My account  |  My order  |  Login   |  Register  |  View Cart (0)
Advanced search
Browse for Books
Botany
Botany: GeneralPteridophytes
FlowersMedicinal Plant
PhycologyMycology
view all 
Zoology
EntomologyInvertebrates
MolluscaOrnithology
MammalsHerpetology
view all 
Earth Science
GlaciologyGeology
ClimatologyRemote Sensing
HazardsDesert
view all 
Paleontology
GeneralVertebrate
Micropaleontolo Paleobotany
InvertebrateStratigraphy
view all 
Biology & Ecology
BiodiversityMarine Biology
BiotechnologyEnvironment
MicrobiologyBiomedicine
view all 
Sciences
Science: GeneralMathematics
ChemistryMechanics
GeographyAerospace
view all 
Technology
AgricultureForestry
Civil Engineeri Energy
MetallurgyTransportation
view all 
Social Sciences
Culture and ArtHistory
PoliticsLanguage
StatisticsEconomics
view all 
Browse History
Deep Learing in Physiological Function
Larger Image
Price: US$ 28.00
Deep Learing in Physiological Function
Language:  English
Author:  Cao Wenming & Cao Guitao
Pub. Date:  2022-10 Weight:   kg ISBN:  9787030705730
Format:  Soft Cover Pages:  208
Subject:  Sciences > System Theory
Series:   Size:  180x260 mm
                    Add Favourite
 
  • Description
  • Contents
  • Details
  • Review
  • The author

contents 
preface 
chapter 1  motion detection with skeleton tracking  1 
1.1  introduction  1 
1.1.1  fog puting-based methods for physiological function assessment  1 
1.1.2  motion detection with skeleton tracking for physiological function assessment  2 
1.2  motion detection method  3 
1.2.1  physiological function assessment based on fog puting  3 
1.2.2  motion recognition with rgb-d cameras  5 
1.3  validation for motion detection  9 
1.3.1  parison with digital angle protractor  9 
1.3.2  effect of motion detection  9 
1.3.3  effect of gait analysis  10 
1.4  3d stereo human trajectory learning and prediction  11 
1.4.1  method overview  11 
1.4.2  twin deep neural works with stereo constraint for 3d human e estimation  12 
1.4.3  constructing the forward and backward prediction works  15 
1.5  validation for 3d pedestrian trajectory prediction  17 
1.5.1  3d pedestrian trajectory dataset  17 
1.5.2  evaluation metrics and protocol  17 
1.5.3  performance evaluations and parison  18 
1.6  conclusions  19 
references  19
chapter 2  fa expression and emotion recognition  22 
2.1  introduction  22 
2.2  methodologies  23 
2.2.1  patch manifold  23 
2.2.2  patch discriminative analysis  24 
2.2.3  optimization  25 
2.3  patch discriminative analysis work  27 
2.4  fa expression recognition validation  28 
2.5  methodologies based on lmdap  30 
2.5.1  discriminant embed space  30 
2.5.2  convolutional kernel learning based on the proed lmdap algorithm  32 
2.5.3  local manifold discriminant analysis projections work  36 
2.6  validation for method based on lmdap  37 
2.6.1  datasets  37 
2.6.2  parameter setting  38 
2.6.3  face recognition experiments on extended yale b dataset  39 
2.6.4  face recognition experiments on ar dataset  40 
2.6.5  face recognition experiments on feret dataset  41 
2.6.6  face verification: ytf  42 
2.6.7  impact of parameters  42 
2.6.8  impact of the number block size  42 
2.6.9  impact of the block overlap ratio  43 
2.7  emotion recognition based acoustic features  43 
2.7.1  mfcc related features extraction  43 
2.7.2  speech emotion recognition based on n-lstm  44 
2.7.3  attention-based n-bilstm recognition model (nattbilstm)  45 
2.8  validation for speech emotion recognition  46 
2.8.1  datasets  46 
2.8.2  speech emotion recognition using n-lstm  47 
2.8.3  speech emotion recognition using n-attbilstm  48 
2.9  conclusions  50
references  51 
chapter 3  ga-convolutional neural works and action classification  56 
3.1  introduction  56 
3.2  related work  58 
3.2.1  invariant features/descriptors of motion  58 
3.2.2  skeleton based human motion recognition  60 
3.3  ga-convolutional neural works  61 
3.3.1  geometric algebra: an outline  61 
3.3.2  joints angle and orientation human ture descriptor based on geometric algebra  64 
3.4  skeleton-based ensemble human motion recognition  66 
3.5   validation for motion recognition  67 
3.5.1  szu 3d skeleton & orientation exercise action recognition dataset  67 
3.5.2  sysu 3d human-object interaction dataset  69 
3.6  reduced geometric algebra (rga)  71 
3.6.1  the basics of rga  71 
3.6.2  convolution in rga  73 
3.7  convolutional neural works based on reduced geometric algebra  74 
3.7.1  the structure of rga-ns  74 
3.7.2  rga neuron model  74 
3.7.3  rga multilayer perceptron (rga-mlp) and its learning algorithm  75 
3.7.4  rga-ns  77 
3.8  classification experiments and analysis  79 
3.8.1  datasets  79 
3.8.2  experimental setup  80 
3.8.3  3d geometrical shapes classification  81 
3.9  conclusions  81 
references  82 
chapter 4  object tracking  85 
4.1  introduction  85 
4.2  related work  88
4.2.1  siamfc tracker  88 
4.2.2  optical flow for object tracking  89 
4.2.3  attention model  89 
4.3  main work  89 
4.3.1  tv  89 
4.3.2  aggregation using optical flow  90 
4.3.3  sequential scoring model  91 
4.3.4  aggregation between different frames  92 
4.3.5  optical flow attention model  93 
4.3.6  online tracking  95 
4.4  validation for object tracking  96 
4.4.1   results on vot  96 
4.4.2   ablation analysis  97 
4.5  the static-adaptive tracking algorithm  99 
4.5.1  virtual keypoints  100 
4.5.2  fuzzy logic judgment  102 
4.5.3  weight-based correspondence  103 
4.6  results  104 
4.6.1  parison with its baseline  105 
4.6.2  putation speed evaluation  105 
4.7  conclusions  107 
references  107 
chapter 5  cross-modal hashing  112 
5.1  introduction  112 
5.2  related concepts  114 
5.2.1  hamming distance sorting  114 
5.2.2  hash table retrieval  114 
5.2.3  similarity measures  114 
5.2.4  performance evaluation criteria  116 
5.2.5  element-wise sign function  117 
5.3  methodologies  118 
5.3.1  data-independent methods  118 
5.3.2  single-modal methods  119
5.3.3  multi/cross-modal methods  121 
5.3.4  deep hashing methods  124 
5.4  evaluation benchmarks  131 
5.4.1  datasets  131 
5.4.2  published experimental results  132 
5.5  discussion  135 
5.5.1  qualitative parison  135 
5.5.2  sible development trends  137 
5.6  the proed mdch  137 
5.6.1  notations  138 
5.6.2   problem definition  139 
5.6.3  hashing code learning  139 
5.6.4  optimization  140 
5.6.5  out-of-sample extension  142 
5.7  validation for the proed mdch  143 
5.7.1  datasets  143 
5.7.2  evaluation and baselines  144 
5.7.3  implementation details  144 
5.7.4  performance  145 
5.8  conclusions  147 
5.9  appendix  147 
references  148 
chapter 6  deep cross-modal hashing  155 
6.1  introduction  155 
6.2  related work  156 
6.3   the proed approach sdch  158 
6.3.1  notation  159 
6.3.2  problem definition  160 
6.3.3  features learning part  161 
6.3.4  hash codes learning part  162 
6.3.5  optimization  164 
6.4  validation for the proed sdch  166 
6.4.1  datasets  166
6.4.2  evaluation and baseline  166 
6.4.3  performance  167 
6.4.4  ablation extents of sdch  169 
6.5  proof of the first item in eq.(6.3)  171 
6.6  proof of the second item in eq.(6.3)  172 
6.7  proof of the second item in eq.(6.10)  174 
6.8  hybrid representation learning for cross-modal retrieval  175 
6.8.1  modality-friendly and modality-mutual representation learning  176 
6.8.2  hybrid representation learning with a two-level work  177 
6.8.3  hybrid representation correlation learning  178 
6.9  validation for the method based on hrl  178 
6.9.1  experimental setup &





Related Books
Related Papers (PDF Download free)

China Scientific Book Services Co. Ltd., CSBS Bookstore  Join Our Mailing List
Address:  A-1120, Kingsound (Jiahao) International Center, No.116, Zi Zhu Yuan Road, Haidian District, Beijing 100097, China
TeL: +86-10-58930115, Fax: +86-10-80115555-702074  Email: hceis@hceis.com  All Right Reserved