Permalink
Cannot retrieve contributors at this time
Name already in use
A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
TTNPE/Readme.rtf
Go to fileThis commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
32 lines (29 sloc)
2.28 KB
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{\rtf1\ansi\ansicpg1252\cocoartf1671\cocoasubrtf600 | |
{\fonttbl\f0\fnil\fcharset0 HelveticaNeue;} | |
{\colortbl;\red255\green255\blue255;\red27\green31\blue34;\red255\green255\blue255;\red10\green77\blue204; | |
\red218\green221\blue226;} | |
{\*\expandedcolortbl;;\cssrgb\c14118\c16078\c18039;\cssrgb\c100000\c100000\c100000;\cssrgb\c1176\c40000\c83922; | |
\cssrgb\c88235\c89412\c90980;} | |
\margl1440\margr1440\vieww10800\viewh8400\viewkind0 | |
\deftab720 | |
\pard\pardeftab720\sl360\sa320\partightenfactor0 | |
\f0\fs32 \cf2 \cb3 \expnd0\expndtw0\kerning0 | |
\outl0\strokewidth0 \strokec2 This is the demo code for paper "Tensor Train Neighborhood Preserving Embedding"\ | |
\pard\pardeftab720\sl360\partightenfactor0 | |
\b\fs36 \cf4 \cb1 \strokec4 \ | |
\pard\pardeftab720\sl440\sa320\partightenfactor0 | |
\cf2 \cb3 \strokec2 Copyright @ Wenqi Wang, 2018\ | |
\pard\pardeftab720\sl360\sa320\partightenfactor0 | |
\b0\fs32 \cf2 To run the experiment Fig.3 and Fig.6 of the paper Tensor Train Neighborhood Preserving Embedding\ | |
(1) Data processing: download Weizmann Dataset from\'a0{\field{\*\fldinst{HYPERLINK "http://www.wisdom.weizmann.ac.il/~/vision/FaceBase/"}}{\fldrslt \cf4 \strokec4 http://www.wisdom.weizmann.ac.il/~/vision/FaceBase/}}\'a0and build a tensor named 'Data' with dimension 512 x 352 x 66 x 17, which represents 66 images of size 512 x 352 from 17 persons. Save it with name 'WeizmanData.mat' and put it in the folder Data_file.\ | |
(1) run demo.m for NPE algortihm comparision among KNN, TNPE and TTNPE\ | |
(2) The TTNPE-ATN is the implemented in the code Self_Tool/main_App.m. Please refer this function and the folder TT_Approximate for the detail implementation of the algorithm.\ | |
\pard\pardeftab720\sl360\sa480\partightenfactor0 | |
\cf2 \cb5 \ | |
\pard\pardeftab720\sl360\sa320\partightenfactor0 | |
\cf2 \cb3 Terms of use:\ | |
The code is provided for research purpose only without any warranty. Any commercial use if prohibited\ | |
When using the code, please cite the following paper:\ | |
Tensor Train Neighborhood Preserving Embedding Wenqi Wang, Vaneet Aggarwal, and Shuchin Aeron IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2018, pp. 2724-2732\ | |
Available:\'a0{\field{\*\fldinst{HYPERLINK "https://ieeexplore.ieee.org/document/8319501/?arnumber=8319501&source=authoralert"}}{\fldrslt \cf4 \strokec4 https://ieeexplore.ieee.org/document/8319501/?arnumber=8319501&source=authoralert}}\ | |
} |