深度学习视频理解

一、视频理解

视频理解(Video Understanding)

image-20231012165330660

image-20231012165134206

图像分类是视频理解的基础,列出经典的图像分类网络

2 经典网络结构

  • LeNet-5(LeCun et al.,1998)image-20231012170419432

  • AlexNet(Krizhevsky et al.,2012)image-20231012170850504

    image-20231012171216271

  • VGGNet(Simonyan & Zisserman,2015)

    image-20231012171346362

  • GoogLeNet(Szegedy et al.,2015)image-20231012171648117image-20231012171659722image-20231012171712242

  • Inception V2(Szegedy et al.,2016)image-20231012171807983

  • ResNet(Residual Network,残差网络)(He et al.,2016a)

image-20231012172041694

  • preResNet(pre-activation ResNet,预先激活的ResNet)(He et al.,2016b)

    image-20231012172250309

....太多不一一列举了...

经典图像分类模型

image-20231012190833093

经典时序模型

image-20231012190801057