- 电子工业出版社
- 9787121529368
- 1-1
- 16开
- 2026-06
- 640
- 工学
- 计算机类
- 计算机科学与技术
- 本科 研究生及以上
内容简介
本教材适用于高等院校计算机科学与技术、软件工程、人工智能专业的研究生和高年级本科生。本书聚焦视觉模式分析领域，以视觉数据为研究对象，属于计算机视觉和模式识别的范畴。全书系统阐述视觉模式分析的基础模型和典型任务的算法原理，并通过 PyTorch 代码实例讲解算法的核心思想，助力读者理解与实践。全书共分10章：第1章简要介绍视觉模式分析领域的发展历程和前沿进展，为读者构建领域整体认知。第2章详细介绍主流的深度学习骨干网络，包括 CNN、RNN（GRU、LSTM、Mamba）、GNN、GAN、Transformer、Diffusion model 等，夯实理论基础。第3章至第10章分别围绕视频动作识别、动作检测（时序和时空角度）、视频描述、视频定位、视觉语义分割、视觉模型压缩、视觉对抗攻防等典型任务展开，每个任务均介绍重要算法和代码实例，涵盖全监督、半监督、弱监督等多种场景，以及模型压缩和对抗攻防等前沿方向。
目录
第 1 章 绪论·································································································1
1.1 视频动作理解 ·····················································································2
1.2 视频描述与定位··················································································2
1.3 视觉语义分割 ·····················································································3
1.4 视觉模型轻量化··················································································3
1.5 视觉模型安全性··················································································4
1.6 本章习题 ···························································································4
参考文献 ································································································6
第 2 章 基础网络结构 ·····················································································8
2.1 CNN ································································································8
2.1.1 AlexNet ·························································································8
2.1.2 ResNet ··························································································9
2.2 VGG ······························································································ 11
2.3 RNN ······························································································ 12
2.3.1 LSTM ························································································· 12
2.3.2 GRU ··························································································· 13
2.4 Diffusion ························································································· 15
2.5 Transformer ······················································································ 16
2.6 GNN ······························································································ 17
2.7 Mamba ··························································································· 18
2.8 GAN ······························································································ 19
2.9 本章习题 ························································································· 19
参考文献 ······························································································ 20
第 3 章 动作识别 ························································································· 21
3.1 任务介绍 ························································································· 21
VI | 视觉模式分析及实践
3.2 方法总览 ························································································· 22
3.2.1 概况 ··························································································· 22
3.2.2 基于双流卷积神经网络的动作识别 ···················································· 22
3.2.3 基于三维卷积神经网络的方法 ·························································· 24
3.2.4 基于循环神经网络的动作识别 ·························································· 24
3.2.5 基于 Transformer 的方法 ·································································· 25
3.2.6 全监督点云动作识别 ······································································ 25
3.2.7 半监督点云动作识别 ······································································ 26
3.2.8 自监督点云动作识别 ······································································ 27
3.3 典型方法 ························································································· 27
3.3.1 基于双流卷积神经网络的 RGB 动作识别 ············································ 27
3.3.2 基于三维卷积神经网络的 RGB 动作识别 ············································ 32
3.3.3 基于循环神经网络的 RGB 动作识别 ·················································· 34
3.3.4 基于 Transformer 的 RGB 动作识别 ···
1.1 视频动作理解 ·····················································································2
1.2 视频描述与定位··················································································2
1.3 视觉语义分割 ·····················································································3
1.4 视觉模型轻量化··················································································3
1.5 视觉模型安全性··················································································4
1.6 本章习题 ···························································································4
参考文献 ································································································6
第 2 章 基础网络结构 ·····················································································8
2.1 CNN ································································································8
2.1.1 AlexNet ·························································································8
2.1.2 ResNet ··························································································9
2.2 VGG ······························································································ 11
2.3 RNN ······························································································ 12
2.3.1 LSTM ························································································· 12
2.3.2 GRU ··························································································· 13
2.4 Diffusion ························································································· 15
2.5 Transformer ······················································································ 16
2.6 GNN ······························································································ 17
2.7 Mamba ··························································································· 18
2.8 GAN ······························································································ 19
2.9 本章习题 ························································································· 19
参考文献 ······························································································ 20
第 3 章 动作识别 ························································································· 21
3.1 任务介绍 ························································································· 21
VI | 视觉模式分析及实践
3.2 方法总览 ························································································· 22
3.2.1 概况 ··························································································· 22
3.2.2 基于双流卷积神经网络的动作识别 ···················································· 22
3.2.3 基于三维卷积神经网络的方法 ·························································· 24
3.2.4 基于循环神经网络的动作识别 ·························································· 24
3.2.5 基于 Transformer 的方法 ·································································· 25
3.2.6 全监督点云动作识别 ······································································ 25
3.2.7 半监督点云动作识别 ······································································ 26
3.2.8 自监督点云动作识别 ······································································ 27
3.3 典型方法 ························································································· 27
3.3.1 基于双流卷积神经网络的 RGB 动作识别 ············································ 27
3.3.2 基于三维卷积神经网络的 RGB 动作识别 ············································ 32
3.3.3 基于循环神经网络的 RGB 动作识别 ·················································· 34
3.3.4 基于 Transformer 的 RGB 动作识别 ···
