toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
  Records Links
Author Miguel Angel Bautista; Oriol Pujol; Fernando De la Torre; Sergio Escalera edit   pdf
url  doi
openurl 
  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 (up) 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;MILAB Approved no  
  Call Number Admin @ si @ BPT2018 Serial 3015  
Permanent link to this record
 

 
Author Huamin Ren; Nattiya Kanhabua; Andreas Mogelmose; Weifeng Liu; Kaustubh Kulkarni; Sergio Escalera; Xavier Baro; Thomas B. Moeslund edit  url
doi  openurl
  Title Back-dropout Transfer Learning for Action Recognition Type Journal Article
  Year 2018 Publication IET Computer Vision Abbreviated Journal IETCV  
  Volume 12 Issue 4 Pages 484-491  
  Keywords Learning (artificial intelligence); Pattern Recognition  
  Abstract Transfer learning aims at adapting a model learned from source dataset to target dataset. It is a beneficial approach especially when annotating on the target dataset is expensive or infeasible. Transfer learning has demonstrated its powerful learning capabilities in various vision tasks. Despite transfer learning being a promising approach, it is still an open question how to adapt the model learned from the source dataset to the target dataset. One big challenge is to prevent the impact of category bias on classification performance. Dataset bias exists when two images from the same category, but from different datasets, are not classified as the same. To address this problem, a transfer learning algorithm has been proposed, called negative back-dropout transfer learning (NB-TL), which utilizes images that have been misclassified and further performs back-dropout strategy on them to penalize errors. Experimental results demonstrate the effectiveness of the proposed algorithm. In particular, the authors evaluate the performance of the proposed NB-TL algorithm on UCF 101 action recognition dataset, achieving 88.9% recognition rate.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication (up) 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;MV;OR;MILAB Approved no  
  Call Number Admin @ si @ RKM2018 Serial 3071  
Permanent link to this record
 

 
Author Mark Philip Philipsen; Jacob Velling Dueholm; Anders Jorgensen; Sergio Escalera; Thomas B. Moeslund edit  doi
openurl 
  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 (up) 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;MILAB Approved no  
  Call Number Admin @ si @ PVJ2018 Serial 3072  
Permanent link to this record
 

 
Author Mohamed Ilyes Lakhal; Hakan Çevikalp; Sergio Escalera; Ferda Ofli edit  doi
openurl 
  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 (up) 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;MILAB Approved no  
  Call Number Admin @ si @ LÇE2018 Serial 3119  
Permanent link to this record
 

 
Author Pau Rodriguez; Miguel Angel Bautista; Sergio Escalera; Jordi Gonzalez edit   pdf
url  doi
openurl 
  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 (up) 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;MILAB Approved no  
  Call Number Admin @ si @ RBE2018 Serial 3120  
Permanent link to this record
Select All    Deselect All
 |   | 
Details

Save Citations:
Export Records: