| 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 |
Yaxing Wang; Chenshen Wu; Luis Herranz; Joost Van de Weijer; Abel Gonzalez-Garcia; Bogdan Raducanu |
| Title |
Transferring GANs: generating images from limited data |
Type |
Conference Article |
| Year |
2018 |
Publication |
15th European Conference on Computer Vision |
Abbreviated Journal |
|
| Volume |
11210 |
Issue |
|
Pages |
220-236 |
| Keywords |
Generative adversarial networks; Transfer learning; Domain adaptation; Image generation |
| Abstract |
ransferring knowledge of pre-trained networks to new domains by means of fine-tuning is a widely used practice for applications based on discriminative models. To the best of our knowledge this practice has not been studied within the context of generative deep networks. Therefore, we study domain adaptation applied to image generation with generative adversarial networks. We evaluate several aspects of domain adaptation, including the impact of target domain size, the relative distance between source and target domain, and the initialization of conditional GANs. Our results show that using knowledge from pre-trained networks can shorten the convergence time and can significantly improve the quality of the generated images, especially when target data is limited. We show that these conclusions can also be drawn for conditional GANs even when the pre-trained model was trained without conditioning. Our results also suggest that density is more important than diversity and a dataset with one or few densely sampled classes is a better source model than more diverse datasets such as ImageNet or Places. |
| 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 |
LAMP; 600.109; 600.106; 600.120 |
Approved |
no |
| Call Number |
Admin @ si @ WWH2018a |
Serial |
3130 |
| Permanent link to this record |
| |
|
| |
| Author |
Boris N. Oreshkin; Pau Rodriguez; Alexandre Lacoste |
| Title |
TADAM: Task dependent adaptive metric for improved few-shot learning |
Type |
Conference Article |
| Year |
2018 |
Publication |
32nd Annual Conference on Neural Information Processing Systems |
Abbreviated Journal |
|
| Volume |
|
Issue |
|
Pages |
|
| Keywords |
|
| Abstract |
Few-shot learning has become essential for producing models that generalize from few examples. In this work, we identify that metric scaling and metric task conditioning are important to improve the performance of few-shot algorithms. Our analysis reveals that simple metric scaling completely changes the nature of few-shot algorithm parameter updates. Metric scaling provides improvements up to 14% in accuracy for certain metrics on the mini-Imagenet 5-way 5-shot classification task. We further propose a simple and effective way of conditioning a learner on the task sample set, resulting in learning a task-dependent metric space. Moreover, we propose and empirically test a practical end-to-end optimization procedure based on auxiliary task co-training to learn a task-dependent metric space. The resulting few-shot learning model based on the task-dependent scaled metric achieves state of the art on mini-Imagenet. We confirm these results on another few-shot dataset that we introduce in this paper based on CIFAR100. |
| Address |
Montreal; Canada; December 2018 |
| Corporate Author |
|
Thesis |
|
| Publisher |
|
Place of Publication |
|
Editor |
|
| Language |
|
Summary Language |
|
Original Title |
|
| Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
| Series Volume |
|
Series Issue |
|
Edition |
|
| ISSN |
|
ISBN |
|
Medium |
|
| Area |
|
Expedition |
|
Conference |
NIPS |
| Notes |
ISE; 600.098; 600.119 |
Approved |
no |
| Call Number |
Admin @ si @ ORL2018 |
Serial |
3140 |
| Permanent link to this record |
| |
|
| |
| Author |
Hugo Jair Escalante; Heysem Kaya; Albert Ali Salah; Sergio Escalera; Yagmur Gucluturk; Umut Guclu; Xavier Baro; Isabelle Guyon; Julio C. S. Jacques Junior; Meysam Madadi; Stephane Ayache; Evelyne Viegas; Furkan Gurpinar; Achmadnoer Sukma Wicaksana; Cynthia C. S. Liem; Marcel A. J. van Gerven; Rob van Lier |
| Title |
Explaining First Impressions: Modeling, Recognizing, and Explaining Apparent Personality from Videos |
Type |
Miscellaneous |
| Year |
2018 |
Publication |
Arxiv |
Abbreviated Journal |
|
| Volume |
|
Issue |
|
Pages |
|
| Keywords |
|
| Abstract |
Explainability and interpretability are two critical aspects of decision support systems. Within computer vision, they are critical in certain tasks related to human behavior analysis such as in health care applications. Despite their importance, it is only recently that researchers are starting to explore these aspects. This paper provides an introduction to explainability and interpretability in the context of computer vision with an emphasis on looking at people tasks. Specifically, we review and study those mechanisms in the context of first impressions analysis. To the best of our knowledge, this is the first effort in this direction. Additionally, we describe a challenge we organized on explainability in first impressions analysis from video. We analyze in detail the newly introduced data set, the evaluation protocol, and summarize the results of the challenge. Finally, derived from our study, we outline research opportunities that we foresee will be decisive in the near future for the development of the explainable computer vision field. |
| 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 |
Approved |
no |
| Call Number |
Admin @ si @ JKS2018 |
Serial |
3095 |
| Permanent link to this record |
| |
|
| |
| Author |
Sounak Dey; Anjan Dutta; Juan Ignacio Toledo; Suman Ghosh; Josep Llados; Umapada Pal |
| Title |
SigNet: Convolutional Siamese Network for Writer Independent Offline Signature Verification |
Type |
Miscellaneous |
| Year |
2018 |
Publication |
Arxiv |
Abbreviated Journal |
|
| Volume |
|
Issue |
|
Pages |
|
| Keywords |
|
| Abstract |
Offline signature verification is one of the most challenging tasks in biometrics and document forensics. Unlike other verification problems, it needs to model minute but critical details between genuine and forged signatures, because a skilled falsification might often resembles the real signature with small deformation. This verification task is even harder in writer independent scenarios which is undeniably fiscal for realistic cases. In this paper, we model an offline writer independent signature verification task with a convolutional Siamese network. Siamese networks are twin networks with shared weights, which can be trained to learn a feature space where similar observations are placed in proximity. This is achieved by exposing the network to a pair of similar and dissimilar observations and minimizing the Euclidean distance between similar pairs while simultaneously maximizing it between dissimilar pairs. Experiments conducted on cross-domain datasets emphasize the capability of our network to model forgery in different languages (scripts) and handwriting styles. Moreover, our designed Siamese network, named SigNet, exceeds the state-of-the-art results on most of the benchmark signature datasets, which paves the way for further research in this direction. |
| 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; 600.121 |
Approved |
no |
| Call Number |
Admin @ si @ DDT2018 |
Serial |
3085 |
| Permanent link to this record |
| |
|
| |
| Author |
F. Javier Sanchez; Jorge Bernal |
| Title |
Use of Software Tools for Real-time Monitoring of Learning Processes: Application to Compilers subject |
Type |
Conference Article |
| Year |
2018 |
Publication |
4th International Conference of Higher Education Advances |
Abbreviated Journal |
|
| Volume |
|
Issue |
|
Pages |
1359-1366 |
| Keywords |
Monitoring; Evaluation tool; Gamification; Student motivation |
| Abstract |
The effective implementation of the Higher European Education Area has meant a change regarding the focus of the learning process, being now the student at its very center. This shift of focus requires a strong involvement and fluent communication between teachers and students to succeed. Considering the difficulties associated to motivate students to take a more active role in the learning process, we explore how the use of a software tool can help both actors to improve the learning experience. We present a tool that can help students to obtain instantaneous feedback with respect to their progress in the subject as well as providing teachers with useful information about the evolution of knowledge acquisition with respect to each of the subject areas. We compare the performance achieved by students in two academic years: results show an improvement in overall performance which, after observing graphs provided by our tool, can be associated to an increase in students interest in the subject. |
| Address |
Valencia; June 2018 |
| Corporate Author |
|
Thesis |
|
| Publisher |
|
Place of Publication |
|
Editor |
|
| Language |
|
Summary Language |
|
Original Title |
|
| Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
| Series Volume |
|
Series Issue |
|
Edition |
|
| ISSN |
|
ISBN |
|
Medium |
|
| Area |
|
Expedition |
|
Conference |
HEAD |
| Notes |
MV; no proj |
Approved |
no |
| Call Number |
Admin @ si @ SaB2018 |
Serial |
3165 |
| Permanent link to this record |
| |
|
| |
| Author |
Ana Maria Ares; Jorge Bernal; Maria Jesus Nozal; F. Javier Sanchez; Jose Bernal |
| Title |
Results of the use of Kahoot! gamification tool in a course of Chemistry |
Type |
Conference Article |
| Year |
2018 |
Publication |
4th International Conference on Higher Education Advances |
Abbreviated Journal |
|
| Volume |
|
Issue |
|
Pages |
1215-1222 |
| Keywords |
|
| Abstract |
The present study examines the use of Kahoot! as a gamification tool to explore mixed learning strategies. We analyze its use in two different groups of a theoretical subject of the third course of the Degree in Chemistry. An empirical-analytical methodology was used using Kahoot! in two different groups of students, with different frequencies. The academic results of these two group of students were compared between them and with those obtained in the previous course, in which Kahoot! was not employed, with the aim of measuring the evolution in the students´ knowledge. The results showed, in all cases, that the use of Kahoot! has led to a significant increase in the overall marks, and in the number of students who passed the subject. Moreover, some differences were also observed in students´ academic performance according to the group. Finally, it can be concluded that the use of a gamification tool (Kahoot!) in a university classroom had generally improved students´ learning and marks, and that this improvement is more prevalent in those students who have achieved a better Kahoot! performance. |
| Address |
Valencia; June 2018 |
| Corporate Author |
|
Thesis |
|
| Publisher |
|
Place of Publication |
|
Editor |
|
| Language |
|
Summary Language |
|
Original Title |
|
| Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
| Series Volume |
|
Series Issue |
|
Edition |
|
| ISSN |
|
ISBN |
|
Medium |
|
| Area |
|
Expedition |
|
Conference |
HEAD |
| Notes |
MV; no proj |
Approved |
no |
| Call Number |
Admin @ si @ ABN2018 |
Serial |
3246 |
| Permanent link to this record |
| |
|
| |
| Author |
Miguel Angel Bautista; Oriol Pujol; Fernando De la Torre; Sergio Escalera |
| Title |
Error-Correcting Factorization |
Type |
Journal Article |
| Year |
2018 |
Publication |
IEEE Transactions on Pattern Analysis and Machine Intelligence |
Abbreviated Journal |
TPAMI |
| Volume |
40 |
Issue |
|
Pages |
2388-2401 |
| Keywords |
|
| Abstract |
Error Correcting Output Codes (ECOC) is a successful technique in multi-class classification, which is a core problem in Pattern Recognition and Machine Learning. A major advantage of ECOC over other methods is that the multi- class problem is decoupled into a set of binary problems that are solved independently. However, literature defines a general error-correcting capability for ECOCs without analyzing how it distributes among classes, hindering a deeper analysis of pair-wise error-correction. To address these limitations this paper proposes an Error-Correcting Factorization (ECF) method, our contribution is three fold: (I) We propose a novel representation of the error-correction capability, called the design matrix, that enables us to build an ECOC on the basis of allocating correction to pairs of classes. (II) We derive the optimal code length of an ECOC using rank properties of the design matrix. (III) ECF is formulated as a discrete optimization problem, and a relaxed solution is found using an efficient constrained block coordinate descent approach. (IV) Enabled by the flexibility introduced with the design matrix we propose to allocate the error-correction on classes that are prone to confusion. Experimental results in several databases show that when allocating the error-correction to confusable classes ECF outperforms state-of-the-art approaches. |
| 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 |
0162-8828 |
ISBN |
|
Medium |
|
| Area |
|
Expedition |
|
Conference |
|
| Notes |
HuPBA; no menciona |
Approved |
no |
| Call Number |
Admin @ si @ BPT2018 |
Serial |
3015 |
| Permanent link to this record |
| |
|
| |
| Author |
Rain Eric Haamer; Eka Rusadze; Iiris Lusi; Tauseef Ahmed; Sergio Escalera; Gholamreza Anbarjafari |
| Title |
Review on Emotion Recognition Databases |
Type |
Book Chapter |
| Year |
2018 |
Publication |
Human-Robot Interaction: Theory and Application |
Abbreviated Journal |
|
| Volume |
|
Issue |
|
Pages |
|
| Keywords |
emotion; computer vision; databases |
| Abstract |
Over the past few decades human-computer interaction has become more important in our daily lives and research has developed in many directions: memory research, depression detection, and behavioural deficiency detection, lie detection, (hidden) emotion recognition etc. Because of that, the number of generic emotion and face databases or those tailored to specific needs have grown immensely large. Thus, a comprehensive yet compact guide is needed to help researchers find the most suitable database and understand what types of databases already exist. In this paper, different elicitation methods are discussed and the databases are primarily organized into neat and informative tables based on the format. |
| 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 |
978-1-78923-316-2 |
Medium |
|
| Area |
|
Expedition |
|
Conference |
|
| Notes |
HUPBA; 602.133 |
Approved |
no |
| Call Number |
Admin @ si @ HRL2018 |
Serial |
3212 |
| Permanent link to this record |
| |
|
| |
| Author |
Mohamed Ilyes Lakhal; Hakan Cevikalp; Sergio Escalera |
| Title |
CRN: End-to-end Convolutional Recurrent Network Structure Applied to Vehicle Classification |
Type |
Conference Article |
| Year |
2018 |
Publication |
13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications |
Abbreviated Journal |
|
| Volume |
5 |
Issue |
|
Pages |
137-144 |
| Keywords |
Vehicle Classification; Deep Learning; End-to-end Learning |
| Abstract |
Vehicle type classification is considered to be a central part of Intelligent Traffic Systems. In the recent years, deep learning methods have emerged in as being the state-of-the-art in many computer vision tasks. In this paper, we present a novel yet simple deep learning framework for the vehicle type classification problem. We propose an end-to-end trainable system, that combines convolution neural network for feature extraction and recurrent neural network as a classifier. The recurrent network structure is used to handle various types of feature inputs, and at the same time allows to produce a single or a set of class predictions. In order to assess the effectiveness of our solution, we have conducted a set of experiments in two public datasets, obtaining state of the art results. In addition, we also report results on the newly released MIO-TCD dataset. |
| Address |
Funchal; Madeira; Portugal; January 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 |
VISAPP |
| Notes |
HUPBA |
Approved |
no |
| Call Number |
Admin @ si @ LCE2018a |
Serial |
3094 |
| Permanent link to this record |
| |
|
| |
| Author |
Jon Almazan; Bojana Gajic; Naila Murray; Diane Larlus |
| Title |
Re-ID done right: towards good practices for person re-identification |
Type |
Miscellaneous |
| Year |
2018 |
Publication |
Arxiv |
Abbreviated Journal |
|
| Volume |
|
Issue |
|
Pages |
|
| Keywords |
|
| Abstract |
Training a deep architecture using a ranking loss has become standard for the person re-identification task. Increasingly, these deep architectures include additional components that leverage part detections, attribute predictions, pose estimators and other auxiliary information, in order to more effectively localize and align discriminative image regions. In this paper we adopt a different approach and carefully design each component of a simple deep architecture and, critically, the strategy for training it effectively for person re-identification. We extensively evaluate each design choice, leading to a list of good practices for person re-identification. By following these practices, our approach outperforms the state of the art, including more complex methods with auxiliary components, by large margins on four benchmark datasets. We also provide a qualitative analysis of our trained representation which indicates that, while compact, it is able to capture information from localized and discriminative regions, in a manner akin to an implicit attention mechanism. |
| Address |
January 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 |
|
| Notes |
|
Approved |
no |
| Call Number |
Admin @ si @ |
Serial |
3711 |
| Permanent link to this record |
| |
|
| |
| Author |
Cristhian A. Aguilera-Carrasco; C. Aguilera; Angel Sappa |
| Title |
Melamine Faced Panels Defect Classification beyond the Visible Spectrum |
Type |
Journal Article |
| Year |
2018 |
Publication |
Sensors |
Abbreviated Journal |
SENS |
| Volume |
18 |
Issue |
11 |
Pages |
1-10 |
| Keywords |
industrial application; infrared; machine learning |
| Abstract |
In this work, we explore the use of images from different spectral bands to classify defects in melamine faced panels, which could appear through the production process. Through experimental evaluation, we evaluate the use of images from the visible (VS), near-infrared (NIR), and long wavelength infrared (LWIR), to classify the defects using a feature descriptor learning approach together with a support vector machine classifier. Two descriptors were evaluated, Extended Local Binary Patterns (E-LBP) and SURF using a Bag of Words (BoW) representation. The evaluation was carried on with an image set obtained during this work, which contained five different defect categories that currently occurs in the industry. Results show that using images from beyond the visual spectrum helps to improve classification performance in contrast with a single visible spectrum solution. |
| 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 |
MSIAU; 600.122 |
Approved |
no |
| Call Number |
Admin @ si @ AAS2018 |
Serial |
3191 |
| Permanent link to this record |
| |
|
| |
| Author |
Mark Philip Philipsen; Jacob Velling Dueholm; Anders Jorgensen; Sergio Escalera; Thomas B. Moeslund |
| Title |
Organ Segmentation in Poultry Viscera Using RGB-D |
Type |
Journal Article |
| Year |
2018 |
Publication |
Sensors |
Abbreviated Journal |
SENS |
| Volume |
18 |
Issue |
1 |
Pages |
117 |
| Keywords |
semantic segmentation; RGB-D; random forest; conditional random field; 2D; 3D; CNN |
| Abstract |
We present a pattern recognition framework for semantic segmentation of visual structures, that is, multi-class labelling at pixel level, and apply it to the task of segmenting organs in the eviscerated viscera from slaughtered poultry in RGB-D images. This is a step towards replacing the current strenuous manual inspection at poultry processing plants. Features are extracted from feature maps such as activation maps from a convolutional neural network (CNN). A random forest classifier assigns class probabilities, which are further refined by utilizing context in a conditional random field. The presented method is compatible with both 2D and 3D features, which allows us to explore the value of adding 3D and CNN-derived features. The dataset consists of 604 RGB-D images showing 151 unique sets of eviscerated viscera from four different perspectives. A mean Jaccard index of 78.11% is achieved across the four classes of organs by using features derived from 2D, 3D and a CNN, compared to 74.28% using only basic 2D image features. |
| 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; no proj |
Approved |
no |
| Call Number |
Admin @ si @ PVJ2018 |
Serial |
3072 |
| Permanent link to this record |
| |
|
| |
| Author |
Razieh Rastgoo; Kourosh Kiani; Sergio Escalera |
| Title |
Multi-Modal Deep Hand Sign Language Recognition in Still Images Using Restricted Boltzmann Machine |
Type |
Journal Article |
| Year |
2018 |
Publication |
Entropy |
Abbreviated Journal |
ENTROPY |
| Volume |
20 |
Issue |
11 |
Pages |
809 |
| Keywords |
hand sign language; deep learning; restricted Boltzmann machine (RBM); multi-modal; profoundly deaf; noisy image |
| Abstract |
In this paper, a deep learning approach, Restricted Boltzmann Machine (RBM), is used to perform automatic hand sign language recognition from visual data. We evaluate how RBM, as a deep generative model, is capable of generating the distribution of the input data for an enhanced recognition of unseen data. Two modalities, RGB and Depth, are considered in the model input in three forms: original image, cropped image, and noisy cropped image. Five crops of the input image are used and the hand of these cropped images are detected using Convolutional Neural Network (CNN). After that, three types of the detected hand images are generated for each modality and input to RBMs. The outputs of the RBMs for two modalities are fused in another RBM in order to recognize the output sign label of the input image. The proposed multi-modal model is trained on all and part of the American alphabet and digits of four publicly available datasets. We also evaluate the robustness of the proposal against noise. Experimental results show that the proposed multi-modal model, using crops and the RBM fusing methodology, achieves state-of-the-art results on Massey University Gesture Dataset 2012, American Sign Language (ASL). and Fingerspelling Dataset from the University of Surrey’s Center for Vision, Speech and Signal Processing, NYU, and ASL Fingerspelling A datasets. |
| 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; no proj |
Approved |
no |
| Call Number |
Admin @ si @ RKE2018 |
Serial |
3198 |
| 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 |
