A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL.
The file type is application/pdf.
Filters
Second Order Bilinear Discriminant Analysis for single trial EEG analysis
2007
Neural Information Processing Systems
Preserved Fulltext
Here we propose a principled method, based on a bilinear model, in which the algorithm simultaneously learns the best first and second order spatial and temporal features for classification of EEG. ...
for classification, e.g. event related potentials; and second order methods, in which the feature of interest is the power of the signal, e.g. event related (de)synchronization. ...
Second order bilinear discriminant analysis 2.1 Problem setting
Given a set of sample points D = {X n , y n } N n=1 , X ∈ R D × T , y ∈ {−1, 1} , where X n corresponds to the EEG signal of D channels ...
dblp:conf/nips/ChristoforouSP07
fatcat:vvau5oceune6vfcd6akojyhtbm
Second-order properties for multiple-bilinear models
1990
Journal of Multivariate Analysis
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 exact form of the spectral density function shows that there is no way one can discriminate between a linear (non-Gaussian) and a bilinear model based on the second-order properties of the process. ...
We give a necessary and sufficient condition for the second-order stationarity of multiple bilinear models in terms of the spectral radius of a particular matrix involving the coefficients of the model ...
An easy consequence of these formulae is that there is no way one would discriminate between the linear (D,=O, j = 1, 2, . ..) d) non-Gaussian and the bilinear process on the basis of the second-order ...
doi:10.1016/0047-259x(90)90030-l
fatcat:muyf3s3gk5c37k2gqj5txviph4
Multimodal Bilinear Fusion Network with Second-order Attention Based Channel Selection for Land Cover Classification
2020
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
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.
The MBFNet consists of three components: the feature extractor, the second-order attention-based channel selection module (SACSM), and the bilinear fusion module. ...
Then, the SACSM is embedded into each stream, and the fine channel-attention maps with second-order statistics are obtained by bilinear integrating the global averagepooling and global max-pooling information ...
However, the channel attention maps of CBAM lacked more discriminative second-order statistics. ...
doi:10.1109/jstars.2020.2975252
fatcat:kybbaqqdavgljnnce2tgvmyhm4
Compact Bilinear Pooling
[article]
2016
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
However, bilinear features are high dimensional, typically on the order of hundreds of thousands to a few million, which makes them impractical for subsequent analysis. ...
The compact bilinear representations are derived through a novel kernelized analysis of bilinear pooling which provide insights into the discriminative power of bilinear pooling, and a platform for further ...
Bilinear pooling thus gives a linear classifier the discriminative power of a second order kernel-machine, which may help explain the strong empirical performance observed in previous work [23, 3, 8, ...
arXiv:1511.06062v2
fatcat:eithehndyjdcdfwk5o2urvx6qq
Compact Bilinear Pooling
2016
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
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 2016; you can also visit the original URL.
The file type is application/pdf.
However, bilinear features are high dimensional, typically on the order of hundreds of thousands to a few million, which makes them impractical for subsequent analysis. ...
The compact bilinear representations are derived through a novel kernelized analysis of bilinear pooling which provide insights into the discriminative power of bilinear pooling, and a platform for further ...
Bilinear pooling thus gives a linear classifier the discriminative power of a second order kernel-machine, which may help explain the strong empirical performance observed in previous work [23, 3, 8, ...
doi:10.1109/cvpr.2016.41
dblp:conf/cvpr/GaoBZD16
fatcat:ik3q4hhngbf5nkwrsqt5u4bxza
Face Recognition Using Modular Bilinear Discriminant Analysis
[chapter]
2006
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.
In this paper, we present a new approach for face recognition, named Modular Bilinear Discriminant Analysis (MBDA). ...
In a first step, a set of experts is created, each one being trained independently on specific face regions using a new supervised technique named Bilinear Discriminant Analysis (BDA). ...
We therefore propose an iterative procedure that we call Bilinear Discriminant Analysis. ...
doi:10.1007/11590064_3
fatcat:lqssjrudqnfwxmmmdmriduu2xu
Multi-Objective Matrix Normalization for Fine-grained Visual Recognition
2020
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 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2003.13272v1 fatcat:6j6nqyipj5gcri7dyhs2r5ychyOther Versions
These three regularizers can not only stabilize the second-order information, but also compact the bilinear features and promote model generalization. ...
Recent methods have shown that the matrix power normalization can stabilize the second-order information in bilinear features, but some problems, e.g., redundant information and over-fitting, remain to ...
Inspired by the second-order descriptors, the bilinear pooling is first proposed by Lin et al. [7] to capture the second-order information for FGVC. ...
doi:10.1109/tip.2020.2977457
pmid:32149637
fatcat:w5syyp7emnhxfp63yydnar3v5q
Page 5855 of Mathematical Reviews Vol. , Issue 87j
[page]
1987
Mathematical Reviews
Preserved Fulltext
The Internet Archive has digitized a microfilm copy of this work. It may be possible to borrow a copy for reading.
However, in this paper it is shown that some of the third-order moments do not vanish for some superdiagonal and diagonal bilinear models and the pattern of nonzero moments can be used to discriminate ...
for some bilinear models they will all be zero, and hence are of no use in discriminating between true white noise and some bilinear models. ...
Correlation Codes in Neuronal Populations
2001
Neural Information Processing Systems
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 2016; you can also visit the original URL.
The file type is application/pdf.
Here we study the efficiency of coding information in the second order statistics of the population responses. ...
We propose a bilinear readout model for extracting information from correlation codes, and evaluate its performance in discrimination and estimation tasks. ...
Secondly, we inquire how information in the second order statistics can be efficiently extracted. ...
dblp:conf/nips/ShamirS01
fatcat:hkxmxtqujba3zjwgaghzdxpbba
The Analytic Bilinear Discrimination of Single-Trial EEG Signals in Rapid Image Triage
2014
PLoS ONE
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.
Being a first-order discriminator, LDA is usually preceded by the feature extraction of electroencephalogram (EEG) signals, as multi-density EEG data are of second order. ...
The linear discriminant analysis (LDA) method is a classical and commonly utilized technique for dimensionality reduction and classification in brain-computer interface (BCI) systems. ...
On the other hand, bilinear discriminant analysis (BDA) [32] and 2-dimensional linear discriminant analysis (2DLDA) [33] extend LDA by iteratively optimizing bilinear projections instead of one LDA ...
doi:10.1371/journal.pone.0100097
pmid:24933017
pmcid:PMC4059712
fatcat:gfulifj7mbbxdm2ke2slb64efa
Bilinear image translation for temporal analysis of photo collections
2019
IEEE Transactions on Pattern Analysis and Machine Intelligence
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.
To isolate and transfer time dependent appearance variations, we introduce a new trainable bilinear factor separation module. ...
Others have looked at identifying parts of images that are temporally discriminative in order to date historical objects in photographs [39] . ...
The second term encourages that for the generated images M (I, y) the discriminator output for period y, D y should be zero. ...
doi:10.1109/tpami.2019.2950317
pmid:31675318
fatcat:tl3l3w2aqvb4ff5ifnyudxyj5a
Temporal Attention augmented Bilinear Network for Financial Time-Series Data Analysis
[article]
2017
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.
The resulting network is highly interpretable, given its ability to highlight the importance and contribution of each temporal instance, thus allowing further analysis on the time instances of interest ...
In this paper, we propose a neural network layer architecture that incorporates the idea of bilinear projection as well as an attention mechanism that enables the layer to detect and focus on crucial temporal ...
For example, popular discriminant and regression criteria were extended for tensor inputs, such as Multilinear Discriminant Analysis (MDA) [41] , Multilinear Class-specific Discriminant Analysis (MCSDA ...
arXiv:1712.00975v1
fatcat:vqgcwtk5fndijmvi7hoxglybyi
A Vehicle Detection Algorithm Based on Deep Belief Network
2014
The Scientific World Journal
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 the algorithm, the proposed 2D-DBN architecture uses second-order planes instead of first-order vector as input and uses bilinear projection for retaining discriminative information so as to determine ...
The bilinear projection maps original second-order output of lower layer to a small bilinear space without reducing discriminative information. ...
In the algorithm, the proposed 2D-DBN architecture uses second-order planes instead of first-order vector as input and uses bilinear projection for retaining discriminative information so as to determine ...
doi:10.1155/2014/647380
pmid:24959617
pmcid:PMC4052056
fatcat:kb3m3v6aorghjmlaxccsqkzy3i
Bilinear Discriminant Analysis for Face Recognition
[chapter]
2005
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.
In this paper, a new statistical projection method called Bilinear Discriminant Analysis (BDA) is presented. ...
Linear Discriminant Analysis (RoLDA), through an iterative algorithm using a generalized bilinear projectionbased Fisher criterion. ...
We therefore propose an iterative procedure that we call Bilinear Discriminant Analysis. ...
doi:10.1007/11552499_28
fatcat:govndsb5tba4todowipm2ord3e
Aircraft Type Recognition in Remote Sensing Images: Bilinear Discriminative Extreme Learning Machine Framework
2021
Electronics
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 2021; you can also visit the original URL.
The file type is application/pdf.
To solve the above problems, we propose the bilinear discriminative extreme learning machine (ELM) network (BD-ELMNet), which integrates the advantages of the CNN, autoencoder (AE), and ELM. ...
The bilinear pooling model uses the feature association information for feature fusion to enhance the substantial distinction of features. ...
In the high-order feature extraction module, the bilinear pool model is used as the high-order feature extractor of the BD-ELMNet, which extracts second-order statistical information by calculating the ...
doi:10.3390/electronics10172046
fatcat:nl32ybgumra4bk6qs4uyirisja
« Previous
Showing results 1 — 15 out of 14,109 results