A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Sparse Online Learning of Image Similarity
2017
ACM Transactions on Intelligent Systems and Technology
Preserved Fulltext
scheme of Sparse Online Learning of Image Similarity (SOLIS). ...
In contrast to many existing image-similarity learning algorithms that are designed to work with low-dimensional data, SOLIS is able to learn image similarity from large-scale image data in sparse and ...
In summary, these are the main contributions of this article: -We present a novel framework of Sparse Online Learning of Image Similarity (SOLIS) for learning sparse similarity functions from large-scale ...
doi:10.1145/3065950
fatcat:j7ay74yywzbdnigskt42fiqhpy
SOML: Sparse Online Metric Learning with Application to Image Retrieval
2014
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
In thispaper, we propose a novel Sparse Online Metric Learning (SOML)scheme for learning sparse distance functions from large-scalehigh-dimensional data and explore its application to imageretrieval. ...
Image similarity search plays a key role in many multimediaapplications, where multimedia data (such as images and videos) areusually represented in high-dimensional feature space. ...
Sparse Online Metric Learning Problem Formulation We address the fundamental problem of distance metric learning from side information (pairwise or triplet image relationship) towards image retrieval applications ...
doi:10.1609/aaai.v28i1.8911
fatcat:a523gi4iubejdopb7maf4mgfza
Sparse Online Relative Similarity Learning
2015
2015 IEEE International Conference on Data Mining
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Most of the existing similarity learning algorithms are online similarity learning method, since online learning is more scalable than offline learning. ...
To solve this issue, we introduce several Sparse Online Relative Similarity (SORS) learning algorithms, which learn a sparse model during the learning process, so that the memory and computational cost ...
The proposed online learning scheme is close to the recent work of scalable image similarity learning (OASIS) [13] , [14] . ...
doi:10.1109/icdm.2015.100
dblp:conf/icdm/YaoZYJL15
fatcat:rlb3cha2ujhv7grqw3ylj7jhaq
Sparse Spatial Coding: A novel approach for efficient and accurate object recognition
2012
2012 IEEE International Conference on Robotics and Automation
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We overcome the problem of techniques which make use of sparse representation alone by generating the final representation with SSC and max pooling, presented for an online learning classifier. ...
However, one serious drawback of sparse space based methods is that similar local features can be quantized into different visual words. ...
Furthermore, the combination of sparse coding and locality with the correct online learning method can produce superior results.
A. ...
doi:10.1109/icra.2012.6224785
dblp:conf/icra/OliveiraNVC12
fatcat:hzcavzeznjaobkzlqa6ob4pnca
Online Representation Learning with Single and Multi-layer Hebbian Networks for Image Classification
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
These have been shown to perform sparse representation learning. This study tests the effectiveness of one such learning rule for learning features from images. ...
The algorithm performs well in comparison to other unsupervised learning algorithms and multi-layer networks, thus suggesting its validity in the design of a new class of compact, online learning networks ...
It is not obvious a priori that the online optimisation of a cost-function for sparse similarity matching (Eq.2) produces features suitable for image classification. ...
arXiv:1702.06456v3
fatcat:dugfqrn2prdhbaywjdcqnnfrpm
Transferring Visual Prior for Online Object Tracking
2012
IEEE Transactions on Image Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
From a collection of realworld images, we learn an overcomplete dictionary to represent visual prior. ...
The prior knowledge of objects is generic, and the training image set does not necessarily contain any observation of the target object. ...
Wang was a visiting student at the University of California at Merced. ...
doi:10.1109/tip.2012.2190085
pmid:22491081
fatcat:obwthxkxqvag5eo6rwtqsaqpp4
Online dictionary learning algorithm with periodic updates and its application to image denoising
2014
Expert systems with applications
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
The performance of the proposed DLAs in synthetic dictionary learning and image denoising settings demonstrates that the coecient update procedure improves the dictionary learning ability. ...
Secondly, we present a periodically coecient updated version of the online Recursive Least Squares (RLS)-DLA, where the data is used sequentially to gradually improve the learned dictionary. ...
The RLS approach has also been used for sparse adaptive ltering in recent studies [19, 20] . Another online DLA is the Online Dictionary Learning (ODL) algorithm of [21] . ...
doi:10.1016/j.eswa.2013.11.036
fatcat:l36mfcfz3zh3hm356h4tvhzque
Stochastic Convolutional Sparse Coding
2019
International Symposium on Vision, Modeling, and Visualization
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
learned image features. ...
Finally, we evaluate the effectiveness of the over-complete dictionary learned from large-scale datasets, which demonstrates an improved sparse representation of the natural images on account of more abundant ...
Acknowledgements This work was supported by King Abdullah University of Science and Technology as part of VCC center baseline funding. ...
doi:10.2312/vmv.20191317
dblp:conf/vmv/XiongRH19
fatcat:p4b3zg2nwjhafmesc5laxiwzta
Stochastic Convolutional Sparse Coding
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
learned image features. ...
Finally, we evaluate the effectiveness of the over-complete dictionary learned from large-scale datasets, which demonstrates an improved sparse representation of the natural images on account of more abundant ...
Later on, online learning strategies were synergetic with sparse cod-ing, which was then scaled up for learning dictionary from millions of training samples [MBPS09, MBPS10] , and for large-scale matrix ...
arXiv:1909.00145v1
fatcat:yhpv2eugl5bzno77hskau467eq
Online Representation Learning with Single and Multi-layer Hebbian Networks for Image Classification
[chapter]
2017
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
These have been shown to perform sparse representation learning. This study tests the effectiveness of one such learning rule for learning features from images. ...
The algorithm performs well in comparison to other unsupervised learning algorithms and multi-layer networks, thus suggesting its validity in the design of a new class of compact, online learning networks ...
It is not obvious a priori that the online optimisation of a cost-function for sparse similarity matching (Eq.2) produces features suitable for image classification. ...
doi:10.1007/978-3-319-68600-4_41
fatcat:lmkrezfembcovdtpiiwym4r5zq
Dictionary Learning in Texture Classification
[chapter]
2011
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2015; you can also visit the original URL.
The file type is application/pdf.
In this paper, online learning is used as fast implementation of sparse coding for texture classification. ...
Recently, dictionary learning and sparse coding has provided state-of-the-art results in various applications. ...
Solving (2) using one of the approaches in the literature such as online learning [12] yields the dictionary D and the sparse coefficients a. ...
doi:10.1007/978-3-642-21593-3_34
fatcat:pbnbw5sb7zbzdihppqlgjhooyu
Online Learning for Fast Segmentation of Moving Objects
[chapter]
2013
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
This work addresses the problem of fast, online segmentation of moving objects in video. ...
The computational complexity of the approach is significantly reduced by performing learning and classification on oversegmented image regions (superpixels), rather than per pixel. ...
illustrate the online learning aspect of the method. ...
doi:10.1007/978-3-642-37444-9_5
fatcat:aycqmtnpnnhtlfhwnd3wzsgvea
Shape Prior Modeling Using Sparse Representation and Online Dictionary Learning
[chapter]
2012
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
In this paper, we propose an online learning method to address these two limitations. Our method starts from constructing an initial shape dictionary using the K-SVD algorithm. ...
Instead of assuming any parametric model of shape statistics, SSC incorporates shape priors onthe-fly by approximating a shape instance (usually derived from appearance cues) by a sparse combination of ...
To tackle this problem, we employ a recently proposed online dictionary method [7] to update the shape dictionary. Algorithm 1 shows the framework of online dictionary learning for sparse coding. ...
doi:10.1007/978-3-642-33454-2_54
fatcat:jmgjlgge5vb6paenzryi2n7exy
Group-based single image super-resolution with online dictionary learning
2016
EURASIP Journal on Advances in Signal Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Unlike the traditional single image super-resolution methods such as image interpolation, the super-resolution with sparse representation reconstructs image with one or several constant dictionaries learned ...
Extensive experiments on natural images show that our method achieves better results than some state-of-the-art algorithms in terms of both objective and human visual evaluations. ...
Availability of data and materials The images supporting the conclusions of this article are available in the "Test Images of Computer Vision Group", All of the images are Copyright free. http://decsai.ugr.es ...
doi:10.1186/s13634-016-0380-9
fatcat:rh2hvujumfak5ht43jsysjb6xa
Online Learning a High-Quality Dictionary and Classifier Jointly for Multitask Object Tracking
2014
IEEE Multimedia
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
To survey many of these algorithms, we refer the reader to earlier work. [1] [2] [3] [4] In this article, we present a supervised approach to online learning and update a structured sparse and discriminative ...
This approach exploits label information strength and encourages images from the same class to have similar representations. ...
We combine the K-SVD and online dictionary learning for sparse coding methods to solve Equation 8 to obtain online learning of the compact and discriminative dictionary. ...
doi:10.1109/mmul.2014.53
fatcat:7zgen63rg5hkjm4mmeyxuylame
« Previous
Showing results 1 — 15 out of 69,969 results