Filters








298,283 Hits in 3.8 sec

On sparse evaluation representations

G. Ramalingam
2002 Theoretical Computer Science  
Second, our algorithm generates a more compact representation than the one generated by previous algorithms.  ...  The sparse evaluation graph has emerged over the past several years as an intermediate representation that captures the data ow information in a program compactly and helps perform data ow analysis e ciently  ...  Then, we can construct the sparse evaluation representation of each procedure independently, using our intraprocedural algorithm.  ... 
doi:10.1016/s0304-3975(00)00315-7 fatcat:5oittl5rprgvzht4nefvpcf2km

ERT Image Evaluation Based on Sparse Representation Algorithm

Bo Song, Pai Wang, Jaqing Li
2020 DEStech Transactions on Engineering and Technology Research  
In this paper, an adaptive sub-dictionary image evaluation algorithm based on sparse representation is used.  ...  Most of the existing image quality evaluation is to extract image features, and then use support vector regression, sparse representation and other algorithms to evaluate the image quality.  ...  In this paper, an image evaluation method based on the sparse representation adaptive sub-dictionary [4] is used to evaluate the quality of ERT images.  ... 
doi:10.12783/dtetr/mcaee2020/35026 fatcat:blf7pvfyzzb6vhv4ushgrgxzmy

Sparse Representation Based Genetic Biomarker Evaluation for Congenital Heart Defects

2016 Med One  
The proposed approach was used to evaluate 167 CHD candidate genes and was followed by validation on a microarray expression data set.  ...  Methods: We proposed a sparse representation-based variable selection (SRVS) approach to select disease-related genetic markers from a huge disease candidate gene pool acquired from ResNet relation database  ...  This study proposed a sparse representation based genetic marker selection approach, and applied it to evaluate 167 CHD candidate genes.  ... 
doi:10.20900/mo.20160016 fatcat:wmg3wu4qtbdvrky3kwu6ipurnq

Sparse Representation for Color Image Super-Resolution with Image Quality Difference Evaluation

Zi-wen WANG, Guo-rui FENG, Ling-yan FAN, Jin-wei WANG
2017 IEICE transactions on information and systems  
Based on this point, we present two sparse representation algorithms for image super-resolution, one achieves the further improvement in image quality and the other decreases running time on the basis  ...  Experimental results also show that our quantitative results on several test datasets are in line with exceptions. key words: image super-resolution, sparse representation, generalized Gaussian distribution  ...  on sparse representation.  ... 
doi:10.1587/transinf.2016edp7217 fatcat:zttkyg7d6zdupbsoez2ysgkmqa

SMALLbox - An Evaluation Framework for Sparse Representations and Dictionary Learning Algorithms [chapter]

Ivan Damnjanovic, Matthew E. P. Davies, Mark D. Plumbley
2010 Lecture Notes in Computer Science  
SMALLbox is a new foundational framework for processing signals, using adaptive sparse structured representations.  ...  As an open source MATLAB toolbox, it can be also seen as a tool for reproducible research in the sparse representations research community.  ...  The authors would also like to thank to all researchers working on the SMALL project especially Miki Elad and Pierre Vandergheynst for fruitful discussion and help in developing the SMALLbox.  ... 
doi:10.1007/978-3-642-15995-4_52 fatcat:blboliqnlbf7tnjvquuivb6iza

Massively Multilingual Sparse Word Representations

Gábor Berend
2020 International Conference on Learning Representations  
Additionally, our experiments relying on the QVEC-CCA evaluation score suggests that the proposed sparse word representations convey an increased interpretability as opposed to alternative approaches.  ...  Finally, we are releasing our multilingual sparse word representations for the 27 typologically diverse set of languages that we conducted our various experiments on.  ...  Evaluation scores for those models that are based on MAMUS representations rank second on both downstream evaluation tasks with a minor performance gap to the best results obtained by different dense representations  ... 
dblp:conf/iclr/Berend20 fatcat:zoommhwkq5db7dqw6l4mk6v2ui

Learning and Evaluating Sparse Interpretable Sentence Embeddings [article]

Valentin Trifonov, Octavian-Eugen Ganea, Anna Potapenko, Thomas Hofmann
2018 arXiv   pre-print
Previous research on word embeddings has shown that sparse representations, which can be either learned on top of existing dense embeddings or obtained through model constraints during training time, have  ...  In this paper, we transfer this idea to sentence embeddings and explore several approaches to obtain a sparse representation.  ...  However, this does not occur on all tasks: for example, SST2 and SST5 clearly benefit from a sparse representation.  ... 
arXiv:1809.08621v2 fatcat:newrr5qp3zbclg3jkobhjyqexm

A Study on Sparse Representation Model of Image Denoising Method

Qiang Zhu, Yang Chen
2015 International Journal of Signal Processing, Image Processing and Pattern Recognition  
sparse representation, the structure information of image is improved after denoising, at the same time making similar image tiles have similar sparse representation, image reconstruction effect is better  ...  denoising is a basic problem in image processing, due to the image structure has the characteristic of self-similar, using the ideas of nonlocal, this paper proposes a non-local denoising method based on  ...  Based on sparse representation model research focuses on two aspects: the sparse coding method and dictionary learning method.  ... 
doi:10.14257/ijsip.2015.8.10.01 fatcat:zujee5tuqfb3xg7ny2p7itfmrq

Visual Tracking Based on Reversed Sparse Representation

Wenhui Dong
2014 International Journal of Signal Processing, Image Processing and Pattern Recognition  
In this paper, we propose a fast and robust tracking method based on reversed sparse representation.  ...  Be different from other sparse representation based visual tracking methods, the target template is sparsely represented by the candidate particles which are gotten by particle filter.  ...  Evaluation the Time Cost of the Trackers In this experiment, we evaluate the time cost of the L1 tracker and the proposed tracker. The two trackers are both based on spare representation.  ... 
doi:10.14257/ijsip.2014.7.5.08 fatcat:ri5huwxslrcjxju5v4ar6i363e

Robust Visual Object Tracking via Sparse Representation and Reconstruction [chapter]

Zhenjun Han, Qixiang Ye, Jianbin Jiao
2013 Lecture Notes in Computer Science  
And the sparse representation and reconstruction (SR 2 ) are integrated into a Kalman filter framework to form a robust object tracker named as SR 2 KF tracker.  ...  To address these challenges, this paper proposes a new approach for robust visual object tracking via sparse representation and reconstruction, where two main contributions are devoted in terms of object  ...  Evaluation on the Appearances Variation The average and variance of DER were used to validate the effectiveness of the sparse representation against other two representative feature representation methods  ... 
doi:10.1007/978-3-642-40246-3_35 fatcat:3nq7asro7bdx7ayngndel3jugy

Contextual Bandits with Sparse Data in Web setting [article]

Björn H Eriksson
2021 arXiv   pre-print
The identified methods are policy evaluation (off-line and on-line) , hybrid-method, model representation (clusters and deep neural networks), dimensionality reduction, and simulation.  ...  In addition, each method has multiple techniques to choose from for future evaluation. The problem areas are also mentioned that each article covers.  ...  These are: Off-line policy evaluation, on-line policy evaluation, hybrid method, model representation using clusters, model representation using Deep Neural Networks, dimensionality reduction and simulations  ... 
arXiv:2105.02873v1 fatcat:ewa5c6ag35edppez72kzx2meuu

Learning and Evaluating Sparse Interpretable Sentence Embeddings

Valentin Trifonov, Octavian-Eugen Ganea, Anna Potapenko, Thomas Hofmann
2018 Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP  
Previous research on word embeddings has shown that sparse representations, which can be either learned on top of existing dense embeddings or obtained through model constraints during training time, have  ...  In this paper, we transfer this idea to sentence embeddings and explore several approaches to obtain a sparse representation.  ...  However, this does not occur on all tasks: for example, SST2 and SST5 clearly benefit from a sparse representation.  ... 
doi:10.18653/v1/w18-5422 dblp:conf/emnlp/TrifonovGPH18 fatcat:d5sws3e26jhzllgqb33hlgucau

Using Sparse Semantic Embeddings Learned from Multimodal Text and Image Data to Model Human Conceptual Knowledge [article]

Steven Derby and Paul Miller and Brian Murphy and Barry Devereux
2018 arXiv   pre-print
In this paper, we combine multimodal information from both text and image-based representations derived from state-of-the-art distributional models to produce sparse, interpretable vectors using Joint  ...  Non-Negative Sparse Embedding.  ...  We would also like to thank Alona Fyshe for providing the Joint Non-Negative Sparse Embedding code.  ... 
arXiv:1809.02534v3 fatcat:nbclpylzkzb7fgfa7kt6kr2qzu

Improved Image Fusion Method Based on Sparse Decomposition

Xiaomei Qin, Yuxi Ban, Peng Wu, Bo Yang, Shan Liu, Lirong Yin, Mingzhe Liu, Wenfeng Zheng
2022 Electronics  
We proposed a new multi-focus image fusion method based on sparse representation (DWT-SR).  ...  It also solves the problem that dictionary training sparse approximation takes a long time.  ...  The fusion method based on sparse representation realizes the matching of sparse matrix and features through dictionary learning and obtains a more meaningful representation of the source image.  ... 
doi:10.3390/electronics11152321 fatcat:tc3wmtw6b5ec3azm3ldtuozaqu

Transformation of Dense and Sparse Text Representations [article]

Wenpeng Hu, Mengyu Wang, Bing Liu, Feng Ji, Haiqing Chen, Dongyan Zhao, Jinwen Ma, Rui Yan
2019 arXiv   pre-print
Most NLP research progresses in recent years are based on dense representations. Thus the desirable property of sparsity cannot be leveraged.  ...  Then some useful operations in the sparse space can be performed over the sparse representations, and the sparse representations can be used directly to perform downstream tasks such as text classification  ...  Sparsity is evaluated using the following Sparse Evaluation (SE) function.  ... 
arXiv:1911.02914v1 fatcat:y7p2cqudsrhsbgd22xlwiitvna
« Previous Showing results 1 — 15 out of 298,283 results