, most encodes the proportion of fish which are red fish. In this paper, we study how well current neural network strategies model such relations. We propose a task where, given an image and a query expressed by an object–property pair, the system must return a quantifier expressing which proportions of the queried object have the queried property. Our contributions are twofold. First, we show that the best performance on this task involves coupling state-of-the-art attention mechanisms with a network architecture mirroring the logical structure assigned to quantifiers by classic linguistic formalisation. Second, we introduce a new balanced dataset of image scenarios associated with quantification queries, which we hope will foster further research in this area. | ||||
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 @ SPH2018 | Serial | 3021 | ||
Permanent link to this record | |||||
Author | David Geronimo; Joan Serrat; Antonio Lopez; Ramon Baldrich | ||||
Title | Traffic sign recognition for computer vision project-based learning | Type | Journal Article | ||
Year | 2013 | Publication | IEEE Transactions on Education | Abbreviated Journal | T-EDUC |
Volume | 56 | Issue | 3 | Pages ![]() |
364-371 |
Keywords | traffic signs | ||||
Abstract | This paper presents a graduate course project on computer vision. The aim of the project is to detect and recognize traffic signs in video sequences recorded by an on-board vehicle camera. This is a demanding problem, given that traffic sign recognition is one of the most challenging problems for driving assistance systems. Equally, it is motivating for the students given that it is a real-life problem. Furthermore, it gives them the opportunity to appreciate the difficulty of real-world vision problems and to assess the extent to which this problem can be solved by modern computer vision and pattern classification techniques taught in the classroom. The learning objectives of the course are introduced, as are the constraints imposed on its design, such as the diversity of students' background and the amount of time they and their instructors dedicate to the course. The paper also describes the course contents, schedule, and how the project-based learning approach is applied. The outcomes of the course are discussed, including both the students' marks and their personal feedback. | ||||
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 | 0018-9359 | ISBN | Medium | ||
Area | Expedition | Conference | |||
Notes | ADAS; CIC | Approved | no | ||
Call Number | Admin @ si @ GSL2013; ADAS @ adas @ | Serial | 2160 | ||
Permanent link to this record | |||||
Author | Juan Ignacio Toledo; Alicia Fornes; Jordi Cucurull; Josep Llados | ||||
Title | Election Tally Sheets Processing System | Type | Conference Article | ||
Year | 2016 | Publication | 12th IAPR Workshop on Document Analysis Systems | Abbreviated Journal | |
Volume | Issue | Pages ![]() |
364-368 | ||
Keywords | |||||
Abstract | In paper based elections, manual tallies at polling station level produce myriads of documents. These documents share a common form-like structure and a reduced vocabulary worldwide. On the other hand, each tally sheet is filled by a different writer and on different countries, different scripts are used. We present a complete document analysis system for electoral tally sheet processing combining state of the art techniques with a new handwriting recognition subprocess based on unsupervised feature discovery with Variational Autoencoders and sequence classification with BLSTM neural networks. The whole system is designed to be script independent and allows a fast and reliable results consolidation process with reduced operational cost. | ||||
Address | Santorini; Greece; April 2016 | ||||
Corporate Author | Thesis | ||||
Publisher | Place of Publication | Editor | |||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | DAS | ||
Notes | DAG; 602.006; 600.061; 601.225; 600.077; 600.097 | Approved | no | ||
Call Number | TFC2016 | Serial | 2752 | ||
Permanent link to this record | |||||
Author | Ferran Diego; G.D. Evangelidis; Joan Serrat | ||||
Title | Night-time outdoor surveillance by mobile cameras | Type | Conference Article | ||
Year | 2012 | Publication | 1st International Conference on Pattern Recognition Applications and Methods | Abbreviated Journal | |
Volume | 2 | Issue | Pages ![]() |
365-371 | |
Keywords | |||||
Abstract | This paper addresses the problem of video surveillance by mobile cameras. We present a method that allows online change detection in night-time outdoor surveillance. Because of the camera movement, background frames are not available and must be “localized” in former sequences and registered with the current frames. To this end, we propose a Frame Localization And Registration (FLAR) approach that solves the problem efficiently. Frames of former sequences define a database which is queried by current frames in turn. To quickly retrieve nearest neighbors, database is indexed through a visual dictionary method based on the SURF descriptor. Furthermore, the frame localization is benefited by a temporal filter that exploits the temporal coherence of videos. Next, the recently proposed ECC alignment scheme is used to spatially register the synchronized frames. Finally, change detection methods apply to aligned frames in order to mark suspicious areas. Experiments with real night sequences recorded by in-vehicle cameras demonstrate the performance of the proposed method and verify its efficiency and effectiveness against other methods. | ||||
Address | Algarve, Portugal | ||||
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 | ICPRAM | ||
Notes | ADAS | Approved | no | ||
Call Number | Admin @ si @ DES2012 | Serial | 2035 | ||
Permanent link to this record | |||||
Author | David Roche; Debora Gil; Jesus Giraldo | ||||
Title | Multiple active receptor conformation, agonist efficacy and maximum effect of the system: the conformation-based operational model of agonism, | Type | Journal Article | ||
Year | 2013 | Publication | Drug Discovery Today | Abbreviated Journal | DDT |
Volume | 18 | Issue | 7-8 | Pages ![]() |
365-371 |
Keywords | |||||
Abstract | The operational model of agonism assumes that the maximum effect a particular receptor system can achieve (the Em parameter) is fixed. Em estimates are above but close to the asymptotic maximum effects of endogenous agonists. The concept of Em is contradicted by superagonists and those positive allosteric modulators that significantly increase the maximum effect of endogenous agonists. An extension of the operational model is proposed that assumes that the Em parameter does not necessarily have a single value for a receptor system but has multiple values associated to multiple active receptor conformations. The model provides a mechanistic link between active receptor conformation and agonist efficacy, which can be useful for the analysis of agonist response under different receptor scenarios. | ||||
Address | |||||
Corporate Author | Thesis | ||||
Publisher | Elsevier | Place of Publication | Editor | ||
Language | Summary Language | Original Title | |||
Series Editor | Series Title | Abbreviated Series Title | |||
Series Volume | Series Issue | Edition | |||
ISSN | ISBN | Medium | |||
Area | Expedition | Conference | |||
Notes | IAM; 600.057; 600.054 | Approved | no | ||
Call Number | IAM @ iam @ RGG2013a | Serial | 2190 | ||
Permanent link to this record | |||||
Author | Md. Mostafa Kamal Sarker; Mohammed Jabreel; Hatem A. Rashwan; Syeda Furruka Banu; Petia Radeva; Domenec Puig | ||||
Title | CuisineNet: Food Attributes Classification using Multi-scale Convolution Network | Type | Conference Article | ||
Year | 2018 | Publication | 21st International Conference of the Catalan Association for Artificial Intelligence | Abbreviated Journal | |
Volume | Issue | Pages ![]() |
365-372 | ||
Keywords | |||||
Abstract | Diversity of food and its attributes represents the culinary habits of peoples from different countries. Thus, this paper addresses the problem of identifying food culture of people around the world and its flavor by classifying two main food attributes, cuisine and flavor. A deep learning model based on multi-scale convotuional networks is proposed for extracting more accurate features from input images. The aggregation of multi-scale convolution layers with different kernel size is also used for weighting the features results from different scales. In addition, a joint loss function based on Negative Log Likelihood (NLL) is used to fit the model probability to multi labeled classes for multi-modal classification task. Furthermore, this work provides a new dataset for food attributes, so-called Yummly48K, extracted from the popular food website, Yummly. Our model is assessed on the constructed Yummly48K dataset. The experimental results show that our proposed method yields 65% and 62% average F1 score on validation and test set which outperforming the state-of-the-art models. | ||||
Address | Roses; catalonia; 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 | CCIA | ||
Notes | MILAB; no menciona | Approved | no | ||
Call Number | Admin @ si @ SJR2018 | Serial | 3113 | ||
Permanent link to this record |