Records |
Author |
Santiago Segui; Michal Drozdzal; Guillem Pascual; Petia Radeva; Carolina Malagelada; Fernando Azpiroz; Jordi Vitria |
Title |
Generic Feature Learning for Wireless Capsule Endoscopy Analysis |
Type |
Journal Article |
Year |
2016 |
Publication |
Computers in Biology and Medicine |
Abbreviated Journal |
CBM |
Volume |
79 |
Issue |
|
Pages |
163-172 |
Keywords |
Wireless capsule endoscopy; Deep learning; Feature learning; Motility analysis |
Abstract |
The interpretation and analysis of wireless capsule endoscopy (WCE) recordings is a complex task which requires sophisticated computer aided decision (CAD) systems to help physicians with video screening and, finally, with the diagnosis. Most CAD systems used in capsule endoscopy share a common system design, but use very different image and video representations. As a result, each time a new clinical application of WCE appears, a new CAD system has to be designed from the scratch. This makes the design of new CAD systems very time consuming. Therefore, in this paper we introduce a system for small intestine motility characterization, based on Deep Convolutional Neural Networks, which circumvents the laborious step of designing specific features for individual motility events. Experimental results show the superiority of the learned features over alternative classifiers constructed using state-of-the-art handcrafted features. In particular, it reaches a mean classification accuracy of 96% for six intestinal motility events, outperforming the other classifiers by a large margin (a 14% relative performance increase). |
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 |
OR; MILAB;MV; |
Approved |
no |
Call Number |
Admin @ si @ SDP2016 |
Serial |
2836 |
Permanent link to this record |
|
|
|
Author |
Jun Wan; Sergio Escalera; Francisco Perales; Josef Kittler |
Title |
Articulated Motion and Deformable Objects |
Type |
Journal Article |
Year |
2018 |
Publication |
Pattern Recognition |
Abbreviated Journal |
PR |
Volume |
79 |
Issue |
|
Pages |
55-64 |
Keywords |
|
Abstract |
This guest editorial introduces the twenty two papers accepted for this Special Issue on Articulated Motion and Deformable Objects (AMDO). They are grouped into four main categories within the field of AMDO: human motion analysis (action/gesture), human pose estimation, deformable shape segmentation, and face analysis. For each of the four topics, a survey of the recent developments in the field is presented. The accepted papers are briefly introduced in the context of this survey. They contribute novel methods, algorithms with improved performance as measured on benchmarking datasets, as well as two new datasets for hand action detection and human posture analysis. The special issue should be of high relevance to the reader interested in AMDO recognition and promote future research directions in the 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; no proj |
Approved |
no |
Call Number |
Admin @ si @ WEP2018 |
Serial |
3126 |
Permanent link to this record |
|
|
|
Author |
Julio C. S. Jacques Junior; Xavier Baro; Sergio Escalera |
Title |
Exploiting feature representations through similarity learning, post-ranking and ranking aggregation for person re-identification |
Type |
Journal Article |
Year |
2018 |
Publication |
Image and Vision Computing |
Abbreviated Journal |
IMAVIS |
Volume |
79 |
Issue |
|
Pages |
76-85 |
Keywords |
|
Abstract |
Person re-identification has received special attention by the human analysis community in the last few years. To address the challenges in this field, many researchers have proposed different strategies, which basically exploit either cross-view invariant features or cross-view robust metrics. In this work, we propose to exploit a post-ranking approach and combine different feature representations through ranking aggregation. Spatial information, which potentially benefits the person matching, is represented using a 2D body model, from which color and texture information are extracted and combined. We also consider background/foreground information, automatically extracted via Deep Decompositional Network, and the usage of Convolutional Neural Network (CNN) features. To describe the matching between images we use the polynomial feature map, also taking into account local and global information. The Discriminant Context Information Analysis based post-ranking approach is used to improve initial ranking lists. Finally, the Stuart ranking aggregation method is employed to combine complementary ranking lists obtained from different feature representations. Experimental results demonstrated that we improve the state-of-the-art on VIPeR and PRID450s datasets, achieving 67.21% and 75.64% on top-1 rank recognition rate, respectively, as well as obtaining competitive results on CUHK01 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; 602.143 |
Approved |
no |
Call Number |
Admin @ si @ JBE2018 |
Serial |
3138 |
Permanent link to this record |
|
|
|
Author |
Meysam Madadi; Sergio Escalera; Alex Carruesco Llorens; Carlos Andujar; Xavier Baro; Jordi Gonzalez |
Title |
Top-down model fitting for hand pose recovery in sequences of depth images |
Type |
Journal Article |
Year |
2018 |
Publication |
Image and Vision Computing |
Abbreviated Journal |
IMAVIS |
Volume |
79 |
Issue |
|
Pages |
63-75 |
Keywords |
|
Abstract |
State-of-the-art approaches on hand pose estimation from depth images have reported promising results under quite controlled considerations. In this paper we propose a two-step pipeline for recovering the hand pose from a sequence of depth images. The pipeline has been designed to deal with images taken from any viewpoint and exhibiting a high degree of finger occlusion. In a first step we initialize the hand pose using a part-based model, fitting a set of hand components in the depth images. In a second step we consider temporal data and estimate the parameters of a trained bilinear model consisting of shape and trajectory bases. We evaluate our approach on a new created synthetic hand dataset along with NYU and MSRA real datasets. Results demonstrate that the proposed method outperforms the most recent pose recovering approaches, including those based on CNNs. |
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; 600.098 |
Approved |
no |
Call Number |
Admin @ si @ MEC2018 |
Serial |
3203 |
Permanent link to this record |
|
|
|
Author |
Razieh Rastgoo; Kourosh Kiani; Sergio Escalera |
Title |
Video-based Isolated Hand Sign Language Recognition Using a Deep Cascaded Model |
Type |
Journal Article |
Year |
2020 |
Publication |
Multimedia Tools and Applications |
Abbreviated Journal |
MTAP |
Volume |
79 |
Issue |
|
Pages |
22965–22987 |
Keywords |
|
Abstract |
In this paper, we propose an efficient cascaded model for sign language recognition taking benefit from spatio-temporal hand-based information using deep learning approaches, especially Single Shot Detector (SSD), Convolutional Neural Network (CNN), and Long Short Term Memory (LSTM), from videos. Our simple yet efficient and accurate model includes two main parts: hand detection and sign recognition. Three types of spatial features, including hand features, Extra Spatial Hand Relation (ESHR) features, and Hand Pose (HP) features, have been fused in the model to feed to LSTM for temporal features extraction. We train SSD model for hand detection using some videos collected from five online sign dictionaries. Our model is evaluated on our proposed dataset (Rastgoo et al., Expert Syst Appl 150: 113336, 2020), including 10’000 sign videos for 100 Persian sign using 10 contributors in 10 different backgrounds, and isoGD dataset. Using the 5-fold cross-validation method, our model outperforms state-of-the-art alternatives in sign language recognition |
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 menciona |
Approved |
no |
Call Number |
Admin @ si @ RKE2020b |
Serial |
3442 |
Permanent link to this record |
|
|
|
Author |
Rahma Kalboussi; Aymen Azaza; Joost Van de Weijer; Mehrez Abdellaoui; Ali Douik |
Title |
Object proposals for salient object segmentation in videos |
Type |
Journal Article |
Year |
2020 |
Publication |
Multimedia Tools and Applications |
Abbreviated Journal |
MTAP |
Volume |
79 |
Issue |
13 |
Pages |
8677-8693 |
Keywords |
|
Abstract |
Salient object segmentation in videos is generally broken up in a video segmentation part and a saliency assignment part. Recently, object proposals, which are used to segment the image, have had significant impact on many computer vision applications, including image segmentation, object detection, and recently saliency detection in still images. However, their usage has not yet been evaluated for salient object segmentation in videos. Therefore, in this paper, we investigate the application of object proposals to salient object segmentation in videos. In addition, we propose a new motion feature derived from the optical flow structure tensor for video saliency detection. Experiments on two standard benchmark datasets for video saliency show that the proposed motion feature improves saliency estimation results, and that object proposals are an efficient method for salient object segmentation. Results on the challenging SegTrack v2 and Fukuchi benchmark data sets show that we significantly outperform the state-of-the-art. |
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; 600.120 |
Approved |
no |
Call Number |
KAW2020 |
Serial |
3504 |
Permanent link to this record |
|
|
|
Author |
Egils Avots; Meysam Madadi; Sergio Escalera; Jordi Gonzalez; Xavier Baro; Paul Pallin; Gholamreza Anbarjafari |
Title |
From 2D to 3D geodesic-based garment matching |
Type |
Journal Article |
Year |
2019 |
Publication |
Multimedia Tools and Applications |
Abbreviated Journal |
MTAP |
Volume |
78 |
Issue |
18 |
Pages |
25829–25853 |
Keywords |
Shape matching; Geodesic distance; Texture mapping; RGBD image processing; Gaussian mixture model |
Abstract |
A new approach for 2D to 3D garment retexturing is proposed based on Gaussian mixture models and thin plate splines (TPS). An automatically segmented garment of an individual is matched to a new source garment and rendered, resulting in augmented images in which the target garment has been retextured using the texture of the source garment. We divide the problem into garment boundary matching based on Gaussian mixture models and then interpolate inner points using surface topology extracted through geodesic paths, which leads to a more realistic result than standard approaches. We evaluated and compared our system quantitatively by root mean square error (RMS) and qualitatively using the mean opinion score (MOS), showing the benefits of the proposed methodology on our gathered 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; ISE; 600.098; 600.119; 602.133 |
Approved |
no |
Call Number |
Admin @ si @ AME2019 |
Serial |
3317 |
Permanent link to this record |
|
|
|
Author |
Andre Litvin; Kamal Nasrollahi; Sergio Escalera; Cagri Ozcinar; Thomas B. Moeslund; Gholamreza Anbarjafari |
Title |
A Novel Deep Network Architecture for Reconstructing RGB Facial Images from Thermal for Face Recognition |
Type |
Journal Article |
Year |
2019 |
Publication |
Multimedia Tools and Applications |
Abbreviated Journal |
MTAP |
Volume |
78 |
Issue |
18 |
Pages |
25259–25271 |
Keywords |
Fully convolutional networks; FusionNet; Thermal imaging; Face recognition |
Abstract |
This work proposes a fully convolutional network architecture for RGB face image generation from a given input thermal face image to be applied in face recognition scenarios. The proposed method is based on the FusionNet architecture and increases robustness against overfitting using dropout after bridge connections, randomised leaky ReLUs (RReLUs), and orthogonal regularization. Furthermore, we propose to use a decoding block with resize convolution instead of transposed convolution to improve final RGB face image generation. To validate our proposed network architecture, we train a face classifier and compare its face recognition rate on the reconstructed RGB images from the proposed architecture, to those when reconstructing images with the original FusionNet, as well as when using the original RGB images. As a result, we are introducing a new architecture which leads to a more accurate network. |
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 menciona |
Approved |
no |
Call Number |
Admin @ si @ LNE2019 |
Serial |
3318 |
Permanent link to this record |
|
|
|
Author |
Marçal Rusiñol; J. Chazalon; Katerine Diaz |
Title |
Augmented Songbook: an Augmented Reality Educational Application for Raising Music Awareness |
Type |
Journal Article |
Year |
2018 |
Publication |
Multimedia Tools and Applications |
Abbreviated Journal |
MTAP |
Volume |
77 |
Issue |
11 |
Pages |
13773-13798 |
Keywords |
Augmented reality; Document image matching; Educational applications |
Abstract |
This paper presents the development of an Augmented Reality mobile application which aims at sensibilizing young children to abstract concepts of music. Such concepts are, for instance, the musical notation or the idea of rhythm. Recent studies in Augmented Reality for education suggest that such technologies have multiple benefits for students, including younger ones. As mobile document image acquisition and processing gains maturity on mobile platforms, we explore how it is possible to build a markerless and real-time application to augment the physical documents with didactic animations and interactive virtual content. Given a standard image processing pipeline, we compare the performance of different local descriptors at two key stages of the process. Results suggest alternatives to the SIFT local descriptors, regarding result quality and computational efficiency, both for document model identification and perspective transform estimation. All experiments are performed on an original and public dataset we introduce here. |
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; ADAS; 600.084; 600.121; 600.118; 600.129 |
Approved |
no |
Call Number |
Admin @ si @ RCD2018 |
Serial |
2996 |
Permanent link to this record |
|
|
|
Author |
Laura Lopez-Fuentes; Joost Van de Weijer; Manuel Gonzalez-Hidalgo; Harald Skinnemoen; Andrew Bagdanov |
Title |
Review on computer vision techniques in emergency situations |
Type |
Journal Article |
Year |
2018 |
Publication |
Multimedia Tools and Applications |
Abbreviated Journal |
MTAP |
Volume |
77 |
Issue |
13 |
Pages |
17069–17107 |
Keywords |
Emergency management; Computer vision; Decision makers; Situational awareness; Critical situation |
Abstract |
In emergency situations, actions that save lives and limit the impact of hazards are crucial. In order to act, situational awareness is needed to decide what to do. Geolocalized photos and video of the situations as they evolve can be crucial in better understanding them and making decisions faster. Cameras are almost everywhere these days, either in terms of smartphones, installed CCTV cameras, UAVs or others. However, this poses challenges in big data and information overflow. Moreover, most of the time there are no disasters at any given location, so humans aiming to detect sudden situations may not be as alert as needed at any point in time. Consequently, computer vision tools can be an excellent decision support. The number of emergencies where computer vision tools has been considered or used is very wide, and there is a great overlap across related emergency research. Researchers tend to focus on state-of-the-art systems that cover the same emergency as they are studying, obviating important research in other fields. In order to unveil this overlap, the survey is divided along four main axes: the types of emergencies that have been studied in computer vision, the objective that the algorithms can address, the type of hardware needed and the algorithms used. Therefore, this review provides a broad overview of the progress of computer vision covering all sorts of emergencies. |
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; 600.068; 600.120 |
Approved |
no |
Call Number |
Admin @ si @ LWG2018 |
Serial |
3041 |
Permanent link to this record |
|
|
|
Author |
H. Martin Kjer; Jens Fagertun; Sergio Vera; Debora Gil; Miguel Angel Gonzalez Ballester; Rasmus R. Paulsena |
Title |
Free-form image registration of human cochlear uCT data using skeleton similarity as anatomical prior |
Type |
Journal Article |
Year |
2016 |
Publication |
Patter Recognition Letters |
Abbreviated Journal |
PRL |
Volume |
76 |
Issue |
1 |
Pages |
76-82 |
Keywords |
|
Abstract |
|
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 |
IAM; 600.060 |
Approved |
no |
Call Number |
Admin @ si @ MFV2017b |
Serial |
2941 |
Permanent link to this record |
|
|
|
Author |
Anjan Dutta; Josep Llados; Horst Bunke; Umapada Pal |
Title |
Product graph-based higher order contextual similarities for inexact subgraph matching |
Type |
Journal Article |
Year |
2018 |
Publication |
Pattern Recognition |
Abbreviated Journal |
PR |
Volume |
76 |
Issue |
|
Pages |
596-611 |
Keywords |
|
Abstract |
Many algorithms formulate graph matching as an optimization of an objective function of pairwise quantification of nodes and edges of two graphs to be matched. Pairwise measurements usually consider local attributes but disregard contextual information involved in graph structures. We address this issue by proposing contextual similarities between pairs of nodes. This is done by considering the tensor product graph (TPG) of two graphs to be matched, where each node is an ordered pair of nodes of the operand graphs. Contextual similarities between a pair of nodes are computed by accumulating weighted walks (normalized pairwise similarities) terminating at the corresponding paired node in TPG. Once the contextual similarities are obtained, we formulate subgraph matching as a node and edge selection problem in TPG. We use contextual similarities to construct an objective function and optimize it with a linear programming approach. Since random walk formulation through TPG takes into account higher order information, it is not a surprise that we obtain more reliable similarities and better discrimination among the nodes and edges. Experimental results shown on synthetic as well as real benchmarks illustrate that higher order contextual similarities increase discriminating power and allow one to find approximate solutions to the subgraph matching problem. |
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; 602.167; 600.097; 600.121 |
Approved |
no |
Call Number |
Admin @ si @ DLB2018 |
Serial |
3083 |
Permanent link to this record |
|
|
|
Author |
Svebor Karaman; Andrew Bagdanov; Lea Landucci; Gianpaolo D'Amico; Andrea Ferracani; Daniele Pezzatini; Alberto del Bimbo |
Title |
Personalized multimedia content delivery on an interactive table by passive observation of museum visitors |
Type |
Journal Article |
Year |
2016 |
Publication |
Multimedia Tools and Applications |
Abbreviated Journal |
MTAP |
Volume |
75 |
Issue |
7 |
Pages |
3787-3811 |
Keywords |
Computer vision; Video surveillance; Cultural heritage; Multimedia museum; Personalization; Natural interaction; Passive profiling |
Abstract |
The amount of multimedia data collected in museum databases is growing fast, while the capacity of museums to display information to visitors is acutely limited by physical space. Museums must seek the perfect balance of information given on individual pieces in order to provide sufficient information to aid visitor understanding while maintaining sparse usage of the walls and guaranteeing high appreciation of the exhibit. Moreover, museums often target the interests of average visitors instead of the entire spectrum of different interests each individual visitor might have. Finally, visiting a museum should not be an experience contained in the physical space of the museum but a door opened onto a broader context of related artworks, authors, artistic trends, etc. In this paper we describe the MNEMOSYNE system that attempts to address these issues through a new multimedia museum experience. Based on passive observation, the system builds a profile of the artworks of interest for each visitor. These profiles of interest are then used to drive an interactive table that personalizes multimedia content delivery. The natural user interface on the interactive table uses the visitor’s profile, an ontology of museum content and a recommendation system to personalize exploration of multimedia content. At the end of their visit, the visitor can take home a personalized summary of their visit on a custom mobile application. In this article we describe in detail each component of our approach as well as the first field trials of our prototype system built and deployed at our permanent exhibition space at LeMurate (http://www.lemurate.comune.fi.it/lemurate/) in Florence together with the first results of the evaluation process during the official installation in the National Museum of Bargello (http://www.uffizi.firenze.it/musei/?m=bargello). |
Address |
|
Corporate Author |
|
Thesis |
|
Publisher |
Springer US |
Place of Publication |
|
Editor |
|
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
1380-7501 |
ISBN |
|
Medium |
|
Area |
|
Expedition |
|
Conference |
|
Notes |
LAMP; 601.240; 600.079 |
Approved |
no |
Call Number |
Admin @ si @ KBL2016 |
Serial |
2520 |
Permanent link to this record |
|
|
|
Author |
Anastasios Doulamis; Nikolaos Doulamis; Marco Bertini; Jordi Gonzalez; Thomas B. Moeslund |
Title |
Introduction to the Special Issue on the Analysis and Retrieval of Events/Actions and Workflows in Video Streams |
Type |
Journal Article |
Year |
2016 |
Publication |
Multimedia Tools and Applications |
Abbreviated Journal |
MTAP |
Volume |
75 |
Issue |
22 |
Pages |
14985-14990 |
Keywords |
|
Abstract |
|
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 |
ISE; HUPBA |
Approved |
no |
Call Number |
Admin @ si @ DDB2016 |
Serial |
2934 |
Permanent link to this record |
|
|
|
Author |
Pau Rodriguez; Miguel Angel Bautista; Sergio Escalera; Jordi Gonzalez |
Title |
Beyond Oneshot Encoding: lower dimensional target embedding |
Type |
Journal Article |
Year |
2018 |
Publication |
Image and Vision Computing |
Abbreviated Journal |
IMAVIS |
Volume |
75 |
Issue |
|
Pages |
21-31 |
Keywords |
Error correcting output codes; Output embeddings; Deep learning; Computer vision |
Abstract |
Target encoding plays a central role when learning Convolutional Neural Networks. In this realm, one-hot encoding is the most prevalent strategy due to its simplicity. However, this so widespread encoding schema assumes a flat label space, thus ignoring rich relationships existing among labels that can be exploited during training. In large-scale datasets, data does not span the full label space, but instead lies in a low-dimensional output manifold. Following this observation, we embed the targets into a low-dimensional space, drastically improving convergence speed while preserving accuracy. Our contribution is two fold: (i) We show that random projections of the label space are a valid tool to find such lower dimensional embeddings, boosting dramatically convergence rates at zero computational cost; and (ii) we propose a normalized eigenrepresentation of the class manifold that encodes the targets with minimal information loss, improving the accuracy of random projections encoding while enjoying the same convergence rates. Experiments on CIFAR-100, CUB200-2011, Imagenet, and MIT Places demonstrate that the proposed approach drastically improves convergence speed while reaching very competitive accuracy rates. |
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 |
ISE; HuPBA; 600.098; 602.133; 602.121; 600.119 |
Approved |
no |
Call Number |
Admin @ si @ RBE2018 |
Serial |
3120 |
Permanent link to this record |