Hashing with Generalized Nystr&amp;#x00F6;m Approximation

Yun, Jeong-Min; Kim, Saehoon; Choi, Seungjin

doi:10.1109/icdm.2012.22

Cited by 2 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies have disclosed that MVF is an appropriate method to analyze historic price data especially on the occasion when a variety of countries, regions and industries are examined (Pukthuanthong and Roll, 2009). Linear dimensionality reduction by means of MVF is built on leading eigenvectors of data covariance (Yun et al , 2012). If cost indices of all samples have high relevance, CCIs for a country/region can be treated as a signal based on the principle of maximum variance theory.…”

Section: Methodsmentioning

confidence: 99%

Synchronicity of global construction cost indexes

Zhang

Xing

et al. 2019

ECAM

View full text Add to dashboard Cite

Purpose The purpose of this paper is to examine the features and tendency of cost indices in the global construction setting. Design/methodology/approach Data from 22 countries/regions are collected and analyzed using maximum variance formulation and Kendall rank correlation coefficient. Findings It is found that global construction cost indexes (CCIs) have commonly maintained a steady increase for decades, and the CCIs synchronize with each other. Overall synchronicity and synchronicity of different countries pairs have increased with time significantly. Research limitations/implications The major limitation, however, is the availability of data: only 22 regions/countries are examined, the distribution of these regions/countries is imbalanced between different continents and various indices are adopted around the world, of which statistical methods are not same. Practical implications The implication is that a better perception of CCIs enables contractors to have a robust estimation for bidding prices and to improve the efficiency of construction projects management. The research findings also provide a useful reference for those countries that have not established construction cost indices databases to forecast the tendency of domestic construction industries. Originality/value This paper contributes to the overall body of knowledge by presenting the co-movement of global CCIs and measuring the changes of CCI synchronicity with time and in different countries pairs.

show abstract

Section: Methodsmentioning

confidence: 99%

Synchronicity of global construction cost indexes

Zhang

Xing

et al. 2019

ECAM

View full text Add to dashboard Cite

show abstract

“…• CIFAR [22,32]: a labeled subset of the 80 million tiny images dataset, containing 60,000 images, each described by 3072 features (a 32x32 RGB pixel image).…”

Section: Datamentioning

confidence: 99%

“…These data-independent method produce more generalized encodings, but tend to need long codes because they are randomly selected and do not con- sider the distribution of the data. In contrast, datadependent methods that consider the neighbor structure of the data points are able to obtain more compact binary codes (e.g., Restricted Boltzmann Machines (RBMs) [7], spectral hashing [5], PCA hashing [18], spherical hashing [11], kmeans-hashing [13], semi-supervised hashing [19,20], and iterative quantization [21,22]). …”

Section: Introductionmentioning

confidence: 99%

Adaptive Quantization for Hashing: An Information-Based Approach to Learning Binary Codes

Xiong¹,

Chen²,

Chen³

et al. 2014

Proceedings of the 2014 SIAM International Conference on Data Mining

View full text Add to dashboard Cite

Large-scale data mining and retrieval applications have increasingly turned to compact binary data representations as a way to achieve both fast queries and efficient data storage; many algorithms have been proposed for learning effective binary encodings. Most of these algorithms focus on learning a set of projection hyperplanes for the data and simply binarizing the result from each hyperplane, but this neglects the fact that informativeness may not be uniformly distributed across the projections. In this paper, we address this issue by proposing a novel adaptive quantization (AQ) strategy that adaptively assigns varying numbers of bits to different hyperplanes based on their information content. Our method provides an information-based schema that preserves the neighborhood structure of data points, and we jointly find the globally optimal bit-allocation for all hyperplanes. In our experiments, we compare with state-of-the-art methods on four large-scale datasets and find that our adaptive quantization approach significantly improves on traditional hashing methods.

show abstract

Hashing with Generalized Nyström Approximation

Cited by 2 publications

References 14 publications

Synchronicity of global construction cost indexes

Synchronicity of global construction cost indexes

Adaptive Quantization for Hashing: An Information-Based Approach to Learning Binary Codes

Contact Info

Product

Resources

About