Publicacions CVC -- Query Results

	Publicacions CVC Home \| Show All \| Simple Search \| Advanced Search \| Add Record \| Import	Login Quick Search: Field: contains: ...
	106–120 of 155 records found matching your query (RSS \| history):

Search & Display Options

Select All Deselect All

<< 1 2 3 4 5 6 7 8 9 10 >> [11–11]

List View

Citations

Details

	Records
	Author	Mohamed Ilyes Lakhal; Hakan Çevikalp; Sergio Escalera; Ferda Ofli
	Title	Recurrent Neural Networks for Remote Sensing Image Classification			Type	Journal Article
	Year	2018	Publication	IET Computer Vision	Abbreviated Journal	IETCV
	Volume	12	Issue	7	Pages	1040 - 1045
	Keywords
	Abstract	Automatically classifying an image has been a central problem in computer vision for decades. A plethora of models has been proposed, from handcrafted feature solutions to more sophisticated approaches such as deep learning. The authors address the problem of remote sensing image classification, which is an important problem to many real world applications. They introduce a novel deep recurrent architecture that incorporates high-level feature descriptors to tackle this challenging problem. Their solution is based on the general encoder–decoder framework. To the best of the authors’ knowledge, this is the first study to use a recurrent network structure on this task. The experimental results show that the proposed framework outperforms the previous works in the three datasets widely used in the literature. They have achieved a state-of-the-art accuracy rate of 97.29% on the UC Merced dataset.
	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 @ LÇE2018			Serial	3119
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	Mohammad A. Haque; Ruben B. Bautista; Kamal Nasrollahi; Sergio Escalera; Christian B. Laursen; Ramin Irani; Ole K. Andersen; Erika G. Spaich; Kaustubh Kulkarni; Thomas B. Moeslund; Marco Bellantonio; Golamreza Anbarjafari; Fatemeh Noroozi
	Title	Deep Multimodal Pain Recognition: A Database and Comparision of Spatio-Temporal Visual Modalities, Faces and Gestures			Type	Conference Article
	Year	2018	Publication	13th IEEE Conference on Automatic Face and Gesture Recognition	Abbreviated Journal
	Volume		Issue		Pages	250 - 257
	Keywords
	Abstract	Pain is a symptom of many disorders associated with actual or potential tissue damage in human body. Managing pain is not only a duty but also highly cost prone. The most primitive state of pain management is the assessment of pain. Traditionally it was accomplished by self-report or visual inspection by experts. However, automatic pain assessment systems from facial videos are also rapidly evolving due to the need of managing pain in a robust and cost effective way. Among different challenges of automatic pain assessment from facial video data two issues are increasingly prevalent: first, exploiting both spatial and temporal information of the face to assess pain level, and second, incorporating multiple visual modalities to capture complementary face information related to pain. Most works in the literature focus on merely exploiting spatial information on chromatic (RGB) video data on shallow learning scenarios. However, employing deep learning techniques for spatio-temporal analysis considering Depth (D) and Thermal (T) along with RGB has high potential in this area. In this paper, we present the first state-of-the-art publicly available database, 'Multimodal Intensity Pain (MIntPAIN)' database, for RGBDT pain level recognition in sequences. We provide a first baseline results including 5 pain levels recognition by analyzing independent visual modalities and their fusion with CNN and LSTM models. From the experimental evaluation we observe that fusion of modalities helps to enhance recognition performance of pain levels in comparison to isolated ones. In particular, the combination of RGB, D, and T in an early fusion fashion achieved the best recognition rate.
	Address	Xian; China; May 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	FG
	Notes	HUPBA; no proj			Approved	no
	Call Number	Admin @ si @ HBN2018			Serial	3117
Permanent link to this record



	Author	Mohammad N. S. Jahromi; Morten Bojesen Bonderup; Maryam Asadi-Aghbolaghi; Egils Avots; Kamal Nasrollahi; Sergio Escalera; Shohreh Kasaei; Thomas B. Moeslund; Gholamreza Anbarjafari
	Title	Automatic Access Control Based on Face and Hand Biometrics in a Non-cooperative Context			Type	Conference Article
	Year	2018	Publication	IEEE Winter Applications of Computer Vision Workshops	Abbreviated Journal
	Volume		Issue		Pages	28-36
	Keywords	IEEE Winter Applications of Computer Vision Workshops
	Abstract	Automatic access control systems (ACS) based on the human biometrics or physical tokens are widely employed in public and private areas. Yet these systems, in their conventional forms, are restricted to active interaction from the users. In scenarios where users are not cooperating with the system, these systems are challenged. Failure in cooperation with the biometric systems might be intentional or because the users are incapable of handling the interaction procedure with the biometric system or simply forget to cooperate with it, due to for example, illness like dementia. This work introduces a challenging bimodal database, including face and hand information of the users when they approach a door to open it by its handle in a noncooperative context. We have defined two (an easy and a challenging) protocols on how to use the database. We have reported results on many baseline methods, including deep learning techniques as well as conventional methods on the database. The obtained results show the merit of the proposed database and the challenging nature of access control with non-cooperative users.
	Address	Lake Tahoe; USA; March 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	WACVW
	Notes	HUPBA; 602.133			Approved	no
	Call Number	Admin @ si @ JBA2018			Serial	3121
Permanent link to this record



	Author	Mohammed Al Rawi; Dimosthenis Karatzas
	Title	On the Labeling Correctness in Computer Vision Datasets			Type	Conference Article
	Year	2018	Publication	Proceedings of the Workshop on Interactive Adaptive Learning, co-located with European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	Image datasets have heavily been used to build computer vision systems. These datasets are either manually or automatically labeled, which is a problem as both labeling methods are prone to errors. To investigate this problem, we use a majority voting ensemble that combines the results from several Convolutional Neural Networks (CNNs). Majority voting ensembles not only enhance the overall performance, but can also be used to estimate the confidence level of each sample. We also examined Softmax as another form to estimate posterior probability. We have designed various experiments with a range of different ensembles built from one or different, or temporal/snapshot CNNs, which have been trained multiple times stochastically. We analyzed CIFAR10, CIFAR100, EMNIST, and SVHN datasets and we found quite a few incorrect labels, both in the training and testing sets. We also present detailed confidence analysis on these datasets and we found that the ensemble is better than the Softmax when used estimate the per-sample confidence. This work thus proposes an approach that can be used to scrutinize and verify the labeling of computer vision datasets, which can later be applied to weakly/semi-supervised learning. We propose a measure, based on the Odds-Ratio, to quantify how many of these incorrectly classified labels are actually incorrectly labeled and how many of these are confusing. The proposed methods are easily scalable to larger datasets, like ImageNet, LSUN and SUN, as each CNN instance is trained for 60 epochs; or even faster, by implementing a temporal (snapshot) ensemble.
	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	ECML-PKDDW
	Notes	DAG; 600.121; 600.129			Approved	no
	Call Number	Admin @ si @ RaK2018			Serial	3144
Permanent link to this record



	Author	Muhammad Anwer Rao; Fahad Shahbaz Khan; Joost Van de Weijer; Matthieu Molinier; Jorma Laaksonen
	Title	Binary patterns encoded convolutional neural networks for texture recognition and remote sensing scene classification			Type	Journal Article
	Year	2018	Publication	ISPRS Journal of Photogrammetry and Remote Sensing	Abbreviated Journal	ISPRS J
	Volume	138	Issue		Pages	74-85
	Keywords	Remote sensing; Deep learning; Scene classification; Local Binary Patterns; Texture analysis
	Abstract	Designing discriminative powerful texture features robust to realistic imaging conditions is a challenging computer vision problem with many applications, including material recognition and analysis of satellite or aerial imagery. In the past, most texture description approaches were based on dense orderless statistical distribution of local features. However, most recent approaches to texture recognition and remote sensing scene classification are based on Convolutional Neural Networks (CNNs). The de facto practice when learning these CNN models is to use RGB patches as input with training performed on large amounts of labeled data (ImageNet). In this paper, we show that Local Binary Patterns (LBP) encoded CNN models, codenamed TEX-Nets, trained using mapped coded images with explicit LBP based texture information provide complementary information to the standard RGB deep models. Additionally, two deep architectures, namely early and late fusion, are investigated to combine the texture and color information. To the best of our knowledge, we are the first to investigate Binary Patterns encoded CNNs and different deep network fusion architectures for texture recognition and remote sensing scene classification. We perform comprehensive experiments on four texture recognition datasets and four remote sensing scene classification benchmarks: UC-Merced with 21 scene categories, WHU-RS19 with 19 scene classes, RSSCN7 with 7 categories and the recently introduced large scale aerial image dataset (AID) with 30 aerial scene types. We demonstrate that TEX-Nets provide complementary information to standard RGB deep model of the same network architecture. Our late fusion TEX-Net architecture always improves the overall performance compared to the standard RGB network on both recognition problems. Furthermore, our final combination leads to consistent improvement over the state-of-the-art for remote sensing scene
	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; 600.109; 600.106; 600.120			Approved	no
	Call Number	Admin @ si @ RKW2018			Serial	3158
Permanent link to this record



	Author	Oscar Argudo; Marc Comino; Antonio Chica; Carlos Andujar; Felipe Lumbreras
	Title	Segmentation of aerial images for plausible detail synthesis			Type	Journal Article
	Year	2018	Publication	Computers & Graphics	Abbreviated Journal	CG
	Volume	71	Issue		Pages	23-34
	Keywords	Terrain editing; Detail synthesis; Vegetation synthesis; Terrain rendering; Image segmentation
	Abstract	The visual enrichment of digital terrain models with plausible synthetic detail requires the segmentation of aerial images into a suitable collection of categories. In this paper we present a complete pipeline for segmenting high-resolution aerial images into a user-defined set of categories distinguishing e.g. terrain, sand, snow, water, and different types of vegetation. This segmentation-for-synthesis problem implies that per-pixel categories must be established according to the algorithms chosen for rendering the synthetic detail. This precludes the definition of a universal set of labels and hinders the construction of large training sets. Since artists might choose to add new categories on the fly, the whole pipeline must be robust against unbalanced datasets, and fast on both training and inference. Under these constraints, we analyze the contribution of common per-pixel descriptors, and compare the performance of state-of-the-art supervised learning algorithms. We report the findings of two user studies. The first one was conducted to analyze human accuracy when manually labeling aerial images. The second user study compares detailed terrains built using different segmentation strategies, including official land cover maps. These studies demonstrate that our approach can be used to turn digital elevation models into fully-featured, detailed terrains with minimal authoring efforts.
	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	0097-8493	ISBN		Medium
	Area		Expedition		Conference
	Notes	MSIAU; 600.086; 600.118			Approved	no
	Call Number	Admin @ si @ ACC2018			Serial	3147
Permanent link to this record



	Author	Ozan Caglayan; Adrien Bardet; Fethi Bougares; Loic Barrault; Kai Wang; Marc Masana; Luis Herranz; Joost Van de Weijer
	Title	LIUM-CVC Submissions for WMT18 Multimodal Translation Task			Type	Conference Article
	Year	2018	Publication	3rd Conference on Machine Translation	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	This paper describes the multimodal Neural Machine Translation systems developed by LIUM and CVC for WMT18 Shared Task on Multimodal Translation. This year we propose several modifications to our previou multimodal attention architecture in order to better integrate convolutional features and refine them using encoder-side information. Our final constrained submissions ranked first for English→French and second for English→German language pairs among the constrained submissions according to the automatic evaluation metric METEOR.
	Address	Brussels; Belgium; 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	WMT
	Notes	LAMP; 600.106; 600.120			Approved	no
	Call Number	Admin @ si @ CBB2018			Serial	3240
Permanent link to this record



	Author	Patricia Suarez; Angel Sappa; Boris X. Vintimilla
	Title	Cross-spectral image dehaze through a dense stacked conditional GAN based approach			Type	Conference Article
	Year	2018	Publication	14th IEEE International Conference on Signal Image Technology & Internet Based System	Abbreviated Journal
	Volume		Issue		Pages
	Keywords	Infrared imaging; Dense; Stacked CGAN; Crossspectral; Convolutional networks
	Abstract	This paper proposes a novel approach to remove haze from RGB images using a near infrared images based on a dense stacked conditional Generative Adversarial Network (CGAN). The architecture of the deep network implemented receives, besides the images with haze, its corresponding image in the near infrared spectrum, which serve to accelerate the learning process of the details of the characteristics of the images. The model uses a triplet layer that allows the independence learning of each channel of the visible spectrum image to remove the haze on each color channel separately. A multiple loss function scheme is proposed, which ensures balanced learning between the colors and the structure of the images. Experimental results have shown that the proposed method effectively removes the haze from the images. Additionally, the proposed approach is compared with a state of the art approach showing better results.
	Address	Las Palmas de Gran Canaria; November 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	978-1-5386-9385-8	Medium
	Area		Expedition		Conference	SITIS
	Notes	MSIAU; 600.086; 600.130; 600.122			Approved	no
	Call Number	Admin @ si @ SSV2018a			Serial	3193
Permanent link to this record



	Author	Patricia Suarez; Angel Sappa; Boris X. Vintimilla
	Title	Vegetation Index Estimation from Monospectral Images			Type	Conference Article
	Year	2018	Publication	15th International Conference on Images Analysis and Recognition	Abbreviated Journal
	Volume	10882	Issue		Pages	353-362
	Keywords
	Abstract	This paper proposes a novel approach to estimate Normalized Difference Vegetation Index (NDVI) from just the red channel of a RGB image. The NDVI index is defined as the ratio of the difference of the red and infrared radiances over their sum. In other words, information from the red channel of a RGB image and the corresponding infrared spectral band are required for its computation. In the current work the NDVI index is estimated just from the red channel by training a Conditional Generative Adversarial Network (CGAN). The architecture proposed for the generative network consists of a single level structure, which combines at the final layer results from convolutional operations together with the given red channel with Gaussian noise to enhance details, resulting in a sharp NDVI image. Then, the discriminative model estimates the probability that the NDVI generated index came from the training dataset, rather than the index automatically generated. Experimental results with a large set of real images are provided showing that a Conditional GAN single level model represents an acceptable approach to estimate NDVI index.
	Address	Povoa de Varzim; Portugal; June 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	ICIAR
	Notes	MSIAU; 600.086; 600.130; 600.122			Approved	no
	Call Number	Admin @ si @ SSV2018c			Serial	3196
Permanent link to this record



	Author	Patricia Suarez; Angel Sappa; Boris X. Vintimilla; Riad I. Hammoud
	Title	Near InfraRed Imagery Colorization			Type	Conference Article
	Year	2018	Publication	25th International Conference on Image Processing	Abbreviated Journal
	Volume		Issue		Pages	2237 - 2241
	Keywords	Convolutional Neural Networks (CNN), Generative Adversarial Network (GAN), Infrared Imagery colorization
	Abstract	This paper proposes a stacked conditional Generative Adversarial Network-based method for Near InfraRed (NIR) imagery colorization. We propose a variant architecture of Generative Adversarial Network (GAN) that uses multiple loss functions over a conditional probabilistic generative model. We show that this new architecture/loss-function yields better generalization and representation of the generated colored IR images. The proposed approach is evaluated on a large test dataset and compared to recent state of the art methods using standard metrics.
	Address	Athens; Greece; 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	ICIP
	Notes	MSIAU; 600.086; 600.130; 600.122			Approved	no
	Call Number	Admin @ si @ SSV2018b			Serial	3195
Permanent link to this record



	Author	Patricia Suarez; Angel Sappa; Boris X. Vintimilla; Riad I. Hammoud
	Title	Deep Learning based Single Image Dehazing			Type	Conference Article
	Year	2018	Publication	31st IEEE Conference on Computer Vision and Pattern Recognition Workhsop	Abbreviated Journal
	Volume		Issue		Pages	1250 - 12507
	Keywords	Gallium nitride; Atmospheric modeling; Generators; Generative adversarial networks; Convergence; Image color analysis
	Abstract	This paper proposes a novel approach to remove haze degradations in RGB images using a stacked conditional Generative Adversarial Network (GAN). It employs a triplet of GAN to remove the haze on each color channel independently. A multiple loss functions scheme, applied over a conditional probabilistic model, is proposed. The proposed GAN architecture learns to remove the haze, using as conditioned entrance, the images with haze from which the clear images will be obtained. Such formulation ensures a fast model training convergence and a homogeneous model generalization. Experiments showed that the proposed method generates high-quality clear images.
	Address	Salt Lake City; USA; 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	CVPRW
	Notes	MSIAU; 600.086; 600.130; 600.122			Approved	no
	Call Number	Admin @ si @ SSV2018d			Serial	3197
Permanent link to this record



	Author	Patrick Brandao; O. Zisimopoulos; E. Mazomenos; G. Ciutib; Jorge Bernal; M. Visentini-Scarzanell; A. Menciassi; P. Dario; A. Koulaouzidis; A. Arezzo; D.J. Hawkes; D. Stoyanov
	Title	Towards a computed-aided diagnosis system in colonoscopy: Automatic polyp segmentation using convolution neural networks			Type	Journal
	Year	2018	Publication	Journal of Medical Robotics Research	Abbreviated Journal	JMRR
	Volume	3	Issue	2	Pages
	Keywords	convolutional neural networks; colonoscopy; computer aided diagnosis
	Abstract	Early diagnosis is essential for the successful treatment of bowel cancers including colorectal cancer (CRC) and capsule endoscopic imaging with robotic actuation can be a valuable diagnostic tool when combined with automated image analysis. We present a deep learning rooted detection and segmentation framework for recognizing lesions in colonoscopy and capsule endoscopy images. We restructure established convolution architectures, such as VGG and ResNets, by converting them into fully-connected convolution networks (FCNs), ne-tune them and study their capabilities for polyp segmentation and detection. We additionally use Shape-from-Shading (SfS) to recover depth and provide a richer representation of the tissue's structure in colonoscopy images. Depth is incorporated into our network models as an additional input channel to the RGB information and we demonstrate that the resulting network yields improved performance. Our networks are tested on publicly available datasets and the most accurate segmentation model achieved a mean segmentation IU of 47.78% and 56.95% on the ETIS-Larib and CVC-Colon datasets, respectively. For polyp detection, the top performing models we propose surpass the current state of the art with detection recalls superior to 90% for all datasets tested. To our knowledge, we present the rst work to use FCNs for polyp segmentation in addition to proposing a novel combination of SfS and RGB that boosts performance.
	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	MV; no menciona			Approved	no
	Call Number	BZM2018			Serial	2976
Permanent link to this record



	Author	Pau Riba; Andreas Fischer; Josep Llados; Alicia Fornes
	Title	Learning Graph Distances with Message Passing Neural Networks			Type	Conference Article
	Year	2018	Publication	24th International Conference on Pattern Recognition	Abbreviated Journal
	Volume		Issue		Pages	2239-2244
	Keywords	★Best Paper Award★
	Abstract	Graph representations have been widely used in pattern recognition thanks to their powerful representation formalism and rich theoretical background. A number of error-tolerant graph matching algorithms such as graph edit distance have been proposed for computing a distance between two labelled graphs. However, they typically suffer from a high computational complexity, which makes it difficult to apply these matching algorithms in a real scenario. In this paper, we propose an efficient graph distance based on the emerging field of geometric deep learning. Our method employs a message passing neural network to capture the graph structure and learns a metric with a siamese network approach. The performance of the proposed graph distance is validated in two application cases, graph classification and graph retrieval of handwritten words, and shows a promising performance when compared with (approximate) graph edit distance benchmarks.
	Address	Beijing; China; August 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	ICPR
	Notes	DAG; 600.097; 603.057; 601.302; 600.121			Approved	no
	Call Number	Admin @ si @ RFL2018			Serial	3168
Permanent link to this record



	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