- 生理机能中的深度学习(英文版)
- - 作者：编者:曹文明//曹桂涛
  - 出版社：科学
  - ISBN：9787030705730
  - 出版日期：2022/01/01
  - 页数：194
- 售价：139.6

内容大纲
随着年龄的增长，生理机能的下降，如果不采取必要的措施，会导致高血压、心脏病等一些疾病的并发症。如果老年人能够进行生理评估，这些风险可以大大降低。近年来，由于预防对老年人的重要性，许多研究人员将注意力集中在对人体生理功能的评估上。写这本书是为了介绍我们认为是生理功能评估的关键技术，帮助读者更好地了解生理功能评估。
作者介绍
目录
Preface
Chapter 1  Motion Detection with Skeleton Tracking
  1.1  Introduction
    1.1.1  Fog Computing-based Methods for Physiological Function Assessment
    1.1.2  Motion Detection with Skeleton Tracking for Physiological Function Assessment
  1.2  Motion Detection Method
    1.2.1  Physiological Function Assessment Based on Fog Computing
    1.2.2  Motion Recognition with RGB-D Cameras
  1.3  Validation for Motion Detection
    1.3.1  Comparison with Digital Angle Protractor
    1.3.2  Effect of Motion Detection
    1.3.3  Effect of Gait Analysis
  1.4  3D Stcreo Human Trajectory Learning and Prediction
    1.4.1  Method Overview
    1.4.2  Twin Deep Neural Networks with Stereo Constraint for 3D Human Pose Estimation
    1.4.3  Constructing the Forward and Backward Prediction Networks
  1.5  Validation for 3D Pedestrian Trajectory Prediction
    1.5.1  3D Pedestrian Trajectory Dataset
    1.5.2  Evaluation Metrics and Protocol
    1.5.3  Performance Evaluations and Comparison
  1.6  Conclusions
  References
Chapter 2  Facial Expression and Emotion Recognition
  2.1  Introduction
  2.2  Methodologies
    2.2.1  Patch Manifold
    2.2.2  Patch Discriminative Analysis
    2.2.3  Optimization
  2.3  Patch Discriminative Analysis Network
  2.4  Facial Expression Recognition Validation
  2.5  Methodologies Based on LMDAP
    2.5.1  Discriminant Embedding Space
    2.5.2  Convolutional Kernel Learning Based on the Proposed LMDAP Algorithm
    2.5.3  Local Manifold Discriminant Analysis Projections Network
  2.6  Validation for Method Based on LMDAP
    2.6.1  Datasets
    2.6.2  Parameter Setting
    2.6.3  Face Recognition Experiments on Extended Yale B Dataset
    2.6.4  Face Recognition Experiments on AR Dataset
    2.6.5  Face Recognition Experiments on FERET Dataset
    2.6.6  Face Verification: YTF
    2.6.7  Impact of Parameters
    2.6.8  Impact of the Number Block Size
    2.6.9  Impact of the Block Overlap Ratio
  2.7  Emotion Recognition Based Acoustic Features
    2.7.1  MFCC Related Features Extraction
    2.7.2  Speech Emotion Recognition Based on CNN-LSTM
    2.7.3  Attention-based CNN-BiLSTM Recognition Model (CNN AttBiLSTM)
  2.8  Validation for Speech Emotion Recognition
    2.8.1  Datasets

    2.8.2  Speech Emotion Recognition Using CNN-LSTM
    2.8.3  Speech Emotion Recognition Using CNN-AttBiLSTM
  2.9  Conclusions
  References
Chapter 3  GA-convolutional Neural Networks and Action Classification
  3.1  Introduction
  3.2  Related Work
    3.2.1  Invariant Features/Descriptors of Motion
    3.2.2  Skeleton Based Human Motion Recognition
  3.3  GA-convolutional Neural Networks
    3.3.1  Geometric Algebra: An Outline
    3.3.2  Joints Angle and Orientation Human Posture Descriptor Based on Geometric Algebra
  3.4  Skeleton-based Ensemble Human Motion Recognition
  3.5  Validation for Motion Recognition
    3.5.1  SZU 3D Skeleton &: Orientation Exercise Action Recognition Dataset
    3.5.2  SYSU 3D Human-object Interaction Dataset
  3.6  Reduced Geometric Algebra (RGA)
    3.6.1  The Basics of RGA
    3.6.2  Convolution in RGA
  3.7  Convolutional Neural Networks Based on Reduced Geometric Algebra
    3.7.1  The Structure of RGA-CNNs
    3.7.2  RGA Neuron Model
    3.7.3  RGA Multilayer Perceptron (RGA-MLP) and Its Learning Algorithm
    3.7.4  RGA-CNNs
  3.8  Classification Experiments and Analysis
    3.8.1  Datasets
    3.8.2  Experimental Setup
    3.8.3  3D Geometrical Shapes Classification
  3.9  Conclusions
  References
Chapter 4  Object Tracking
  4.1  Introduction
  4.2  Related Work
    4.2.1  SiamFC Tracker
    4.2.2  Optical Flow for Object Tracking
    4.2.3  Attention Model
  4.3  Main Work
    4.3.1  TVNet
    4.3.2  Aggregation Using Optical Flow
    4.3.3  Sequential Scoring Model
    4.3.4  Aggregation Between Different Frames
    4.3.5  Optical Flow Attention Model
    4.3.6  Online Tracking
  4.4  Validation for Object Tracking
    4.4.1  Results on VOT
    4.4.2  Ablation Analysis
  4.5  The Static-adaptive Tracking Algorithm
    4.5.1  Virtual Keypoints
    4.5.2  Fuzzy Logic Judgment
    4.5.3  Weight-Based Correspondence

  4.6  Results
    4.6.1  Comparison with Its Baseline
    4.6.2  Computation Speed Evaluation
  4.7  Conclusions
  References
Chapter 5  Cross-modal Hashing
  5.1  Introduction
  5.2  Related Concepts
    5.2.1  Hamming Distance Sorting
    5.2.2  Hash Table Retrieval
    5.2.3  Similarity Measures
    5.2.4  Performance Evaluation Criteria
    5.2.5  Element-wise Sign ~nction
  5.3  Methodologies
    5.3.1  Data-independent Methods
    5.3.2  Single-modal Methods
    5.3.3  Multi/Cross-modal Methods
    5.3.4  Deep Hashing Methods
  5.4  Evaluation Benchmarks
    5.4.1  Datasets
    5.4.2  Published Experimental Results
  5.5  Discussion
    5.5.1  Qualitative Comparison
    5.5.2  Possible Development Trends
  5.6  The Proposed MDCH
    5.6.1  Notations
    5.6.2  Problem Definition
    5.6.3  Hashing Code Learning
    5.6.4  Optimization
    5.6.5  Out-of-Sample Extension
  5.7  Validation for the Proposed MDCH
    5.7.1  Datasets
    5.7.2  Evaluation and Baselines
    5.7.3  Implementation Details
    5.7.4  Performance
  5.8  Conclusions
  5.9  Appendix
  References
Chapter 6  Deep Cross-modal Hashing
  6.1  Introduction
  6.2  Related Work
  6.3  The Proposed Approach SDCH
    6.3.1  Notation
    6.3.2  Problem Definition
    6.3.3  Features Learning Part
    6.3.4  Hash Codes Learning Part
    6.3.5  Optimization
  6.4  Validation for the Proposed SDCH
    6.4.1  Datasets
    6.4.2  Evaluation and Baseline

    6.4.3  Performance
    6.4.4  Ablation Extents of SDCH
  6.5  Proof of the First Item in Eq.(6.3)
  6.6  Proof of the Second Item in Eq.(6.3)
  6.7  Proof of the Second Item in Eq.(6.10)
  6.8  Hybrid Representation Learning for Cross-modal Retrieval
    6.8.1  Modality-friendly and Modality-mutual Representation Learning
    6.8.2  Hybrid Representation Learning with a Two-level Network
    6.8.3  Hybrid Representation Correlation Learning
  6.9  Validation for the Method Based on HRL
    6.9.1  Experimental Setup
    6.9.2  Details of the HRL Method
    6.9.3  Evaluation Metrics
    6.9.4  Comparison with State-of-the-art Methods
    6.9.5  Experimental Results
    6.9.6  Baseline Experiments
  6.10  Conclusions
  References

内容大纲

作者介绍

目录

同类热销排行榜

推荐书目