Filters








8,519 Hits in 3.2 sec

Sparse Coding and Dictionary Learning with Linear Dynamical Systems

Wenbing Huang, Fuchun Sun, Lele Cao, Deli Zhao, Huaping Liu, Mehrtash Harandi
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Linear Dynamical Systems (LDSs) are the fundamental tools for encoding spatio-temporal data in various disciplines.  ...  Then, we propose an efficient method to learn the system parameters of the dictionary atoms explicitly, by imposing the symmetric constraint to the transition matrices of the data and dictionary systems  ...  The codes of training and testing systems with respect to the learned dictionary are fed to a linear SVM [14] for classification. Learning effectiveness analysis.  ... 
doi:10.1109/cvpr.2016.427 dblp:conf/cvpr/HuangSCZLH16 fatcat:igckwxidtbhytdnrix353dik5y

Equiangular Kernel Dictionary Learning with Applications to Dynamic Texture Analysis

Yuhui Quan, Chenglong Bao, Hui Ji
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Ghanem and N. Ahuja. Sparse coding of linear dynamical systems [39] X. Wei, H. Shen, and M. Kleinsteuber.  ...  The proposed kernel sparse coding 25].The basic idea of kernel sparse coding is linearizing the method is applied to dynamic texture analysis with both lo- nonlinear patterns existing in data  ... 
doi:10.1109/cvpr.2016.40 dblp:conf/cvpr/QuanBJ16 fatcat:jqxuen27izeqjewq4ai2cngy7u

Unsupervised Temporal Feature Learning Based on Sparse Coding Embedded BoAW for Acoustic Event Recognition

Liwen Zhang, Jiqing Han, Shiwen Deng
2018 Interspeech 2018  
The performance of an Acoustic Event Recognition (AER) system highly depends on the statistical information and the temporal dynamics in the audio signals.  ...  In this paper, we proposed a novel unsupervised temporal feature learning method, which can effectively capture the temporal dynamics for an entire audio signal with arbitrary duration by building direct  ...  Hence, the sparse coding can effectively improve our system with much smaller dictionary size.  ... 
doi:10.21437/interspeech.2018-1243 dblp:conf/interspeech/ZhangHD18 fatcat:aydiltvs65ek3os5ptzeszdsma

Towards Motion Aware Light Field Video for Dynamic Scenes

Salil Tambe, Ashok Veeraraghavan, Amit Agrawal
2013 2013 IEEE International Conference on Computer Vision  
The key idea is (a) to design efficient multiplexing matrices that allow resolution tradeoffs, (b) use dictionary learning and sparse representations for robust reconstruction, and (c) perform local motion-aware  ...  Our reconstruction is motion-aware and offers a continuum of resolution tradeoff with increasing motion in the scene.  ...  Acknowledgements S.T and A.V were supported by NSF Grants NSF-IIS:1116718, NSF-CCF:1117939 and by funding from a Samsung GRO research award.  ... 
doi:10.1109/iccv.2013.129 dblp:conf/iccv/TambeVA13 fatcat:ucib636dbnej5ko452pjgvm7vu

On the Sparse Structure of Natural Sounds and Natural Images: Similarities, Differences, and Implications for Neural Coding

Eric McVoy Dodds, Michael Robert DeWeese
2019 Frontiers in Computational Neuroscience  
Sparse coding models of natural images and sounds have been able to predict several response properties of neurons in the visual and auditory systems.  ...  In particular, a sparse coding network with synaptically local plasticity rules learns different sparse features from speech data than are found by more conventional sparse coding algorithms, but the learned  ...  We especially thank Joel Zylberberg, Nicole Carlson, and Jesse Livezey for providing code used in our preprocessing, and Bruno Olshausen for providing whitened image data and for code that guided our LCA  ... 
doi:10.3389/fncom.2019.00039 pmid:31293408 pmcid:PMC6606779 fatcat:7n7sxvxlbnc2jiipk7u26fwfci

Extrinsic Methods for Coding and Dictionary Learning on Grassmann Manifolds [article]

Mehrtash Harandi, Richard Hartley, Chunhua Shen, Brian Lovell, Conrad Sanderson
2015 arXiv   pre-print
With the aim of building a bridge between the two realms, we address the problem of sparse coding and dictionary learning over the space of linear subspaces, which form Riemannian structures known as Grassmann  ...  Lastly, to handle non-linearity in data, we extend the proposed Grassmann sparse coding and dictionary learning algorithms through embedding into Hilbert spaces.  ...  Acknowledgements NICTA is funded by the Australian Government as represented by the Department of Broadband, Communications and the Digital Economy, as well as the Australian Research Council through the  ... 
arXiv:1401.8126v2 fatcat:vojc4cwe7fgyxkzvajr5hcsiwq

An Adaptive Dictionary Learning Approach for Modeling Dynamical Textures [article]

Xian Wei, Hao Shen, Martin Kleinsteuber
2013 arXiv   pre-print
We propose a sparse coding framework, named adaptive video dictionary learning (AVDL), to model a video adaptively.  ...  Video representation is an important and challenging task in the computer vision community. In this paper, we assume that image frames of a moving scene can be modeled as a Linear Dynamical System.  ...  ADAPTIVE VIDEO DICTIONARY LEARNING In this section, we start with a brief introduction to the linear dynamical systems (LDS) model and develop an adaptive dictionary learning framework for sparse coding  ... 
arXiv:1312.5568v1 fatcat:ugixfanrqbddjonnxfnrk7bhci

Extrinsic Methods for Coding and Dictionary Learning on Grassmann Manifolds

Mehrtash Harandi, Richard Hartley, Chunhua Shen, Brian Lovell, Conrad Sanderson
2015 International Journal of Computer Vision  
With the aim of building a bridge between the two realms, we address the problem of sparse coding and dictionary learning in Grassmann manifolds, i.e., the space of linear subspaces.  ...  Lastly, to handle non-linearity in data, we extend the proposed Grassmann sparse coding and dictionary learning algorithms through embedding into higher dimensional Hilbert spaces.  ...  Acknowledgements NICTA is funded by the Australian Government as represented by the Department of Broadband, Communications and the Digital Economy, as well as the Australian Research Council through the  ... 
doi:10.1007/s11263-015-0833-x fatcat:zarnbfkt4zcmvbncljoat4k6u4

Motion Detection Algorithm for Unmanned Aerial Vehicle Nighttime Surveillance

Huaxin XIAO, Yu LIU, Wei WANG, Maojun ZHANG
2014 IEICE transactions on information and systems  
A universal dictionary for arbitrary scenes is presented. Realistic and synthetic experiments demonstrate the robustness of the proposed approach.  ...  In consideration of the image noise captured by photoelectric cameras at nighttime, a robust motion detection algorithm based on sparse representation is proposed in this study.  ...  The proposed approach regards the process of motion detection as a sparse representation problem and employs dictionary learning and sparse coding.  ... 
doi:10.1587/transinf.2014edl8129 fatcat:htvsrwk7xjbrdmruwhm73pwbcq

Dictionary learning based image enhancement for rarity detection [article]

Hui Li, Xiaomeng Wang, Weifeng Liu, Yanjiang Wang
2016 arXiv   pre-print
Firstly, learn the dictionary through sparse coding algorithms on divided sub-image blocks. Secondly, compute the rarity of dictionary atoms on statistics of the corresponding sparse coefficients.  ...  Thirdly, adjust the rarity according to specific application and form a new dictionary. Finally, reconstruct the image using the updated dictionary and sparse coefficients.  ...  corresponding dictionary are learned by sparse coding theory [13] - [14] . ) , 2 , 1 ( 1 N i R y n i !  ... 
arXiv:1305.0871v2 fatcat:zzyxu6pvmzepnmvgmsu6ysqawy

An adaptive dictionary learning approach for modeling dynamical textures

Xian Wei, Hao Shen, Martin Kleinsteuber
2014 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
We propose a sparse coding framework, named adaptive video dictionary learning (AVDL), to model a video adaptively.  ...  The developed framework is able to capture the dynamics of a moving scene by exploring both sparse properties and the temporal correlations of consecutive video frames.  ...  ADAPTIVE VIDEO DICTIONARY LEARNING In this section, we start with a brief introduction to the linear dynamical systems (LDS) model and develop an adaptive dictionary learning framework for sparse coding  ... 
doi:10.1109/icassp.2014.6854265 dblp:conf/icassp/WeiSK14 fatcat:hqftas5op5g6nbz7g6rr3vd7wu

Role of Homeostasis in Learning Sparse Representations

Laurent U. Perrinet
2010 Neural Computation  
Indeed, different models of sparse coding, coupled with Hebbian learning and homeostasis, have been proposed that successfully match the observed emergent response.  ...  We apply this homeostasis while learning small patches taken from natural images and compare its efficiency with state-of-the-art algorithms.  ...  Special thanks to Bruno Olshausen, Laura Rebollo-Neira, Gabriel Peyré, Martin Rehn and Fritz Sommer for providing the source code for their experiments.  ... 
doi:10.1162/neco.2010.05-08-795 pmid:20235818 pmcid:PMC2929690 fatcat:3vjq4ezpenaclj6g6rfvyz4iv4

Video from a single coded exposure photograph using a learned over-complete dictionary

Yasunobu Hitomi, Jinwei Gu, Mohit Gupta, Tomoo Mitsunaga, Shree K. Nayar
2011 2011 International Conference on Computer Vision  
Our approach has two important distinctions compared to previous works: (1) we achieve sparse representation of videos by learning an over-complete dictionary on video patches, and (2) we adhere to practical  ...  To demonstrate the power of our approach, we have implemented a prototype imaging system with per-pixel coded exposure control using a liquid crystal on silicon (LCoS) device.  ...  Acknowledgments: This research was supported in parts by Sony Corporation, NSF (grant number IIS 09-64429) and ONR (grant number N00014-08-1-0638).  ... 
doi:10.1109/iccv.2011.6126254 dblp:conf/iccv/HitomiGGMN11 fatcat:fyn3lox5mfc75bkmjor2aq75ki

A Evaluation on Removing of Rain from Images

2019 International Journal of Engineering and Advanced Technology  
A rain removal technique has wide applications in indoor and outdoor security surveillance systems, tracking and navigation, entertainment industries and consumer electronics.  ...  Here merits and demerits of existing methods are discussed, which motivates further research.  ...  By learning a dictionary with mutual exclusivity, the de rained image layer and the rain layer can be accurately separated using sparse coding with high discriminability.  ... 
doi:10.35940/ijeat.f1180.0886s19 fatcat:mebh6epwevb7pk7tpdrsukd4o4

Learning and Inference in Sparse Coding Models with Langevin Dynamics [article]

Michael Y.-S. Fang, Mayur Mudigonda, Ryan Zarcone, Amir Khosrowshahi, Bruno A. Olshausen
2022 arXiv   pre-print
We describe a stochastic, dynamical system capable of inference and learning in a probabilistic latent variable model.  ...  Simulations of the proposed dynamical system on both synthetic and natural image datasets demonstrate that the model is capable of probabilistically correct inference, enabling learning of the dictionary  ...  Next, we introduce simultaneous-update sparse coding (SSC) in which dictionary updates are made continuously and concurrent with the dynamics of the coefficients.  ... 
arXiv:2204.11150v1 fatcat:dmpvqlfjbndc7bruxb4hcr4evq
« Previous Showing results 1 — 15 out of 8,519 results