视频动作识别--Two-Stream Convolutional Networks for Action Recognition in Videos

Two-Stream Convolutional Networks for Action Recognition in Videos NIPS2014 http://www.robots.ox.ac.uk/~vgg/software/two_stream_action/

2 Two-stream architecture for video recognition 视频可以很自然的被分为 空间部分和时间部分，空间部分主要对应单张图像中的 appearance，传递视频中描述的场景和物体的相关信息。时间部分对应连续帧的运动，包含物体和观察者（相机）的运动信息。

Each stream is implemented using a deep ConvNet, softmax scores of which are combined by late fusion. We consider two fusion methods: averaging and training a multi-class linear SVM [6] on stacked L 2 -normalised softmax scores as features.

Spatial stream ConvNet： 这就是对单张图像进行分类，我们可以使用最新的网络结构，在图像分类数据库上预训练

3 Optical flow ConvNets the input to our model is formed by stacking optical flow displacement fields between several consecutive frames. Such input explicitly describes the motion between video frames, which makes the recognition easier 对于 Optical flow ConvNets 我们将若干连续帧图像对应的光流场输入到 CNN中，这种显示的运动信息可以帮助动作分类。

Trajectory stacking，作为另一种运动表达方式，我们可以将运动轨迹信息输入 CNN

Bi-directional optical flow 双向光流的计算

Mean flow subtraction： 这算是一种输入的归一化了，将均值归一化到 0 It is generally beneficial to perform zero-centering of the network input, as it allows the model to better exploit the rectification non-linearities In our case, we consider a simpler approach: from each displacement field d we subtract its mean vector.

Individual ConvNets accuracy on UCF-101

Temporal ConvNet accuracy on HMDB-51

Two-stream ConvNet accuracy on UCF-101

Mean accuracy (over three splits) on UCF-101 and HMDB-51

0 条评论

相关文章

1084

22310

《计算机图形学基础（OpenGL版）》勘误表

T2=[cos600∘sin600∘0−sin600∘cos600∘0001]=[−1/2−3/203/2−1/20001]T_2= \left[ \begin...

914

711

36915

903

672

5215

快速去阴影--Fast Shadow Detection from a Single Image Using a Patched Convolutional Neural Network

Fast Shadow Detection from a Single Image Using a Patched Convolutional Neural N...

2099